https://peertube.laas.fr/about/instancehttps://peertube.laas.fr/videos/localhttps://peertube.laas.fr/w/oL4BBBs5qyY9GvJHyUFUFohttps://peertube.laas.fr/lazy-static/thumbnails/b85000ed-bb3b-498e-9b3b-38be162df1d4.jpghrp2-1stdayTime lapse of HRP-2 unboxing at LAAS (june 2006)https://peertube.laas.fr/static/streaming-playlists/hls/b85000ed-bb3b-498e-9b3b-38be162df1d4/cabab23b-b95e-4df1-a35c-87cf3f7dc9f5-master.m3u8https://peertube.laas.fr/videos/embed/oL4BBBs5qyY9GvJHyUFUFo1150642019-06-22T09:39:06.819ZYESArchives Robotique NOhttps://peertube.laas.fr/w/gkf6sJF8h2pvhejVzHEcWEhttps://peertube.laas.fr/lazy-static/thumbnails/7c28e5b9-7615-4726-803e-4dbe8f45914e.jpgkarmaSlam-320x240Simultaneous Localization and Mapping with the Karma blimp (2005)https://peertube.laas.fr/static/streaming-playlists/hls/7c28e5b9-7615-4726-803e-4dbe8f45914e/34e40d2d-ab60-4195-9a8e-3b324f701358-master.m3u8https://peertube.laas.fr/videos/embed/gkf6sJF8h2pvhejVzHEcWE730272019-06-22T09:46:16.284ZYESArchives Robotique NOhttps://peertube.laas.fr/w/8jVhFE8pH8PaMyNVwfcyFRhttps://peertube.laas.fr/lazy-static/thumbnails/3b5432ba-b741-462e-b5bc-104a894cb91f.jpglama2001-640x480-15fpsNavigation of the Lama robot (July 2001)https://peertube.laas.fr/static/streaming-playlists/hls/3b5432ba-b741-462e-b5bc-104a894cb91f/15a99203-e31a-4358-b3f9-7bdf0efb7c4d-master.m3u8https://peertube.laas.fr/videos/embed/8jVhFE8pH8PaMyNVwfcyFR2470322019-06-22T09:49:11.873ZYESArchives Robotique NOhttps://peertube.laas.fr/w/uvD3qQ4CCddcuDNUyfGXWnhttps://peertube.laas.fr/lazy-static/thumbnails/e6e34798-6582-4beb-908d-dc551e98d12d.jpgRackhamSpaceCityLe robot guide Rackham à la cité de l'espace en 2004https://peertube.laas.fr/static/streaming-playlists/hls/e6e34798-6582-4beb-908d-dc551e98d12d/d1b8ce13-4b8a-44b0-80dd-e572f4135099-master.m3u8https://peertube.laas.fr/videos/embed/uvD3qQ4CCddcuDNUyfGXWn4490242019-06-22T13:17:01.194ZYESArchives Robotique NOhttps://peertube.laas.fr/w/xfQaiHjirTmFJKL9LdcBu5https://peertube.laas.fr/lazy-static/thumbnails/fd1d6423-51b3-4408-9b5f-a312e093a140.jpghilare-cnrs-a2-1982Documentaire sur le robot Hilare réalisé en 1982 par le CNRS et diffusé sur Antenne2https://peertube.laas.fr/static/streaming-playlists/hls/fd1d6423-51b3-4408-9b5f-a312e093a140/f7424870-7363-4192-96e7-97158e6045c7-master.m3u8https://peertube.laas.fr/videos/embed/xfQaiHjirTmFJKL9LdcBu55835792019-06-22T13:24:40.547ZYESArchives Robotique NOhttps://peertube.laas.fr/w/31HBt8b2Awh9WvNoSxJ4Qghttps://peertube.laas.fr/lazy-static/thumbnails/104bebdb-f2e6-4d02-9ab9-39087c41909b.jpgThe rover Adam on the CNES experimental site (1994)A pretty old flick, extracted from a TV report entitled "Cars on Mars", realized and broadcasted by the BBC in the "Tomorrow's world" programme. It shows the rover Adam reaching autonomously a visual target, modelling its environment with a home made 3D scanning laser range finder, and planning trajectories on the built digital elevation map. At that time, it took 3 minutes to gather a 100x100 points 3D image...https://peertube.laas.fr/static/streaming-playlists/hls/104bebdb-f2e6-4d02-9ab9-39087c41909b/050989c2-ae3f-4deb-bdc2-38412f588e60-master.m3u8https://peertube.laas.fr/videos/embed/31HBt8b2Awh9WvNoSxJ4Qg915542019-06-22T13:28:05.808ZYESArchives Robotique NOhttps://peertube.laas.fr/w/cbS5ZqqC1C11exzCyZSVhjhttps://peertube.laas.fr/lazy-static/thumbnails/5a98d45f-1019-4e96-8dde-8299b9192106.jpgRoboscopieOn the 14th of October 2011, we performed for a general public audience (over 300 persons) a 18 min long live theatre play, acted by professional actor Xavier Brossard and the LAAS/CNRS PR2 robot. The play was created and directed by Nicolas Darrot, a mixed-media artist from Paris. It talks about how the robot and the human are trying to build a common world where they can understand and help each other. The performance was presented at Salle du Cap, Toulouse, France. The PR2 has been programmed in a 2-months course, reusing several software components developed at LAAS/CNRS, including the 3D environment for situation assessment SPARK, the ontology-based knowledge base ORO and the natural-language processor Dialogs. This video abstract presents the storyline of the play, and underlines some of the significant outcome for the human-robot interaction community. https://hal.laas.fr/hal-00667021v1 Credits ---------- Direction: Nicolas Darrot Original idea: Rachid Alami, Nicolas Darrot Interpreted by: Xavier Brossard Robot programming: Séverin Lemaignan Mamoun Gharbi Nicolas Courbet Matthieu Herrb Jim Mainprice Xavier Broquèrehttps://peertube.laas.fr/static/streaming-playlists/hls/5a98d45f-1019-4e96-8dde-8299b9192106/baca3bca-1174-49cf-b0dc-1294f016426d-master.m3u8https://peertube.laas.fr/videos/embed/cbS5ZqqC1C11exzCyZSVhj10880382019-06-22T15:05:12.071ZLAASCNRSScienceRoboticsPR2YESArchives Robotique NOhttps://peertube.laas.fr/w/7afugxdhuw5q1jgg6N9f7dhttps://peertube.laas.fr/lazy-static/thumbnails/31e1743c-db08-4571-96fc-6f2f2c9d9ce0.jpgD2-Khatib_720pPr. Oussama Khatib talks at LAAS, on Human-Centered Robotics. october 2008 https://peertube.laas.fr/static/streaming-playlists/hls/31e1743c-db08-4571-96fc-6f2f2c9d9ce0/197e1d0b-3990-4d47-a306-ead05a224d97-master.m3u8https://peertube.laas.fr/videos/embed/7afugxdhuw5q1jgg6N9f7d28990222019-06-22T17:54:08.889ZYESArchives Robotique NOhttps://peertube.laas.fr/w/6TUjA7QWgyb1F55fLoV3Tshttps://peertube.laas.fr/lazy-static/thumbnails/2fbcde84-ea84-4cda-8fd5-0f5a1c6d5298.jpgtearing test-720ptearing test-720phttps://peertube.laas.fr/static/streaming-playlists/hls/2fbcde84-ea84-4cda-8fd5-0f5a1c6d5298/9becb60d-317e-4c90-9732-2924fc5614b9-master.m3u8https://peertube.laas.fr/videos/embed/6TUjA7QWgyb1F55fLoV3Ts300122020-06-10T19:16:15.694ZYESTest channelNOhttps://peertube.laas.fr/w/fgjbh4x7DRfE8qC7eitnnThttps://peertube.laas.fr/lazy-static/thumbnails/73834cc4-f0ad-469a-b8b7-6c44fd60b7d1.jpgMove It Task Constructor gives solution with collisionMove It Task Constructor gives solution with collisionhttps://peertube.laas.fr/static/streaming-playlists/hls/73834cc4-f0ad-469a-b8b7-6c44fd60b7d1/ff02edbf-dc5f-40f2-a11d-91320afb0385-master.m3u8https://peertube.laas.fr/videos/embed/fgjbh4x7DRfE8qC7eitnnT268062020-08-31T14:20:26.972ZYESMain yriou channelNOhttps://peertube.laas.fr/w/fGcNj1qcKiMr7WY68aD7UAhttps://peertube.laas.fr/lazy-static/thumbnails/76fcf68d-8509-4257-a3a4-c1d0eca7a8ba.jpgHigh-Frequency Nonlinear MPC of a Manipulator High-Frequency Nonlinear MPC of a Manipulator https://peertube.laas.fr/static/streaming-playlists/hls/76fcf68d-8509-4257-a3a4-c1d0eca7a8ba/4cc1c7bf-db0c-4428-8e2a-f9ce140b8f70-master.m3u8https://peertube.laas.fr/videos/embed/fGcNj1qcKiMr7WY68aD7UA16251372020-11-06T09:27:00.476ZYESMain skleff channelNOhttps://peertube.laas.fr/w/3Md4doTL6cj3AVQDJSjU2Mhttps://peertube.laas.fr/lazy-static/thumbnails/16822d27-3557-4e35-9a0d-ce5b0aea4c27.jpgContact forces pre-integration for the whole body estimation of legged robotsAttached video for ICRA 2021 submitted paper "Contact forces pre-integration for the whole body estimation of legged robots", Médéric Fourmy, Thomas Flayols, Nicolas Mansard, Joan Solàhttps://peertube.laas.fr/static/streaming-playlists/hls/16822d27-3557-4e35-9a0d-ce5b0aea4c27/e754e59a-9cd4-4b30-a18f-5b8c2830094e-master.m3u8https://peertube.laas.fr/videos/embed/3Md4doTL6cj3AVQDJSjU2M550562020-11-06T11:29:04.424ZYESMain mfourmy channelNOhttps://peertube.laas.fr/w/swKZc8RT5Fhn3xtntPiti6https://peertube.laas.fr/lazy-static/thumbnails/d6d90690-3262-4e61-9d03-08a2623726e3.jpgComparison of predictive controllers for locomotion and balance recovery of quadruped robotsAttached video for ICRA 2021 submitted paper "Comparison of predictive controllers for locomotion and balance recovery of quadruped robots", Thomas Corbères, Thomas Flayols, Pierre-Alexandre Léziart, Rohan Budhiraja, Nicolas Mansardhttps://peertube.laas.fr/static/streaming-playlists/hls/d6d90690-3262-4e61-9d03-08a2623726e3/8c2c8742-6a04-40ec-8788-ecdea1ec7c7c-master.m3u8https://peertube.laas.fr/videos/embed/swKZc8RT5Fhn3xtntPiti617801672020-11-06T16:34:25.506ZYESMain tcorberes channelNOhttps://peertube.laas.fr/w/oA2bQ9beLkFeMFRiyMuUW8https://peertube.laas.fr/lazy-static/thumbnails/b6e911ee-728f-4337-a76e-8138a332b583.jpgA hybrid collision model for safety collision control - Solo quadruped experimentsVideo attachment for corresponding ICRA2021 submitted paper Authors : Thibault NOËL, Thomas FLAYOLS, Joseph MIRABEL, Justin CARPENTIER, Nicolas MANSARDhttps://peertube.laas.fr/static/streaming-playlists/hls/b6e911ee-728f-4337-a76e-8138a332b583/ab1df085-19fa-433e-ac63-a2acd40bfe6e-master.m3u8https://peertube.laas.fr/videos/embed/oA2bQ9beLkFeMFRiyMuUW81670922020-11-06T19:04:22.886ZsoloicracollisionYESMain tnoel channelNOhttps://peertube.laas.fr/w/rakM3PzkmXhrVA1wgTWFM8https://peertube.laas.fr/lazy-static/thumbnails/cbc25927-337c-4635-a1bc-153b9aeb4135.jpgMPC experiments on a torque-controlled TalosThis video presents a set of experiments performed with a Crocoddyl based MPC scheme on a whole body torque-controlled Talos. Collision avoidance, center of mass tracking, target tracking and stabilization have been achieved at a 100 Hz MPC frequency with a 2 kHz low-level servo control. https://peertube.laas.fr/static/streaming-playlists/hls/cbc25927-337c-4635-a1bc-153b9aeb4135/03c532b8-7621-460c-9906-428a0d3d424a-master.m3u8https://peertube.laas.fr/videos/embed/rakM3PzkmXhrVA1wgTWFM819102502020-11-09T11:37:47.713ZYESMain edantec channelNOhttps://peertube.laas.fr/w/dxuDnd2J9kwDQWXt8o1c7fhttps://peertube.laas.fr/lazy-static/thumbnails/65935f98-ea53-46ef-9f23-489fa094fcf6.jpgLearning to steer a locomotion contact plannerLearning to steer a locomotion contact plannerhttps://peertube.laas.fr/static/streaming-playlists/hls/65935f98-ea53-46ef-9f23-489fa094fcf6/fb392b1e-7645-4e3b-beaa-7bf4c22d7da0-master.m3u8https://peertube.laas.fr/videos/embed/dxuDnd2J9kwDQWXt8o1c7f1430182020-11-10T16:04:27.490ZYESMain jchemin channelNOhttps://peertube.laas.fr/w/4PmDdBRwFPgB5tPaLDbqydhttps://peertube.laas.fr/lazy-static/thumbnails/1ee81814-3715-4d88-85be-cd3d64cbdfcc.jpgImplementation of a Reactive Walking Controller for the New Open-Hardware Quadruped Solo-12 (old)Updated version here: https://peertube.laas.fr/videos/watch/4a8a1bcf-9bd7-4909-af26-ed304ded7df0 Submission for ICRA 2021 Title of article: Implementation of a Reactive Walking Controller for the New Open-Hardware Quadruped Solo-12 Abstract: This paper aims at showing the dynamic performance and reliability of the low-cost, open-access quadruped robot Solo-12, which is developed within the framework of Open Dynamic Robot Initiative. It presents the implementation of a state-of-the-art control pipeline, close to the one that was previously implemented on Mini Cheetah, which implements a model predictive controller based on the centroidal dynamics to compute desired contact forces in order to track a reference velocity. Different contributions are proposed to speed up the computation process, notably at the level of the state estimation and the whole body controller. Experimental results demonstrate that the robot closely follow the reference velocity while being highly reactive and able to recover from perturbations.https://peertube.laas.fr/static/streaming-playlists/hls/1ee81814-3715-4d88-85be-cd3d64cbdfcc/386e8a6d-a3b0-4c35-b297-b62a95d2f085-master.m3u8https://peertube.laas.fr/videos/embed/4PmDdBRwFPgB5tPaLDbqyd1760642020-11-25T13:31:54.765Zmpclocomotionicra2021soloquadrupedYESMain paleziart channelNOhttps://peertube.laas.fr/w/vhRaNeZjhw4k9evwoiooibhttps://peertube.laas.fr/lazy-static/thumbnails/ed33390e-cf21-449e-98bc-1339ad4b0b3c.jpgtransHumUs: A poetic experience in mobile robotics https://hal.laas.fr/hal-01206067 @ICRA16https://peertube.laas.fr/static/streaming-playlists/hls/ed33390e-cf21-449e-98bc-1339ad4b0b3c/0b0a8aa1-80e2-407c-b201-22ba13565970-master.m3u8https://peertube.laas.fr/videos/embed/vhRaNeZjhw4k9evwoiooib1580122020-11-26T14:48:22.628ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/3fiUMd5xotqWEzHNLJq4aKhttps://peertube.laas.fr/lazy-static/thumbnails/1231ba3f-005f-43be-9315-7d796874cc81.jpgTERRINet 01: Marco TognonART: the Aerial Robotic Testbed at LAAS-CNRShttps://peertube.laas.fr/static/streaming-playlists/hls/1231ba3f-005f-43be-9315-7d796874cc81/4a956336-9da9-4d18-8c0f-e31d6ac5daaf-master.m3u8https://peertube.laas.fr/videos/embed/3fiUMd5xotqWEzHNLJq4aK1086042021-01-27T14:20:09.792ZYESTERRINetNOhttps://peertube.laas.fr/w/kYKC23kB2YQCYHztCJoJHFhttps://peertube.laas.fr/lazy-static/thumbnails/a1ca2b05-af8f-47b7-9f43-42b918280c29.jpgTERRINet 02: Guilhem SaurelHumanoid Robotics at LAAS-CNRShttps://peertube.laas.fr/static/streaming-playlists/hls/a1ca2b05-af8f-47b7-9f43-42b918280c29/b5cadc44-600c-4f21-b32d-0b552c7cb211-master.m3u8https://peertube.laas.fr/videos/embed/kYKC23kB2YQCYHztCJoJHF948022021-01-27T15:02:47.272ZYESTERRINetNOhttps://peertube.laas.fr/w/xsK2fsFZbBbG2bgaijUxgLhttps://peertube.laas.fr/lazy-static/thumbnails/fec72642-11b8-4211-b150-0127e5379f8e.jpgTERRINet 03: Fabian Peller-KonradTERRINet robotic platoforms at KIThttps://peertube.laas.fr/static/streaming-playlists/hls/fec72642-11b8-4211-b150-0127e5379f8e/1b3e20cd-2bc0-4c38-810f-f2b63687a398-master.m3u8https://peertube.laas.fr/videos/embed/xsK2fsFZbBbG2bgaijUxgL1520052021-01-27T15:21:36.666ZYESTERRINetNOhttps://peertube.laas.fr/w/gvbi86oBpE2A9TPBfxN8ijhttps://peertube.laas.fr/lazy-static/thumbnails/7d8bfe6e-e4f4-4d3d-b393-ac7552251208.jpgTERRINet 04: Wesley RoozingUniversity of Twente platforms - Technical overviewhttps://peertube.laas.fr/static/streaming-playlists/hls/7d8bfe6e-e4f4-4d3d-b393-ac7552251208/b035717c-bc88-442b-bcda-5332f0a10f8a-master.m3u8https://peertube.laas.fr/videos/embed/gvbi86oBpE2A9TPBfxN8ij1316042021-01-27T15:52:08.328ZYESTERRINetNOhttps://peertube.laas.fr/w/1QZUxQgEe3a4eMoyKPWR6Khttps://peertube.laas.fr/lazy-static/thumbnails/06d76305-eead-4a63-a2d0-d4466eac9371.jpgTERRINet 05: Florian GosselinCEA LIST’s Saclay Manufacturing And Robotics Technology (SMART) Platformhttps://peertube.laas.fr/static/streaming-playlists/hls/06d76305-eead-4a63-a2d0-d4466eac9371/971118d6-06e4-4da6-9596-9fafac53a76c-master.m3u8https://peertube.laas.fr/videos/embed/1QZUxQgEe3a4eMoyKPWR6K1788002021-01-27T16:25:31.012ZYESTERRINetNOhttps://peertube.laas.fr/w/dA5uwanE9uYsTTJu6b6pYLhttps://peertube.laas.fr/lazy-static/thumbnails/65efb860-9170-4bf8-b32b-3691f2be9da0.jpgTERRINet 06: Giuseppe TortoraNew frontiers and applications in Surgical Robotics through DVRK, the SSSA experience in TERRINethttps://peertube.laas.fr/static/streaming-playlists/hls/65efb860-9170-4bf8-b32b-3691f2be9da0/391be424-5088-4f0d-be42-86e4b0efefc9-master.m3u8https://peertube.laas.fr/videos/embed/dA5uwanE9uYsTTJu6b6pYL1006002021-01-27T17:02:10.332ZYESTERRINetNOhttps://peertube.laas.fr/w/mX6VG7RtJXYyCdtzyjfQEBhttps://peertube.laas.fr/lazy-static/thumbnails/a9a85518-69a6-49b6-b41a-3922abb7da8f.jpgTERRINet 07: Begoña Chiquinquira Arrue UllesGRVC Robotics Lab infrastructures at University of Sevillahttps://peertube.laas.fr/static/streaming-playlists/hls/a9a85518-69a6-49b6-b41a-3922abb7da8f/3e9dd47e-0373-42cb-adff-af2fca245f66-master.m3u8https://peertube.laas.fr/videos/embed/mX6VG7RtJXYyCdtzyjfQEB8610402021-01-27T17:21:34.571ZYESTERRINetNOhttps://peertube.laas.fr/w/rjZg4BsDbT6oap2i8MVhEshttps://peertube.laas.fr/lazy-static/thumbnails/cd1b2453-9053-4e1a-a310-4800a6f70e2e.jpgTERRINet 08: Aurelie ClodicHuman-Robot Interaction at LAAS-CNRShttps://peertube.laas.fr/static/streaming-playlists/hls/cd1b2453-9053-4e1a-a310-4800a6f70e2e/a383b234-5a90-41a6-8661-6510a482d660-master.m3u8https://peertube.laas.fr/videos/embed/rjZg4BsDbT6oap2i8MVhEs649052021-01-27T17:50:26.820ZYESTERRINetNOhttps://peertube.laas.fr/w/1nbgaZ8XtvudEfPxcYo5Mrhttps://peertube.laas.fr/lazy-static/thumbnails/02f4f16e-ed4c-4a76-9b12-6ed807d0c0eb.jpgTERRINet 09: Marco MaggialiiCub, Humanoid Platform, and R1, Personal Humanoid, at IIThttps://peertube.laas.fr/static/streaming-playlists/hls/02f4f16e-ed4c-4a76-9b12-6ed807d0c0eb/5dba66d5-a0a8-48b4-84c9-9d602e696845-master.m3u8https://peertube.laas.fr/videos/embed/1nbgaZ8XtvudEfPxcYo5Mr942022021-01-27T18:12:01.329ZYESTERRINetNOhttps://peertube.laas.fr/w/jDuoJ7Nz34DPeqYjK11dFghttps://peertube.laas.fr/lazy-static/thumbnails/97008330-60ad-4c84-8a68-4cd3664b82f5.jpgTERRINet 10: Ugo PattaciniiCub, Humanoid Platform, and R1, Personal Humanoid, at IIThttps://peertube.laas.fr/static/streaming-playlists/hls/97008330-60ad-4c84-8a68-4cd3664b82f5/b827b940-1e66-4e78-94e6-b88e595cd4d4-master.m3u8https://peertube.laas.fr/videos/embed/jDuoJ7Nz34DPeqYjK11dFg1460012021-01-27T18:29:20.252ZYESTERRINetNOhttps://peertube.laas.fr/w/exvS2fpibF1xG5z7kNcMBchttps://peertube.laas.fr/lazy-static/thumbnails/6dad4348-fc32-44d2-b8aa-778619dfeac5.jpgTERRINet 11: Luca TricerriBlockTest - Modular platform for robot testing and benchmarkinghttps://peertube.laas.fr/static/streaming-playlists/hls/6dad4348-fc32-44d2-b8aa-778619dfeac5/be4c3a51-3b44-4acf-beee-13b74b78766d-master.m3u8https://peertube.laas.fr/videos/embed/exvS2fpibF1xG5z7kNcMBc1216002021-01-27T18:58:45.399ZYESTERRINetNOhttps://peertube.laas.fr/w/nt1sGEHjFzyMGmkGNtkP7rhttps://peertube.laas.fr/lazy-static/thumbnails/add54701-0bb3-4452-a218-2652efc968f9.jpgTERRINet 12: Antoine Barbot, Dennis Kundrat and Florent SeichepineMedical robotics development across scalehttps://peertube.laas.fr/static/streaming-playlists/hls/add54701-0bb3-4452-a218-2652efc968f9/e4a0924f-6f79-449a-bd1e-b6936109f863-master.m3u8https://peertube.laas.fr/videos/embed/nt1sGEHjFzyMGmkGNtkP7r2393012021-01-27T19:21:36.257ZYESTERRINetNOhttps://peertube.laas.fr/w/nScRMPz31DpPECHj8CpEfkhttps://peertube.laas.fr/lazy-static/thumbnails/b112688c-211a-4e81-8257-dd875f5d00cf.jpgTERRINet 13: Olexandr GudozhnicMotion Capture Arena at EPFLhttps://peertube.laas.fr/static/streaming-playlists/hls/b112688c-211a-4e81-8257-dd875f5d00cf/b92d873b-2cee-43f0-ae39-13cf5106abfa-master.m3u8https://peertube.laas.fr/videos/embed/nScRMPz31DpPECHj8CpEfk776002021-01-27T20:10:07.050ZYESTERRINetNOhttps://peertube.laas.fr/w/2W884sbD9AwXwPN1VCP9Eehttps://peertube.laas.fr/lazy-static/thumbnails/0fa7b0ef-6a53-4c27-8ffa-3cac789f9981.jpgTERRINet 14: Esra IçerThe TUM platform in TERRInethttps://peertube.laas.fr/static/streaming-playlists/hls/0fa7b0ef-6a53-4c27-8ffa-3cac789f9981/97f18946-c504-4958-a297-a7f803346a48-master.m3u8https://peertube.laas.fr/videos/embed/2W884sbD9AwXwPN1VCP9Ee917062021-01-27T20:27:11.756ZYESTERRINetNOhttps://peertube.laas.fr/w/g8X1aDFv5AUu97axVFbYThhttps://peertube.laas.fr/lazy-static/thumbnails/7a952ed9-deaf-4bd6-89fb-71c0d853cede.jpgTERRINet 15: Fernando Herrero, Sergi Hernandez Juan and Alejandro López GestosoThe robotics platform of the Barcelona Robot Lab at UPChttps://peertube.laas.fr/static/streaming-playlists/hls/7a952ed9-deaf-4bd6-89fb-71c0d853cede/ea400cdf-481e-4eb4-877e-ea9b7d56ff42-master.m3u8https://peertube.laas.fr/videos/embed/g8X1aDFv5AUu97axVFbYTh905012021-01-27T20:45:56.400ZYESTERRINetNOhttps://peertube.laas.fr/w/nzMNzanhBGXMaMT4V3dYJ3https://peertube.laas.fr/lazy-static/thumbnails/aec7aeef-dd3f-4ddb-b6ca-9a3f772164c6.jpgPhD Diane BuryPlanification de tâches de manipulation pour robots parallèles à câbles http://theses.fr/s251476https://peertube.laas.fr/static/streaming-playlists/hls/aec7aeef-dd3f-4ddb-b6ca-9a3f772164c6/b55b3067-d532-4118-beef-adb4b0674d0d-master.m3u8https://peertube.laas.fr/videos/embed/nzMNzanhBGXMaMT4V3dYJ389680172021-01-27T21:02:18.402ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/nPybp1jKzKgb5Y4MLDe7Qvhttps://peertube.laas.fr/lazy-static/thumbnails/b0b3b341-896d-479d-b44b-119a1815f16d.jpgPhD Melya BoukheddimiSimulation de la marche humaine en utilisant les méthodes|de génération de mouvements issus de la robotique http://theses.fr/2020TOU30105https://peertube.laas.fr/static/streaming-playlists/hls/b0b3b341-896d-479d-b44b-119a1815f16d/ab7ceede-4734-42d8-85c4-9b1a120d2bf2-master.m3u8https://peertube.laas.fr/videos/embed/nPybp1jKzKgb5Y4MLDe7Qv76400372021-01-27T23:49:20.467ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/sdL9FZmFAM1C3kp6UPLdYMhttps://peertube.laas.fr/lazy-static/thumbnails/d455bd1a-eb3e-41d5-ace7-b84099082b9d.jpgPhD Kévin Giraud--EsclasseTowards reactive motion generation on exteroceptive feedback|for generalized locomotion of humanoid robotshttps://peertube.laas.fr/static/streaming-playlists/hls/d455bd1a-eb3e-41d5-ace7-b84099082b9d/5d8ba75f-a6eb-4026-99af-bf4d698942d5-master.m3u8https://peertube.laas.fr/videos/embed/sdL9FZmFAM1C3kp6UPLdYM7778042021-01-28T02:24:22.180ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/w9kB8WpoBnc84nLNExDmhyhttps://peertube.laas.fr/lazy-static/thumbnails/f41c3145-976b-44ab-8f17-c0c1a3b35188.jpgPhD Pierre FernbachModèles réduits fiables et efficaces pour la planification et l'optimisation de mouvement des robots à pattes en environnements contraints. http://theses.fr/2018TOU30232https://peertube.laas.fr/static/streaming-playlists/hls/f41c3145-976b-44ab-8f17-c0c1a3b35188/27487930-3455-4ad9-a438-228ca774c518-master.m3u8https://peertube.laas.fr/videos/embed/w9kB8WpoBnc84nLNExDmhy2908062021-02-02T15:31:58.146ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/sip1unf95AMvCQX3L1LGnbhttps://peertube.laas.fr/lazy-static/thumbnails/d4fb6dbf-4750-4225-bcdf-84a6b03ecacc.jpgPhD Olivier RousselPlanification de mouvement pour tiges élastiques http://theses.fr/2015TOU30355https://peertube.laas.fr/static/streaming-playlists/hls/d4fb6dbf-4750-4225-bcdf-84a6b03ecacc/5d511c3c-e732-44e3-9823-c6b85a20303c-master.m3u8https://peertube.laas.fr/videos/embed/sip1unf95AMvCQX3L1LGnb6946022021-02-12T20:49:02.249ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/rmrf3q6wuChjKac9fgyVXihttps://peertube.laas.fr/lazy-static/thumbnails/cd4ee5dc-7117-4abc-a44e-a2ad3225912b.jpgPhD Andreas OrtheyExploiting structure in humanoid motion planning http://theses.fr/2015INPT0084https://peertube.laas.fr/static/streaming-playlists/hls/cd4ee5dc-7117-4abc-a44e-a2ad3225912b/4fb8dc3e-4f03-44ed-8a02-b8b5bff5f3c5-master.m3u8https://peertube.laas.fr/videos/embed/rmrf3q6wuChjKac9fgyVXi4135032021-02-13T01:31:52.738ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/nz7KkG3M1HofBbGxUyZWYShttps://peertube.laas.fr/lazy-static/thumbnails/aeaf9d49-4ad0-4271-938e-c5ba1d4b81a2.jpgPhD Antonio El KhouryPlanification de mouvements optimaux pour des systèmes anthropomorphes http://theses.fr/2013TOU30065https://peertube.laas.fr/static/streaming-playlists/hls/aeaf9d49-4ad0-4271-938e-c5ba1d4b81a2/13260988-4e1e-43bb-a365-be4eb0e9e2db-master.m3u8https://peertube.laas.fr/videos/embed/nz7KkG3M1HofBbGxUyZWYS3146022021-02-13T02:43:37.226ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/sYevRcAmm8JoVwYF7NNSRMhttps://peertube.laas.fr/lazy-static/thumbnails/da6795c0-2ba7-4458-bdf3-2db69680c1df.jpgPhD Thomas MoulardOptimisation numérique pour la robotique et exécution de trajectoires référencées capteurs http://theses.fr/2012INPT0120https://peertube.laas.fr/static/streaming-playlists/hls/da6795c0-2ba7-4458-bdf3-2db69680c1df/bbdf0bb5-b591-46b9-b504-a793f27441ab-master.m3u8https://peertube.laas.fr/videos/embed/sYevRcAmm8JoVwYF7NNSRM73510102021-02-13T03:59:39.084ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/eJNRxVCiJP3zviXzukMhrRhttps://peertube.laas.fr/lazy-static/thumbnails/6f40ea79-abcd-490e-a616-3a67bf297d93.jpgTiago mobile manipulator performs deburring tasks on an aircraft partThis video illustrates our research in manipulation planning and sensor-based motion control.https://peertube.laas.fr/static/streaming-playlists/hls/6f40ea79-abcd-490e-a616-3a67bf297d93/542b513f-3b0f-4fa1-8133-0744b486189d-master.m3u8https://peertube.laas.fr/videos/embed/eJNRxVCiJP3zviXzukMhrR28902942021-03-11T07:19:58.695ZYESMain florent channelNOhttps://peertube.laas.fr/w/1f6g4YBuvvLXJ6GC7noenDhttps://peertube.laas.fr/lazy-static/thumbnails/01f7a77c-d521-45fc-82b0-ccab28745d3b.jpgconstruction-setSolution to an assembly task computed by the software platform HPPhttps://peertube.laas.fr/static/streaming-playlists/hls/01f7a77c-d521-45fc-82b0-ccab28745d3b/84d51211-3337-449c-aed1-f24904903d7b-master.m3u8https://peertube.laas.fr/videos/embed/1f6g4YBuvvLXJ6GC7noenD3402372021-03-19T09:30:48.172ZYESMain florent channelNOhttps://peertube.laas.fr/w/acRMmwZ4Vh9yJ9WvzDVrshhttps://peertube.laas.fr/lazy-static/thumbnails/4a8a1bcf-9bd7-4909-af26-ed304ded7df0.jpgImplementation of a Reactive Walking Controller for the New Open-Hardware Quadruped Solo-12Submission for ICRA 2021 Title of article: Implementation of a Reactive Walking Controller for the New Open-Hardware Quadruped Solo-12 Abstract: This paper aims at showing the dynamic performance and reliability of the low-cost, open-access quadruped robot Solo-12, which is developed within the framework of Open Dynamic Robot Initiative. It presents the implementation of a state-of-the-art control pipeline, close to the one that was previously implemented on Mini Cheetah, which implements a model predictive controller based on the centroidal dynamics to compute desired contact forces in order to track a reference velocity. Different contributions are proposed to speed up the computation process, notably at the level of the state estimation and the whole body controller. Experimental results demonstrate that the robot closely follow the reference velocity while being highly reactive and able to recover from perturbations.https://peertube.laas.fr/static/streaming-playlists/hls/4a8a1bcf-9bd7-4909-af26-ed304ded7df0/598ef469-0351-422e-a687-f16d490dce30-master.m3u8https://peertube.laas.fr/videos/embed/acRMmwZ4Vh9yJ9WvzDVrsh1790712021-03-25T15:31:11.926Zsololocomotionmpcquadrupedicra2021YESMain paleziart channelNOhttps://peertube.laas.fr/w/nvgBKT3M2kR8bSpAq35xvfhttps://peertube.laas.fr/lazy-static/thumbnails/ae261aee-10f4-4ee3-9e40-45842957b7bc.jpgBaxter robot manipulates boxesA sequence of tasks is automatically discovered during manipulation planning in order to swap the position of the boxes.https://peertube.laas.fr/static/streaming-playlists/hls/ae261aee-10f4-4ee3-9e40-45842957b7bc/b6f4ff55-f702-4178-8761-29725c4aaed1-master.m3u8https://peertube.laas.fr/videos/embed/nvgBKT3M2kR8bSpAq35xvf10042021-04-08T09:01:16.207ZYESMain florent channelNOhttps://peertube.laas.fr/w/kRjrtkZ69fnC4dCmZ81fXFhttps://peertube.laas.fr/lazy-static/thumbnails/a0c0715b-d9c5-445f-acae-513fe61859a5.jpgPath optimization with lazy collision checkingPath optimization algorithm based on collision constraints, automatically built between bodies close to collision.https://peertube.laas.fr/static/streaming-playlists/hls/a0c0715b-d9c5-445f-acae-513fe61859a5/683defc2-c221-4718-9893-81d54f1390c0-master.m3u8https://peertube.laas.fr/videos/embed/kRjrtkZ69fnC4dCmZ81fXF11082021-04-08T09:02:55.675ZYESMain florent channelNOhttps://peertube.laas.fr/w/sqKnFoPkeN7yeu9RtBXw4Ehttps://peertube.laas.fr/lazy-static/thumbnails/d6022f88-c8c0-40e6-9bde-036cb3f7bef4.jpgLocomotion planning expressed as a Manipulation planning problemThe locomotion planning problem is expressed as a Manipulation planning problem.https://peertube.laas.fr/static/streaming-playlists/hls/d6022f88-c8c0-40e6-9bde-036cb3f7bef4/1c625c0e-aa7b-4e8d-a897-0538818a5aea-master.m3u8https://peertube.laas.fr/videos/embed/sqKnFoPkeN7yeu9RtBXw4E10082021-04-08T09:06:17.305ZYESMain florent channelNOhttps://peertube.laas.fr/w/am479AbhTfnzaU3z7EGJyYhttps://peertube.laas.fr/lazy-static/thumbnails/4baf0998-611e-45e6-a5ad-5b74a112a500.jpgMulti-contact locomotion - Stand upA sequence of contact configurations for a multiped robot is computed. Position constraint and static equilibrium constraint are used to create and maintain contacts along the sequence.https://peertube.laas.fr/static/streaming-playlists/hls/4baf0998-611e-45e6-a5ad-5b74a112a500/8f14b66f-3f61-4261-8d24-625d18541fb3-master.m3u8https://peertube.laas.fr/videos/embed/am479AbhTfnzaU3z7EGJyY57092021-04-08T09:21:51.877ZYESMain florent channelNOhttps://peertube.laas.fr/w/fkZ61yZEozCE9wdLnS8Mp8https://peertube.laas.fr/lazy-static/thumbnails/742a40eb-de0b-46c1-b4a1-461196da65e9.jpgElastic rod planning.Integration of external software: QSERL and XDE are used to implement a dedicated steering method for elastic rod planning.(Engine model courtesy of Siemens-KineoCAM).https://peertube.laas.fr/static/streaming-playlists/hls/742a40eb-de0b-46c1-b4a1-461196da65e9/cc45cc73-59bc-4a79-b815-aa6695706c73-master.m3u8https://peertube.laas.fr/videos/embed/fkZ61yZEozCE9wdLnS8Mp845042021-04-08T09:23:26.151ZYESMain florent channelNOhttps://peertube.laas.fr/w/hQoUy1QrJkeTNnWav9GR4Khttps://peertube.laas.fr/lazy-static/thumbnails/8854092f-d4ac-4d7b-b69a-345c24e1eadd.jpgManipulation planning for Romeo Humanoid robotRomeo rotates a placard. Each hand can grasp the placard with one degree of freedom in rotation, thus the space of valid grasps for each hand is continuous.https://peertube.laas.fr/static/streaming-playlists/hls/8854092f-d4ac-4d7b-b69a-345c24e1eadd/bf4817e2-54e7-4a58-a360-88c088352df9-master.m3u8https://peertube.laas.fr/videos/embed/hQoUy1QrJkeTNnWav9GR4K100162021-04-08T09:24:36.434ZYESMain florent channelNOhttps://peertube.laas.fr/w/xfALbnxgJzRsj2BXNmLgEChttps://peertube.laas.fr/lazy-static/thumbnails/fd152247-51d3-4605-973a-8208fed090fc.jpgHPP manipulation softwareDifferents features that can be achieved using the manipulation stack of the Humanoid Path Plannerhttps://peertube.laas.fr/static/streaming-playlists/hls/fd152247-51d3-4605-973a-8208fed090fc/01ca7bd5-ab5a-42df-970a-4be315a859b1-master.m3u8https://peertube.laas.fr/videos/embed/xfALbnxgJzRsj2BXNmLgEC850102021-04-08T09:30:18.332ZYESMain florent channelNOhttps://peertube.laas.fr/w/5mGb8jB3csLWLdrmrWXygGhttps://peertube.laas.fr/lazy-static/thumbnails/23483042-3d29-4a70-8668-6e15f4374426.jpgHeading to a table and grasping it by a humanoid robot TALOSThis video demonstrates the result of Isabelle Maroger practice training in 2019. The robot is reading its position through a Motion Analysis system and generates on line its walking pattern. The motion engine is the one provided by PAL-Robotics. In the second sequence the robot is using the Stack-of-Tasks [1] to hold the table. [1] A versatile generalized inverted kinematics implementation for collaborative working humanoid robots: The stack of tasks, N Mansard, O Stasse, P Evrard, A Kheddar - 2009 International conference on advanced robotics, 2009https://peertube.laas.fr/static/streaming-playlists/hls/23483042-3d29-4a70-8668-6e15f4374426/a3a61491-190f-44aa-8df0-0c5dc05c4321-master.m3u8https://peertube.laas.fr/videos/embed/5mGb8jB3csLWLdrmrWXygG2910172021-05-11T13:19:43.591Zgrasping tablehumanoid robotTALOSYESMain ostasse channelNOhttps://peertube.laas.fr/w/fr84c9R97dNDLdt2jcrRTwhttps://peertube.laas.fr/lazy-static/thumbnails/74e1e220-c22d-478b-8c51-39a45223bc28.jpgHuman Trajectory Prediction Model and its Coupling with a Walking Pattern Generator for TALOS (v2)In order to smoothly perform interactions between a humanoid robot and a human, knowledge about the human locomotion can be efficiently used. Indeed, in a human-robot collaboration, a prediction model of the human behaviour allows the robot to act proactively. In this paper, an optimal control based model predicting the human Center of Mass(CoM) trajectory during gait is presented. A Walking PatternGenerator (WPG) based on non-linear model predictive controlis, then, introduced in order to generate the robot CoM and footsteps along the predicted trajectory. The combination of the human trajectory prediction model and this new WPG aims to allow the robot to proactively walk along with a human instead of passively follow him. These models have been tested in simulation on Gazebo on a TALOS humanoid robot model. To perform the CoM and foot trajectories computed by the WPG, a real-time whole-body controller is used. This controller is a Quadratic Program which solves the inverse dynamics of the robot at torque level.https://peertube.laas.fr/static/streaming-playlists/hls/74e1e220-c22d-478b-8c51-39a45223bc28/6afc1e56-fd69-4db0-a0e9-fe06dd0fd5ea-master.m3u8https://peertube.laas.fr/videos/embed/fr84c9R97dNDLdt2jcrRTw3450132021-05-11T13:51:25.599Zwalkinghumanoid robotTALOShuman modelYESMain ostasse channelNOhttps://peertube.laas.fr/w/3SABJk3JJER2aCnCY8FA5ihttps://peertube.laas.fr/lazy-static/thumbnails/1742cc78-10f6-41ab-b066-a4295c6209c9.jpg3D locomotion planning from LIDAR dataThis video shows the capabilities of our locomotion planner HPP-LOCO and its coupling with the LIDAR-based perception. This result has been obtained in the frame of the project ANR LOCO-3D, using the robot TALOS in collaboration with PAL-Robotics in the EU project Memory of Motion.https://peertube.laas.fr/static/streaming-playlists/hls/1742cc78-10f6-41ab-b066-a4295c6209c9/a83b1467-1518-4c1d-b0ac-3c83326cc358-master.m3u8https://peertube.laas.fr/videos/embed/3SABJk3JJER2aCnCY8FA5i248022021-06-03T19:51:05.705ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/xetmysm669vL7Ckbex8kLyhttps://peertube.laas.fr/lazy-static/thumbnails/fcecd344-7ef2-46dd-9352-0962c97bc6ec.jpgHPP loco using the reachability approximationExample emphasizing the main concept of the locomotion planner HPP-LOCOhttps://peertube.laas.fr/static/streaming-playlists/hls/fcecd344-7ef2-46dd-9352-0962c97bc6ec/68091e45-fb97-4dc6-8f20-166f1f86c116-master.m3u8https://peertube.laas.fr/videos/embed/xetmysm669vL7Ckbex8kLy16042021-06-03T19:59:39.754ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/xnMG16b1GuhopMqDgL9Mwvhttps://peertube.laas.fr/lazy-static/thumbnails/fe16132c-69d8-4d57-b2de-58b2d7c828dd.jpgHRP-2 crossing the "debris" platformsHRP-2 crossing the "debris" platformshttps://peertube.laas.fr/static/streaming-playlists/hls/fe16132c-69d8-4d57-b2de-58b2d7c828dd/2cddd285-6175-4dd2-9435-294d8e7d9c8d-master.m3u8https://peertube.laas.fr/videos/embed/xnMG16b1GuhopMqDgL9Mwv17052021-06-03T20:00:12.260ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/edy2BmiKpX92KLEwAPBfphhttps://peertube.laas.fr/lazy-static/thumbnails/6b077732-ffa9-454a-9e18-aa16b1afbe66.jpgTalos "Pyrene" crossing the debris in torque control modeTalos "Pyrene" crossing the debris in torque control modehttps://peertube.laas.fr/static/streaming-playlists/hls/6b077732-ffa9-454a-9e18-aa16b1afbe66/63c87e62-ad31-4bf7-88f1-3d16ed34d78e-master.m3u8https://peertube.laas.fr/videos/embed/edy2BmiKpX92KLEwAPBfph340582021-06-03T20:01:05.912ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/fDeCB9KssmaoKwrVvU3PvKhttps://peertube.laas.fr/lazy-static/thumbnails/7692dc78-c183-4e99-8ccc-cb90bff68cc9.jpgHRP-2 taking large stepsHRP-2 taking large stepshttps://peertube.laas.fr/static/streaming-playlists/hls/7692dc78-c183-4e99-8ccc-cb90bff68cc9/3f021626-88a7-4646-a06a-6063b9b229ea-master.m3u8https://peertube.laas.fr/videos/embed/fDeCB9KssmaoKwrVvU3PvK57022021-06-03T20:02:34.151ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/5yqf3vvpJZjQySKLLtrS9ehttps://peertube.laas.fr/lazy-static/thumbnails/24eb4b86-740f-4b8f-bc51-7de5df2a017d.jpgHRP-2 climbing the stairs, following a movement automatically planned using HPP-LocoHRP-2 climbing the stairs, following a movement automatically planned using HPP-Locohttps://peertube.laas.fr/static/streaming-playlists/hls/24eb4b86-740f-4b8f-bc51-7de5df2a017d/f197ff24-5129-4998-94d2-cdd27b0f2dc8-master.m3u8https://peertube.laas.fr/videos/embed/5yqf3vvpJZjQySKLLtrS9e39072021-06-03T20:04:33.125ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/1y4WnakEtW3W8tEmex8vh9https://peertube.laas.fr/lazy-static/thumbnails/047a3a23-66d7-40d2-818b-38094d0bcae4.jpgFirst steps of Solo following a pattern planned by HPP-LocoFirst steps of Solo following a pattern planned by HPP-Locohttps://peertube.laas.fr/static/streaming-playlists/hls/047a3a23-66d7-40d2-818b-38094d0bcae4/2580cb4e-9349-4242-af58-62190249d48d-master.m3u8https://peertube.laas.fr/videos/embed/1y4WnakEtW3W8tEmex8vh9140102021-06-03T20:05:52.964ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/9KeSH3su5cFibLCsuoP8SNhttps://peertube.laas.fr/lazy-static/thumbnails/46d2a447-40d9-469d-bb9d-cb187dd68a36.jpgTalos slaloming in simulationMotion planned using HPP-loco with the step optimizer SL1Mhttps://peertube.laas.fr/static/streaming-playlists/hls/46d2a447-40d9-469d-bb9d-cb187dd68a36/143b1254-6b05-4a93-bfa1-95759b9cb37d-master.m3u8https://peertube.laas.fr/videos/embed/9KeSH3su5cFibLCsuoP8SN58032021-06-03T20:07:22.075ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/m4uQUcA4rGDcozrKb466Ybhttps://peertube.laas.fr/lazy-static/thumbnails/a273c79a-ab33-4dbb-bf53-83f6d53654e6.jpgDynamic simulation of Talos in a 3d environmentPlanned with HPP-Loco SL1M and controlled in a complete (closed-loop) simulation with TSID.https://peertube.laas.fr/static/streaming-playlists/hls/a273c79a-ab33-4dbb-bf53-83f6d53654e6/c5c31338-ccf6-4eec-923c-1382732eead2-master.m3u8https://peertube.laas.fr/videos/embed/m4uQUcA4rGDcozrKb466Yb40052021-06-03T20:09:18.325ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/gufqfAtGgyQf5odY64bhymhttps://peertube.laas.fr/lazy-static/thumbnails/7d6aca7b-a3bd-4ed2-ac8a-ab6574f52474.jpgHPP-loco running on AnymalDeveloped in Loco-3D and EU Memmo projects, in collaboration of Univ. Oxford.https://peertube.laas.fr/static/streaming-playlists/hls/7d6aca7b-a3bd-4ed2-ac8a-ab6574f52474/d59395d8-3faf-42ac-8f9a-505c075ce6c1-master.m3u8https://peertube.laas.fr/videos/embed/gufqfAtGgyQf5odY64bhym136012021-06-03T20:10:40.597ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/28kF3CDtJwuZMTvrTohFmohttps://peertube.laas.fr/lazy-static/thumbnails/091f7816-24ce-4292-a8c2-6f0961de0b9a.jpgMulticontact locomotion using centroidal optimizationby Justin Carpentier and Nicolas Mansard, IEEE TRO 2018 see https://hal.laas.fr/hal-01520248/file/tro-carpentier-multicontact.pdf Locomotion of legged robots on arbitrary terrain using multiple contacts is yet an open problem. To tackle it, a common approach is to rely on reduced template models (e.g., the linear inverted pendulum). However, most of existing template models are based on some restrictive hypotheses that limit their range of applications. Moreover, reduced models are generally not able to cope with the constraints of the robot complete model, such as the kinematic limits. In this paper, we propose a complete solution relying on a generic template model, based on the centroidal dynamics, able to quickly compute multicontact locomotion trajectories for any legged robot on arbitrary terrains. The template model relies on exact dynamics and is thus not limited by arbitrary assumption. We also propose a generic procedure to handle feasibility constraints due to the robot's whole body as occupancy measures, and a systematic way to approximate them using offline learning in simulation. An efficient solver is finally obtained by introducing an original second-order approximation of the centroidal wrench cone. The effectiveness and the versatility of the approach are demonstrated in several multicontact scenarios with two humanoid robots both in reality and in simulation.https://peertube.laas.fr/static/streaming-playlists/hls/091f7816-24ce-4292-a8c2-6f0961de0b9a/2e2dd81d-0793-4112-8465-7e472d4badf3-master.m3u8https://peertube.laas.fr/videos/embed/28kF3CDtJwuZMTvrTohFmo120022021-06-03T20:17:43.994ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/5tYpRevRykg5f941MRsm19https://peertube.laas.fr/lazy-static/thumbnails/244c66ab-cfd5-414d-b27b-802adb9f8798.jpgHPP-loco: success in planning for real legged robotsThis video reports a bunch of experiments with our legged robots using HPP-loco to plan locomotion movements on 3D terrains: HRP-2 and Talos bipeds at LAAS-CNRS, Solo quadruped at LAAS as well, and Anymal at Univ. Oxford. https://peertube.laas.fr/static/streaming-playlists/hls/244c66ab-cfd5-414d-b27b-802adb9f8798/75f16199-0637-44b3-93ad-5c868ac41bba-master.m3u8https://peertube.laas.fr/videos/embed/5tYpRevRykg5f941MRsm191410112021-06-04T12:39:04.475ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/9F9Qu3pgaUJyWqBvb5LZkMhttps://peertube.laas.fr/lazy-static/thumbnails/46408fc7-a83c-42d9-b791-dc0994d3659f.jpgLocalization with TALOS Ouster-64 bits using icp_mapping from Oxford UniversityThe robot is about to localize itself with a precision of 2 cm (computed with the Motion Capture system). Here it uses the PAL walking pattern generator to reach each position inside the room. Thanks to the Intel Real Sense D265 on the left, the ICP registration is done extremely accurately.https://peertube.laas.fr/static/streaming-playlists/hls/46408fc7-a83c-42d9-b791-dc0994d3659f/be3f3951-f4d4-44d0-879b-bd9b31cc756d-master.m3u8https://peertube.laas.fr/videos/embed/9F9Qu3pgaUJyWqBvb5LZkM2340732021-06-17T12:23:51.833ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/txU5GkxDeauXgVqHm2NAVshttps://peertube.laas.fr/lazy-static/thumbnails/df1ae58f-6755-44df-a362-912d18db3ee4.jpgSimulation par Nicolas TestardSimulation par Nicolas Testardhttps://peertube.laas.fr/static/streaming-playlists/hls/df1ae58f-6755-44df-a362-912d18db3ee4/8af4b50d-3114-426d-9661-1b4a2ae1dfb4-master.m3u8https://peertube.laas.fr/videos/embed/txU5GkxDeauXgVqHm2NAVs100552021-06-17T13:07:33.528ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/hTPU2DaL1NhEzK5JE9ybkshttps://peertube.laas.fr/lazy-static/thumbnails/88ceab1e-2cc1-4bd1-9c9e-2be0c2c31890.jpgProximal and Sparse Resolution of Constrained Dynamic EquationsCompanion video for RSS 2021 paper: Proximal and Sparse Resolution of Constrained Dynamic Equations by Justin Carpentier, Rohan Budhiraja and Nicolas Mansard. Robotic systems may be subject to different types of constraints: point contact constraints (quadrupeds), flat foot constraints (humanoids), closed kinematic chains (parallel robots, here the 4-bar linkages of Cassie) or even contact with the end effectors (any robot). This video is the companion to our paper, in which we introduce a generic approach to handle all these types of constraints, contacts and kinematic closures, in a unified and efficient manner, even in the context of ill-posed or singular cases.https://peertube.laas.fr/static/streaming-playlists/hls/88ceab1e-2cc1-4bd1-9c9e-2be0c2c31890/fedb7efa-e1a9-4f20-9826-ddae1c770217-master.m3u8https://peertube.laas.fr/videos/embed/hTPU2DaL1NhEzK5JE9ybks1180722021-06-22T11:33:17.119ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/4wrCbetfg2KKKrPtAjYA35https://peertube.laas.fr/lazy-static/thumbnails/1c8b8530-1e39-447d-8e6c-59de880103a0.jpgIntegrating Path Planning and Visual Servoing in Manipulation TasksIntegrating Path Planning and Visual Servoing in Manipulation Taskshttps://peertube.laas.fr/static/streaming-playlists/hls/1c8b8530-1e39-447d-8e6c-59de880103a0/58905a98-51ec-4d0d-9220-6a88751deaf8-master.m3u8https://peertube.laas.fr/videos/embed/4wrCbetfg2KKKrPtAjYA351450602021-06-22T21:05:02.530ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/rm6rHBAHapik8TP4rtxcNshttps://peertube.laas.fr/lazy-static/thumbnails/cd42b24e-f256-4dff-9a7a-59fcdf28b07a.jpgFirst mouvements of Jiminy BoltFirst mouvements of Jiminy Bolthttps://peertube.laas.fr/static/streaming-playlists/hls/cd42b24e-f256-4dff-9a7a-59fcdf28b07a/c3f3c8cf-076b-40f4-a721-d320882ec79f-master.m3u8https://peertube.laas.fr/videos/embed/rm6rHBAHapik8TP4rtxcNs135282021-06-29T14:35:26.820ZYESMain prouanet channelNOhttps://peertube.laas.fr/w/4RTXbeB1nM94eJJY5LGJpghttps://peertube.laas.fr/lazy-static/thumbnails/1f42e079-11d2-4352-96a8-30de667567ad.jpgROSConFr 2021 - Jour 1 - François Leborne - Nimbl'Bot *Simulation cinématique du NB-120 : un nouveau robot sériel modulaire et hautement redondant pour l’usinage et l’intervention.* Depuis 2018, Nimbl’Bot développe une architecture modulaire de robots sériels à actionneurs parallèles. Ces derniers exploitent une technologie brevetée et diffèrent fondamentalement des actionneurs des robots industriels actuels. Pour supporter le développement de lois de commande adaptées, un simulateur cinématique est développé en s’appuyant sur ROS pour la visualisation. Dans ce cadre, nous présenterons un outil de génération des URDF, simplifiant l’étude d’agencements arbitraires, en nombre comme en position, des actionneurs de potentiels robots. De plus, l’intégration avec ROS de ces robots, permettant leur utilisation comme composants d’un système plus complexe, sera aussi abordée.https://peertube.laas.fr/static/streaming-playlists/hls/1f42e079-11d2-4352-96a8-30de667567ad/accf4682-2a9a-4f06-867e-a211a8c95faa-master.m3u8https://peertube.laas.fr/videos/embed/4RTXbeB1nM94eJJY5LGJpg18150482021-07-05T14:43:49.107ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/nZYbu4AejRfrGeQyZir8QGhttps://peertube.laas.fr/lazy-static/thumbnails/b227edeb-3aeb-4375-9dc2-291447a3049c.jpgROSConFr 2021 - Jour 1 - Pierre Fernbach*Développement d’un robot bipède capable de sauter avec ROS.* PAL Robotics et Toward ont développé un concept de jambe pour robots humanoïdes basé sur de nouveaux actionneurs linéaires avec une transmission non linéaire. Cela permet au robot de réaliser des mouvements très dynamiques et de résister à des impacts importants, par exemple lors de la marche sur sol non plat ou instable et également lors de sauts. Le robot utilise ros_control ainsi que des nouveaux plugins de transmissions. Il peut être contrôlé selon différents modes : courant, position ou force et impédancehttps://peertube.laas.fr/static/streaming-playlists/hls/b227edeb-3aeb-4375-9dc2-291447a3049c/16e27c35-c43d-4352-9647-99fbbd6049c2-master.m3u8https://peertube.laas.fr/videos/embed/nZYbu4AejRfrGeQyZir8QG2409082021-07-05T15:00:23.690ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/vw11xJ4G7FpzWcpvuAjqV5https://peertube.laas.fr/lazy-static/thumbnails/ef09570d-9f88-46f6-890c-23cb416b7196.jpgROSConFr 2021 - Jour 1 - Benoit Varillon - ISAE*Corail, ROS2 temps réel* Le package corail propose une nouvelle implémentation des exécuteurs de ROS2 qui permet la réalisation de programmes temps réel. Corail repose sur le standard POSIX, et son implémentation pthread, ainsi que sur son ordonnanceur à priorité fixe (SCHED_FIFO) pour permettre la gestion précise des différents paramètres d’ordonnancement, tel que l’affinité ou la priorité, de chaque éléments. Il permet aussi de gérer leur synchronisation ce que ne permettent pas les exécuteurs actuels. Corail garantit le déterminisme temporel des exécutions des différents éléments du système. Déterminisme qui est indispensable aux analyses d’ordonnaçabilité qui ont pour but de prouver le respect des contraintes temporelles.https://peertube.laas.fr/static/streaming-playlists/hls/ef09570d-9f88-46f6-890c-23cb416b7196/935268bc-d469-4a05-888c-ce9371a3468e-master.m3u8https://peertube.laas.fr/videos/embed/vw11xJ4G7FpzWcpvuAjqV518700102021-07-05T20:40:02.003ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/sDPKwTWP6gAr5h1CcZPnbJhttps://peertube.laas.fr/lazy-static/thumbnails/d7d58d4e-905d-421f-a9ad-956c10d0572a.jpgROSConFr 2021 - Jour 1 - Bence Magyar - ros2_control*Getting started with ros2_control* _Bence Magyar_https://peertube.laas.fr/static/streaming-playlists/hls/d7d58d4e-905d-421f-a9ad-956c10d0572a/4f3f56af-545f-48e7-9e58-e5826757f75e-master.m3u8https://peertube.laas.fr/videos/embed/sDPKwTWP6gAr5h1CcZPnbJ45530902021-07-05T20:54:03.626ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/k69zBDbWcy9tqHnR71qQZ3https://peertube.laas.fr/lazy-static/thumbnails/9a95a406-ff03-4ffd-b65f-0bd9cf9cacec.jpgROSConFr 2021 - Jour 01- Christophe Bédard - DORSAL*Tracer ROS 2 avec ros2_tracing* _Christophe Bédard_ Le traçage (tracing) est une méthode à bas surcoût d’utilisation pour l’extraction d’information sur l’exécution d’une application, tant en développement qu’en production. ros2_tracing est une collection d’outils incluant l’instrumentation directement dans le core de ROS 2 et des outils pour gérer facilement le traçage à travers launch et ros2cli.https://peertube.laas.fr/static/streaming-playlists/hls/9a95a406-ff03-4ffd-b65f-0bd9cf9cacec/5dd0cf0b-ca81-4706-802c-634c76f6870b-master.m3u8https://peertube.laas.fr/videos/embed/k69zBDbWcy9tqHnR71qQZ32193042021-07-06T05:18:29.522ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/smayU5LqTBkHXJspCHhxyEhttps://peertube.laas.fr/lazy-static/thumbnails/d55e6066-3e78-48d4-ab7d-a0aad8db3012.jpgROSConFr 2021 - Jour 1 - Nicolas Rabault - PDG/CEO LUOS*Comment gérer vos architecture électronique distribué avec ROS ?* _Nicolas Rabault_ Robert, dev embarqué dans l’industrie depuis 35 ans : Un développeur embarqué, ça code en C de la même manière depuis 30 ans, et il n’y a pas de raison que ça change. Tous les domaines de l’informatique ont évolué continuellement et se sont modernisés avec de nouveaux languages et de nouvelles méthodologies, permettant de multiplier l’efficacité des développeurs et la fiabilité des systèmes. ROS en est la parfaite illustration. Pourquoi pas en embarqué ? Chez Luos nous pensons que les methodologies modernes sont tout a fait compatibles et peuvent complètement transformer la manière dont on conçoit et pense les produits électroniques.https://peertube.laas.fr/static/streaming-playlists/hls/d55e6066-3e78-48d4-ab7d-a0aad8db3012/8355e8a5-3754-4dc9-8ef3-61af31d78026-master.m3u8https://peertube.laas.fr/videos/embed/smayU5LqTBkHXJspCHhxyE3257082021-07-06T06:31:44.213ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/pcKGfYCaG2pAB5MTkPS4BPhttps://peertube.laas.fr/lazy-static/thumbnails/bbe64c50-480c-4fee-8571-f71c41cf4569.jpgROSConFr 2021 - Jour 1 - Cyril Briand - SMART*ROSIN Occitanie: un retour d’expérience* _Cyril Briand_ Le pôle S-MART Occitanie a développé le projet ROS In Occitanie. Ce projet a eu pour but de développer une ROS-ACademy permettant de mieux diffuser l’usage de ROS sur la région occitane. Les équipements de la plateforme robotique du pôle ont ainsi été intégrés sous ROS. La présentation dressera un bilan de ce projet et, au-delà, s’interroge sur le potentiel de ROS en tant que solution open-source pour l’accélération de la transition vers l’industrie du futur.https://peertube.laas.fr/static/streaming-playlists/hls/bbe64c50-480c-4fee-8571-f71c41cf4569/265e7ef4-da3b-4c7c-9b4e-9a6f0aa3d4ad-master.m3u8https://peertube.laas.fr/videos/embed/pcKGfYCaG2pAB5MTkPS4BP1482072021-07-06T07:11:43.808ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/gJBjRogKrreJmMLaJDtubHhttps://peertube.laas.fr/lazy-static/thumbnails/7f6c168b-1905-4316-91e3-3f66f0b77f65.jpgWhole-body model-predictive control with Talos: resisting external disturbancesWhole-body model-predictive control with Talos: resisting external disturbanceshttps://peertube.laas.fr/static/streaming-playlists/hls/7f6c168b-1905-4316-91e3-3f66f0b77f65/67e8e30e-ada9-46b4-83d7-d64a69a718d7-master.m3u8https://peertube.laas.fr/videos/embed/gJBjRogKrreJmMLaJDtubH21032021-07-16T16:34:34.963ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/2Ym4Jhcef6AECyJspQU35Hhttps://peertube.laas.fr/lazy-static/thumbnails/0ff727a3-8e8e-40b0-934b-812843f6cb59.jpgWhole-body model-predictive control using a memory of motion with Talos: reactive tracking and ob...Whole-body model-predictive control using a memory of motion with Talos: reactive tracking and obstacle avoidancehttps://peertube.laas.fr/static/streaming-playlists/hls/0ff727a3-8e8e-40b0-934b-812843f6cb59/32c0e826-2944-4ec0-9ec1-02f4f135e542-master.m3u8https://peertube.laas.fr/videos/embed/2Ym4Jhcef6AECyJspQU35H1720162021-07-16T16:35:59.655ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/aiLmGFowZhwa6zFafXURUbhttps://peertube.laas.fr/lazy-static/thumbnails/4b5d3a5b-2355-47a0-8197-f41ed4f885c6.jpgComparison of Position and Torque Whole Body Control Schemes on the Humanoid Robot TALOSThis video illustrates the ICAR paper on the comparison of three control schemes applied on the Humanoid Robot TALOS. Aiming to choose the most appropriate scheme for the robot TALOS, we benchmark three control schemes with the robot walking on three different scenarios: flat horizontal ground, tilted platforms and stairs. The first scheme optimizes joint velocities based on hierarchical quadratic programming; the second one, optimizes joint accelerations based on weighted quadratic programming; and the last one optimizes joint torques, also based on weighted quadratic programming. We compare these controllers in terms of tracking error, energy consumption and computational time required for the execution by using Gazebo simulations. Remarkably, our torque control scheme allowed TALOS to walk forward at 0.6m/s, the highest walking velocity achieved so far.https://peertube.laas.fr/static/streaming-playlists/hls/4b5d3a5b-2355-47a0-8197-f41ed4f885c6/b012b855-37d3-4fb9-ba2b-52351a1ed6c6-master.m3u8https://peertube.laas.fr/videos/embed/aiLmGFowZhwa6zFafXURUb1750772021-07-20T09:44:32.552ZHumanoid RobotTorque ControlWhole Body ControlYESMain nramuzat channelNOhttps://peertube.laas.fr/w/bbNkkkmPatMeaELHjo2m44https://peertube.laas.fr/lazy-static/thumbnails/527d60d3-c22a-4e0d-9dbf-a0d454d9b089.jpgROSConFr 2021 - Jour 2 micro-ROS: bringing ROS 2 to microcontrollers - J. Staschulat, M. Merlan, ...Robots nowadays are less of a powerful central unit than an interconnected network of robotic parts, some of which are in charge of highly specialized physical or mechanical tasks, and generally operated by microcontrollers. micro-ROS intends to bridge the gap between standard service-oriented frameworks like ROS 2, not entirely fit to address such scenarios efficiently, and these resource-constrained environments. It does so by creating ROS-like nodes very close to the hardware level, able to interact directly with the drivers that control the peripherals at the same time as allowing a fine-grain integration within the ROS 2 network. In this presentation, we describe the micro-ROS architecture and discuss some of its advanced features and most recent developments. Also, we present a hands-on tutorial for moving the first steps in the micro-ROS world.https://peertube.laas.fr/static/streaming-playlists/hls/527d60d3-c22a-4e0d-9dbf-a0d454d9b089/b49e17dd-d2e7-44aa-998f-8fd83889966f-master.m3u8https://peertube.laas.fr/videos/embed/bbNkkkmPatMeaELHjo2m4438380192021-07-21T16:44:16.929ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/cstoBxV9Anw8QS4Lv6BLgBhttps://peertube.laas.fr/lazy-static/thumbnails/5cc6be2e-2ca0-47b9-8ce2-14b026b10e21.jpgSucessful posture task of the torque control scheme using TSID First success of a simple posture task in torque using TSID on Pyrene. At the end the robot falls because the contacts on the feet have been disturbed (the feet moved) breaking the constraint of TSID.https://peertube.laas.fr/static/streaming-playlists/hls/5cc6be2e-2ca0-47b9-8ce2-14b026b10e21/d2024204-5bbf-4707-b960-de13c49cce92-master.m3u8https://peertube.laas.fr/videos/embed/cstoBxV9Anw8QS4Lv6BLgB340222021-08-04T17:03:41.237ZYESMain nramuzat channelNOhttps://peertube.laas.fr/w/njEPHm4Qo3b7xqU3T9TRahhttps://peertube.laas.fr/lazy-static/thumbnails/acab399a-d875-4754-8873-05c7525907d6.jpgROSConFr 2021 - Jour 2 - Simon Legoff - Pollen RoboticsReachy est un robot humanoïde, téléopérable et entièrement open source conçu pour l’interaction physique et sociale. Nous présenterons la nouvelle version de Reachy et le choix de la baser sur ROS2 Foxy. Nous détaillerons en particulier son utilisation dans ce contexte et les packages de contrôle moteur et planification utilisés.https://peertube.laas.fr/static/streaming-playlists/hls/acab399a-d875-4754-8873-05c7525907d6/83d771ad-2ded-4739-a567-cd40d3878391-master.m3u8https://peertube.laas.fr/videos/embed/njEPHm4Qo3b7xqU3T9TRah18310122021-08-05T20:21:17.572ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/rDw1DRioUA7TqLWzQt3vTFhttps://peertube.laas.fr/lazy-static/thumbnails/cfb17b28-190c-4299-b38b-85481b120909.jpgROSConFr 2021 - Jour 02 - Daniel Soto-Guerrero - XLIMLe projet ROSE est financée par l’Agence Nationale de la Recherche (ANR) française. Le projet a comme objectif d’avancer la robotique appliqué à l’agriculture. Un robot agricole doit réaliser la tâche de binage de façon autonome pour éviter l’utilisation d’herbicides. Les sujets à aborder lors de notre participation sont les suivants : * Géolocalisation d’un robot agricole en utilisant un GPS RTK Real-Time Kinematics. Formation et mise en fonction d’une balise de localisation active sur le site de l’ENSIL (Limoges). * Contrôle autonome de la plateforme robotique ALPO fabriqué par Sabi Agri, notre partenaire dans le projet ROSE. * Mise en oeuvre du modèle du robot agricole sur le Robotics Operating System (ROS) et Gazebo . Le modèle a permis à l’équipe d’avancer le projet même dans des situations adverses (météorologie, Covid-19). Le modèle imite la chaîne de contrôle réel : robot, capteurs et outil de binage. * Intégration du hardware, plateforme des capteurs intelligents : Xeye & Xtool. Le capteur Xeye permet de guider le tracteur tandis que Xtool active l’outil de binage. Les deux capteurs ont été aussi incorporés au modèle du simulation. Outils Requis : Arduino, FreeCAD, parametrage du réseau. * Interfaçage du type serveur-client vers le capteur Aqit. Fabriqué par Carbon Bee, le capteur Aqit, détecte les plantes d’intérêt en utilisant deep learning. Xeye demande au capteur Aqit à travers le réseaux WiFi de ce dernière. Les résultats de détection des plantes d’intérêt sont reçus, traités et partagé en format d’un ROS message.https://peertube.laas.fr/static/streaming-playlists/hls/cfb17b28-190c-4299-b38b-85481b120909/27afe259-daf6-4f40-a3c8-04da49e314aa-master.m3u8https://peertube.laas.fr/videos/embed/rDw1DRioUA7TqLWzQt3vTF21600112021-08-05T20:41:44.956ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/tmLh3jnp2eEYTa63Tz4u3Xhttps://peertube.laas.fr/lazy-static/thumbnails/dd8ce7d6-4b11-4910-97e3-49d806f77503.jpgROSConFr 2021 - Jour 2 - 01 - William Bobillet - RapyutaWith the exponential growth in automation, fleets of robots spread across different geographical sites and their remote operation is becoming the norm. Running applications generate data which is critical for not just operations and debugging, but for process monitoring, machine learning and predictive analytics. State of the art solutions today have focussed on using different specialized products to cobble together a Remote Operation Centre experience. As developers, this means multiple integrations and fragmented operations along with higher Operational costs and lower ROI.In this webinar, We present a Remote Operation Centre blueprint which centralizes multiple aspects of Application Performance Management tailored for ROS. It’s designed to work both as a central ROC or an Edge Operations Centre. We will cover Distributed Logging & Storage, Centralized Rosbag Collection Metrics & Alerting Distributed Tracing.https://peertube.laas.fr/static/streaming-playlists/hls/dd8ce7d6-4b11-4910-97e3-49d806f77503/7159abf8-ae2a-4ec2-acd5-3a5aec68d5a9-master.m3u8https://peertube.laas.fr/videos/embed/tmLh3jnp2eEYTa63Tz4u3X22590202021-08-05T21:14:19.801ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/jx3q4kSYYe828pFqD66rEwhttps://peertube.laas.fr/lazy-static/thumbnails/961a0a79-6851-481d-bc7e-331ba69c3df6.jpgROSConFr 2021 - Jour 2 - Présentations EclairsROSConFr 2021 Présentation Eclairs - Olivier Kermorgant - Simplification de ros2launch - Guillaume Doisy - Démo de PlotJugglerhttps://peertube.laas.fr/static/streaming-playlists/hls/961a0a79-6851-481d-bc7e-331ba69c3df6/951609ff-0821-4d84-bb12-6d16ab611356-master.m3u8https://peertube.laas.fr/videos/embed/jx3q4kSYYe828pFqD66rEw11030182021-08-06T11:29:00.928ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/c7yweQscoUuPAge1dtZ13ihttps://peertube.laas.fr/lazy-static/thumbnails/59ff07a5-fc35-4eb9-bc4f-6c0083fcff1d.jpgROSConFr 2021 - Jour 2 - Felix Ingrand - LAAS - Vérification formelle hors ligne et en ligne de ...Nous présenterons GenoM3, un outil qui permet de spécifier des modules fonctionnels pour la robotique, associé à une suite de vérification formelle: Fiacre/TINA/Hippo. La spécification en GenoM3 propose d’organiser les modules à travers des services, des tâches (qui exécutent ces services), et des ports qui permettent d’échanger des données entre les modules. Les services sont de divers types, et les plus complexes sont spécifiés avec un automate qui explicite les différentes étapes de leur traitement, avec le code (C ou C++) associé à chacune de ces étapes. Au delà du langage de spécification, GenoM3 propose un mécanisme de “template” qui permet de synthétiser automatiquement le module final, en particulier en utilisant, entre autres, ROS Com comme middleware. Dans cette déclinaison là, le module est alors un noeud ROS, les ports GenoM3 sont implémentés avec des topics ROS, et les services GenoM3 sont mapés en ROS Service ou ROS Action. Toujours avec les templates, on peut aussi synthétiser le modèle formel en Fiacre équivalent en tout point au noeud GenoM3/ROS. Cette synthèse automatique permet alors de prouver des propriétés formelles du noeud ROS, hors ligne avec l’outil TINA , mais aussi de faire de la vérification “runtime” et d’exécuter ce même modèle formel avec l’outil Hippo en lieu et place du noeud ROS “classique”. Nous illustrerons la mise en oeuvre de GenoM3 et de Fiacre/TINA/Hippo à travers deux exemples, un drone, comportant 5 modules GenoM3, et un robot mobile d’extérieur, avec 9 modules.https://peertube.laas.fr/static/streaming-playlists/hls/59ff07a5-fc35-4eb9-bc4f-6c0083fcff1d/59aba4af-dfaa-421b-9389-8eb0b76e36d3-master.m3u8https://peertube.laas.fr/videos/embed/c7yweQscoUuPAge1dtZ13i30010952021-08-06T13:23:31.068ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/nVxsoVywzTKa5FXVBAg4nchttps://peertube.laas.fr/lazy-static/thumbnails/b189b770-560a-44ed-9c7d-4d5f3939ed51.jpgROSConFr 2021 - Jour 2 - V. Bissonnette - dISAS – démonstrateur d’assemblage de très grandes str...Un simulateur dédié à l’assemblage dans l’espace a été développé pour projet H2020 PULSAR. Ce démonstrateur adresse l’assemblage autonome d’un miroir principal de télescope composé de 36 tuiles miroir, à l’aide d’un bras manipulateur embarqué. La manipulation des tuiles miroir par le bras robotique induit de nombreuses perturbations et changent la position du centre d’inertie de la structure, rendant son contrôle complexe. La taille des panneaux solaires, du bouclier solaire et du miroir principal induisent des vibrations sur la structure. Ces perturbations doivent être gérées par un contrôle SCAO spécifiquement conçu afin de satisfaire les exigences de maintien d’attitude.https://peertube.laas.fr/static/streaming-playlists/hls/b189b770-560a-44ed-9c7d-4d5f3939ed51/2e8f9123-db93-4d35-a96c-425480eeeb12-master.m3u8https://peertube.laas.fr/videos/embed/nVxsoVywzTKa5FXVBAg4nc2457042021-08-06T18:03:25.750ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/hzsHY763965LyQZsNL44bbhttps://peertube.laas.fr/lazy-static/thumbnails/863e3b61-9677-49f3-a40d-4b774b61e2b2.jpgROSConFr 2021 - Jour 2 - Olivier Stasse - LAAS - ros(2)_control et interfaçage avec les cartes I/Oros_control est une librarie proposant à la fois une abstraction de la partie permettant l’accés au robot, et une abstraction des controllers. ROS1 permet ainsi d’utiliser les mêmes contrôleurs sur de multiples robots, mais au prix d’une rigidité de l’API problématique pour des robots qui souhaitent utiliser des informations supplémentaires par rapport au classique encoder, et retour courant. A travers différents exemples nous illustrerons les avantages et les inconvénients de cette interface et son extension dans ros2_control.https://peertube.laas.fr/static/streaming-playlists/hls/863e3b61-9677-49f3-a40d-4b774b61e2b2/cdf1d8d9-3170-4d00-8e02-9fb32c256959-master.m3u8https://peertube.laas.fr/videos/embed/hzsHY763965LyQZsNL44bb24540142021-08-06T19:44:26.373ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/kJH1Nt8bm2h5Gcby2SrbxPhttps://peertube.laas.fr/lazy-static/thumbnails/9fd42606-bbb6-4750-ab75-ea9b903b0745.jpgROSConFr 2021 - Jour 2 - Charles Lesire - ONERA - Robot Skills ToolchainLa boîte à outils Robot Skills permet de structurer l’architecture logicielle d’un système robotique en capacités, ou skills, à travers plusieurs étapes de développement : (1) la spécification des ces capacités à travers un langage spécifique au domaine (DSL) (2) la génération d’une architecture de managers, constituée de noeuds ROS/ROS2 qui vont gérer l’exécution de ces capacités en lien avec l’architecture fonctionnelle, et fournir une interface standardisée d’exécution de ces capacités, et (3) la génération d’une librairie d’interface permettant de contrôler l’exécution des capacités. Cette boîte à outils intègre également des outils de suivi et visualisation de l’exécution des capacités.https://peertube.laas.fr/static/streaming-playlists/hls/9fd42606-bbb6-4750-ab75-ea9b903b0745/492d8a5c-f32c-4afd-a9c9-bdf1b5d0e3c2-master.m3u8https://peertube.laas.fr/videos/embed/kJH1Nt8bm2h5Gcby2SrbxP18380132021-08-06T20:24:19.785ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/77S6vzBaSZ6uepc7qDvSc6https://peertube.laas.fr/lazy-static/thumbnails/318c2aae-3199-419b-ab30-5d579c6a1e63.jpgROSConFr 2021 - Jour 1 - Présentation EclairGotelli Andrea: A Gazebo Simulator for Continuum Parallel Robotshttps://peertube.laas.fr/static/streaming-playlists/hls/318c2aae-3199-419b-ab30-5d579c6a1e63/838a9433-e15e-4b9a-b1c9-03511bf3975a-master.m3u8https://peertube.laas.fr/videos/embed/77S6vzBaSZ6uepc7qDvSc6452042021-08-06T20:59:51.052ZYESROSConFr 2021NOhttps://peertube.laas.fr/w/mFLtKCuSXJciKHZk5uGRdahttps://peertube.laas.fr/lazy-static/thumbnails/a78430ea-09b0-4e31-8ca6-7436c7af9165.jpgSolo12 outdoor experiment at LAAS, Autonomy UpdateOutdoor experiment, following https://www.youtube.com/watch?v=ZxmbFny51Pg Pierre Alexandre LEZIART, Thomas CORBERES, Thomas FLAYOLS LAAS-CNRS More information: https://open-dynamic-robot-initiative.github.io Forum for questions: https://odri.discourse.group/categories GitHub Hardware Documentation: https://github.com/open-dynamic-robot-initiative/open_robot_actuator_hardware/blob/master/mechanics/quadruped_robot_12dof_v1/README.md#quadruped-robot-12dof-v1https://peertube.laas.fr/static/streaming-playlists/hls/a78430ea-09b0-4e31-8ca6-7436c7af9165/fea1bd14-e2a5-4780-be29-f4c3f457c689-master.m3u8https://peertube.laas.fr/videos/embed/mFLtKCuSXJciKHZk5uGRda1000122021-08-26T07:30:45.695ZYESMain tflayols channelNOhttps://peertube.laas.fr/w/oByc5nstUGm88nZr3DfqZ8https://peertube.laas.fr/lazy-static/thumbnails/b71febbc-d5f4-4e35-a339-b8a3cbd6fed1.jpgFirst Order Approximation of Model Predictive Control Solutions for High Frequency FeedbackFirst Order Approximation of Model Predictive Control Solutions for High Frequency Feedbackhttps://peertube.laas.fr/static/streaming-playlists/hls/b71febbc-d5f4-4e35-a339-b8a3cbd6fed1/85f66214-3f14-461a-ac54-e073814fa369-master.m3u8https://peertube.laas.fr/videos/embed/oByc5nstUGm88nZr3DfqZ81600802021-09-09T21:13:02.435ZYESMain edantec channelNOhttps://peertube.laas.fr/w/6z1hB8r71ScGVpp4hcccGchttps://peertube.laas.fr/lazy-static/thumbnails/2d196a05-d234-4e41-aa09-86e75c1a184f.jpgLearning to walk: presentation at ANITI SAB (9 sep 2021)In this presentation, we discuss optimal control, nonlinear optimization at high frequency, guided by an offline trained memory of motion. This is a part of the activities in the chair "Artificial and Natural Movements" of ANITI, with Olivier Stasse and the colleagues from Gepetto at LAAS-CNRS. It led to the world-premiere implementation of whole-body model predictive control on a legged robot, using the full-scale torque control humanoid Talos. We believe with a large part of the humanoid robotics community, that whole-body predictive control is one of the missing pieces for enabling autonomous navigation in 3D terrains. https://peertube.laas.fr/static/streaming-playlists/hls/2d196a05-d234-4e41-aa09-86e75c1a184f/1dab5869-09ad-4ff7-ad16-c6be8ab83aa0-master.m3u8https://peertube.laas.fr/videos/embed/6z1hB8r71ScGVpp4hcccGc6000152021-09-10T10:03:20.064ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/2gocSzm3DVhHSuSPkYysvahttps://peertube.laas.fr/lazy-static/thumbnails/0a3efab5-c388-413f-801b-275741a0ee63.jpgCosySLAM: tracking contact featuresusing visual-inertial object-level SLAM for locomotionAccompanying video to the ICRA 2022 submission "CosySLAM: tracking contact featuresusing visual-inertial object-level SLAM for locomotion" Authors: César Debeunne, Médéric Fourmy, Yann Labbé,Pierre-Alexandre Leziart, Guilhem Saurel, Joan Solà and Nicolas Mansard More information: https://homepages.laas.fr/mfourmy/icra22_cosyslamhttps://peertube.laas.fr/static/streaming-playlists/hls/0a3efab5-c388-413f-801b-275741a0ee63/dcd420d4-ff02-40b6-949d-1fad2b8b1da4-master.m3u8https://peertube.laas.fr/videos/embed/2gocSzm3DVhHSuSPkYysva1620392021-09-21T15:50:20.077ZYESMain mfourmy channelNOhttps://peertube.laas.fr/w/k3DDpXTnKtViPRugo136wnhttps://peertube.laas.fr/lazy-static/thumbnails/9a3c5258-e5b7-49a5-a153-02e804a06f65.jpgAddressing Flexibility in Biped Locomotion with Robust Control and Closed-loop Model-Predictive C...Addressing Flexibility in Biped Locomotion with Robust Control and Closed-loop Model-Predictive Controlhttps://peertube.laas.fr/static/streaming-playlists/hls/9a3c5258-e5b7-49a5-a153-02e804a06f65/3140f336-9a1e-48b3-beb4-7ce6a59a8b38-master.m3u8https://peertube.laas.fr/videos/embed/k3DDpXTnKtViPRugo136wn15251052021-09-22T11:24:55.537Zrobust controlclosed-loop MPCflexible robotbiped locomotionYESMain nvilla channelNOhttps://peertube.laas.fr/w/wTz6c7haco5MYrRreLhzLMhttps://peertube.laas.fr/lazy-static/thumbnails/fa257bf4-cd46-4590-b234-6c21fce591e9.jpg Implicit Differential Dynamic Programming Author: Wilson Jallet, Nicolas Mansard, Justin Carpentier This is the companion video for the paper https://hal.archives-ouvertes.fr/hal-03351641 Over the past decade, the Differential Dynamic Programming (DDP) method has gained in maturity and popularity within the robotics community. Several recent contributions have led to the integration of constraints within the original DDP formulation, hence enlarging its domain of application while making it a strong and easy-to-implement competitor against alternative methods of the state of the art such as collocation or multiple-shooting approaches. Yet, and similarly to its competitors, DDP remains unable to cope with high-dimensional dynamics within a receding horizon fashion, such as in the case of online generation of athletic motion on humanoid robots. In this paper, we propose to make a step toward this objective by reformulating classic DDP as an implicit optimal control problem, allowing the use of more advanced integration schemes such as implicit or variational integrators. To that end, we introduce a primal-dual proximal Lagrangian approach capable of handling dynamic and path constraints in a unified manner, while taking advantage of the time sparsity inherent to optimal control problems. We show that his reformulation enables us to relax the dynamics along the optimization process by solving it inexactly: far from the optimality conditions, the dynamics are only partially fulfilled, but continuously enforced as the solver get closer to the local optimal solution. This inexactness enables our approach to robustly handle large time steps (100 ms or more), unlike other DDP solvers of the state of the art, as experimentally validated through different robotic scenarios. https://peertube.laas.fr/static/streaming-playlists/hls/fa257bf4-cd46-4590-b234-6c21fce591e9/f403083e-58ab-45ed-938b-b6ff68c131d5-master.m3u8https://peertube.laas.fr/videos/embed/wTz6c7haco5MYrRreLhzLM940252021-09-22T14:29:00.707ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/17uzneDe7QVAZs5ePc8WKMhttps://peertube.laas.fr/lazy-static/thumbnails/00e812a0-7321-4f05-8ab8-3250f2a49deb.jpgValue learning from trajectory optimization and Sobolev descentA step toward reinforcement learning with superlinear convergence propertieshttps://peertube.laas.fr/static/streaming-playlists/hls/00e812a0-7321-4f05-8ab8-3250f2a49deb/4c5b942b-11af-4128-aed3-dd0dc86dd9b0-master.m3u8https://peertube.laas.fr/videos/embed/17uzneDe7QVAZs5ePc8WKM940242021-09-29T10:16:56.098ZYESMain aparag channelNOhttps://peertube.laas.fr/w/bfrWarLhmrB6aBD5i1ihD8https://peertube.laas.fr/lazy-static/thumbnails/52ffc81c-09ce-41e9-8d6c-8c8d2b664d71.jpg"Lie theory for the roboticist" by Joan SolàA Lie group is an old mathematical abstract object dating back to the XIX century, when mathematician Sophus Lie laid the foundations of the theory of continuous transformation groups. Its influence has spread over diverse areas of science and technology many years later. In robotics, we are recently experiencing an important trend in its usage, at least in the fields of estimation, and particularly in motion estimation for navigation. Yet for a vast majority of roboticians, Lie groups are highly abstract constructions and therefore difficult to understand and to use. In robotics it is often not necessary to exploit the full capacity of the theory, and therefore an effort of selection of materials is required. In this course, we will walk through the most basic principles of the Lie theory, with the aim of conveying clear and useful ideas, and leave a significant corpus of the Lie theory behind. Even with this mutilation, the material I will be presenting has proven to be extremely useful in modern estimation and control algorithms for robotics. https://peertube.laas.fr/static/streaming-playlists/hls/52ffc81c-09ce-41e9-8d6c-8c8d2b664d71/2c80f7e9-2a0c-4189-a7a2-8d27d5dfe7d0-master.m3u8https://peertube.laas.fr/videos/embed/bfrWarLhmrB6aBD5i1ihD872075472021-10-13T09:15:43.652ZalgebraroboticsLie theoryYESMain nramuzat channelNOhttps://peertube.laas.fr/w/26qTiZo5JfTFxPg4cMuW4Thttps://peertube.laas.fr/lazy-static/thumbnails/08db3177-372b-43cc-85da-2009a267b5c9.jpgWalking Experience with Pyrene 2020 06 30Walking Experience with Pyrene 2020 06 30https://peertube.laas.fr/static/streaming-playlists/hls/08db3177-372b-43cc-85da-2009a267b5c9/d2acc9b8-7f91-4a26-ab4e-6c5c5cb302af-master.m3u8https://peertube.laas.fr/videos/embed/26qTiZo5JfTFxPg4cMuW4T470322021-10-20T16:20:16.699ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/7dfEsGKEf89m2qZqVkARochttps://peertube.laas.fr/lazy-static/thumbnails/324ccb2d-79b9-493d-876a-061abec3130b.jpgVérification formelle sur robot mobileFélix Ingrand (LAAS) - Vérification formelle sur robot mobile [Journée Robotique Mobile du réseau de métier 2RM](https://wiki.2rm.cnrs.fr/JT_robmob_2021) - 19 octobre 2021 https://peertube.laas.fr/static/streaming-playlists/hls/324ccb2d-79b9-493d-876a-061abec3130b/94760f14-ca2f-4833-9b03-b76298820821-master.m3u8https://peertube.laas.fr/videos/embed/7dfEsGKEf89m2qZqVkARoc2683052021-10-22T12:12:12.783ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/ut1bKBC2Z2zrR6mXuXPzBfhttps://peertube.laas.fr/lazy-static/thumbnails/e6851419-7486-464f-8be9-41c12abcd7a8.jpgActivité de robotique portuaire au CRIStALMamadou Sarifou Diallo & Gerald Derbhomez (CRIStAL) - Activité de robotique portuaire au CRIStAL [Journée Robotique Mobile du réseau de métier 2RM](https://wiki.2rm.cnrs.fr/JT_robmob_2021) - 19 octobre 2021https://peertube.laas.fr/static/streaming-playlists/hls/e6851419-7486-464f-8be9-41c12abcd7a8/223d71cf-ed94-465b-9999-be710fddb7fa-master.m3u8https://peertube.laas.fr/videos/embed/ut1bKBC2Z2zrR6mXuXPzBf1763042021-10-22T12:52:44.553ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/rjyXohrHcxvC7WGFsNaLm7https://peertube.laas.fr/lazy-static/thumbnails/cd0c29dd-a79e-40fd-9874-b7f756910f06.jpgRetour d’expérience sur une campagne d’acquisition de donnéesSimon Lacroix - Retour d’expérience sur une campagne d’acquisition de données [Journée Robotique Mobile du réseau de métier 2RM](https://wiki.2rm.cnrs.fr/JT_robmob_2021) - 19 octobre 2021https://peertube.laas.fr/static/streaming-playlists/hls/cd0c29dd-a79e-40fd-9874-b7f756910f06/8b59f3ba-5397-430e-b499-e4a3ba859d05-master.m3u8https://peertube.laas.fr/videos/embed/rjyXohrHcxvC7WGFsNaLm72058092021-10-22T13:00:52.918ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/j1vkp7vYUmPrNfG9DSEq51https://peertube.laas.fr/lazy-static/thumbnails/91d692e9-debf-4cc9-8d09-9472d3f51778.jpgDétection de contexte environmental par GNSSFlorent Feriol (ISAE-SUPAERO) - Détection de contexte environmental par GNSS [Journée Robotique Mobile du réseau de métier 2RM](https://wiki.2rm.cnrs.fr/JT_robmob_2021) - 19 octobre 2021https://peertube.laas.fr/static/streaming-playlists/hls/91d692e9-debf-4cc9-8d09-9472d3f51778/e4533b44-a2be-4d9b-b103-105e9316d7d2-master.m3u8https://peertube.laas.fr/videos/embed/j1vkp7vYUmPrNfG9DSEq511148092021-10-22T13:09:57.101ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/75bdNU4cubsn5zSanSArCphttps://peertube.laas.fr/lazy-static/thumbnails/312c1b19-4e11-477c-98aa-a6154617ef93.jpgPrésentation de l'axe TIRREX Autonomous Land RoboticsRoland Lenain (INRAe) - Présentation de l'axe TIRREX Autonomous Land Robotics [Journée Robotique Mobile du réseau de métier 2RM](https://wiki.2rm.cnrs.fr/JT_robmob_2021) - 19 octobre 2021https://peertube.laas.fr/static/streaming-playlists/hls/312c1b19-4e11-477c-98aa-a6154617ef93/8916949a-81ca-4b30-b9c6-43d051f909be-master.m3u8https://peertube.laas.fr/videos/embed/75bdNU4cubsn5zSanSArCp15020112021-10-22T14:54:00.709ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/gkdSnHNrc4SGBbqWvy8VsGhttps://peertube.laas.fr/lazy-static/thumbnails/7c28245c-c623-4d30-b211-0e2ae9a61038.jpgServices et mécanismes des communications 5GPhilippe Owezarski (LAAS) - Services et mécanismes des communications 5G [Journée Robotique Mobile du réseau de métier 2RM](https://wiki.2rm.cnrs.fr/JT_robmob_2021) - 19 octobre 2021https://peertube.laas.fr/static/streaming-playlists/hls/7c28245c-c623-4d30-b211-0e2ae9a61038/af4e2ab1-daeb-4767-a956-ecf16171c7fa-master.m3u8https://peertube.laas.fr/videos/embed/gkdSnHNrc4SGBbqWvy8VsG1159062021-10-22T15:04:00.292ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/aDDPTQJ2S7ZoQqVjBu26RThttps://peertube.laas.fr/lazy-static/thumbnails/4e241410-b16d-4cbd-bf14-3c113e6f5ec9.jpgSLAM pour véhicules terrestres: évaluation des méthodes de l’état de l’art sur un véhicule instru...Mohammed Chghaf (Laboratoire SATIE) SLAM pour véhicules terrestres: évaluation des méthodes de l’état de l’art sur un véhicule instrumenté [Journée Robotique Mobile du réseau de métier 2RM](https://wiki.2rm.cnrs.fr/JT_robmob_2021) - 19 octobre 2021https://peertube.laas.fr/static/streaming-playlists/hls/4e241410-b16d-4cbd-bf14-3c113e6f5ec9/2663c700-074a-442b-ab58-d4fb7f4b7459-master.m3u8https://peertube.laas.fr/videos/embed/aDDPTQJ2S7ZoQqVjBu26RT17110132021-10-22T15:18:50.280ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/p5f9cHZBUGmwPUaUAU7Uy4https://peertube.laas.fr/lazy-static/thumbnails/bad9e114-5f86-478c-8290-43e6f0f94b83.jpgThe Open Dynamic Robot Initiative ProjectThomas Flayols (LAAS) - The Open Dynamic Robot Initiative Project: Présentation du robot SOLO [Journée Robotique Mobile du réseau de métier 2RM](https://wiki.2rm.cnrs.fr/JT_robmob_2021) - 19 octobre 2021https://peertube.laas.fr/static/streaming-playlists/hls/bad9e114-5f86-478c-8290-43e6f0f94b83/542dee7d-a479-4a16-891a-332efbcf3971-master.m3u8https://peertube.laas.fr/videos/embed/p5f9cHZBUGmwPUaUAU7Uy413700102021-10-22T15:27:22.335ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/cNZs3skAD4LEpFx53nn1EWhttps://peertube.laas.fr/lazy-static/thumbnails/5fa42494-4455-4ee6-802e-441a8ec66f2a.jpgTALOS: A new humanoid research platform targeted for industrial applications Abstract : The upcoming generation of humanoid robots will have to be equipped with state-of-the-art technical features along with high industrial quality, but they should also offer the prospect of effective physical human interaction. In this paper we introduce a new humanoid robot capable of interacting with a human environment and targeting a whole range of industrial applications. This robot is able to handle weights of 6 Kg with an outstretched arm, and has powerful motors to carry out movements unavailable in previous generations of humanoid robots. Its kinematics has been specially designed for screwing and drilling motions. In order to make interaction possible with human operators, this robot is equipped with torque sensors to measure joint effort and high resolution encoders to measure both motor and joint positions. The humanoid robotics field has reached a stage where robustness and repeatibility is the next watershed. We believe that, this robot has the potential to become a powerful tool for the research community to successfully navigate this turning point, as the humanoid robot HRP-2 was in its own time. https://peertube.laas.fr/static/streaming-playlists/hls/5fa42494-4455-4ee6-802e-441a8ec66f2a/4a6197bc-0a36-451b-aaf8-a1125b255012-master.m3u8https://peertube.laas.fr/videos/embed/cNZs3skAD4LEpFx53nn1EW1030162021-11-10T15:22:49.475Zmechatronicstorque controldesignTALOShumanoidYESMain ostasse channelNOhttps://peertube.laas.fr/w/rhSeS9Umaab6RKfgf49Tv7https://peertube.laas.fr/lazy-static/thumbnails/cccf53e6-4519-4e46-b203-826e22e255b4.jpgManaging Python Packagesslides: https://homepages.laas.fr/gsaurel/talks/managing-python-packages.pdf source: https://gitlab.laas.fr/gsaurel/talks/-/blob/main/managing-python-packages.md chat: https://im.laas.fr/#/room/#managing-python-packages:laas.fr BBB recording: https://seminar.laas.fr/playback/presentation/2.3/d50cf302cc75b1afe290cfaf702a5a556242db59-1636548062422 https://peertube.laas.fr/static/streaming-playlists/hls/cccf53e6-4519-4e46-b203-826e22e255b4/dd120a5c-dd58-488a-81b3-f3935bbdc61e-master.m3u8https://peertube.laas.fr/videos/embed/rhSeS9Umaab6RKfgf49Tv758080172021-11-10T16:03:33.553ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/qCg2ZtP8HhXGCjrQSs77fwhttps://peertube.laas.fr/lazy-static/thumbnails/c76b5e69-41b5-4096-847b-7df9f52da072.jpgPyrène manipulates a wooden plankThis video is the first experiment demonstrating the Agimus framework. The robot is asked to turn the plank upside-down and place it back on the table. Pyrène autonomously estimate the state of the world around it, plan a trajectory and automatically generate the real-time controllers necessary to robustly execute it.https://peertube.laas.fr/static/streaming-playlists/hls/c76b5e69-41b5-4096-847b-7df9f52da072/276761e9-3ce3-477c-8a9d-9757ad822ba0-master.m3u8https://peertube.laas.fr/videos/embed/qCg2ZtP8HhXGCjrQSs77fw960262021-11-11T16:36:06.139ZYESMain anicolin channelNOhttps://peertube.laas.fr/w/wk7um3z5QY7MV4rqxBH4AShttps://peertube.laas.fr/lazy-static/thumbnails/f59d4a4d-68a9-48d4-b1bd-335386288cca.jpgSOLO at SIANE 2021The robot SOLO being autonomous and wireless during the SIANE 2021 show. https://peertube.laas.fr/static/streaming-playlists/hls/f59d4a4d-68a9-48d4-b1bd-335386288cca/5f76b931-3462-49e4-aaac-09ad8c5f92a8-master.m3u8https://peertube.laas.fr/videos/embed/wk7um3z5QY7MV4rqxBH4AS40052021-11-17T13:09:38.229ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/7aWy8W7e8GM5SedHELgiU7https://peertube.laas.fr/lazy-static/thumbnails/31fa2562-ba13-4043-a996-c2b8d5b21f4a.jpgFailure of the torque control scheme using TSID on posture taskEven performing simple task in fixed environment can lead to instabilities, the authors encounter this problem while testing a classical torque control scheme using inverse dynamics on the robot TALOS on a simple postural task. After some repetition of a sinusoidal motion on the robot arm, the system diverged brutally and blocked some of its harmonic drive. The gains tuned in simulation (simulating the actuation chains) were too high for the real robot. Thus, even with gains tuned on a proper simulator with the model of the actuators, we cannot expect the solution to remain stable.https://peertube.laas.fr/static/streaming-playlists/hls/31fa2562-ba13-4043-a996-c2b8d5b21f4a/6444b6fc-a03a-4db2-aa9e-64bf86d38a45-master.m3u8https://peertube.laas.fr/videos/embed/7aWy8W7e8GM5SedHELgiU7440452021-11-20T19:00:57.647ZYESMain nramuzat channelNOhttps://peertube.laas.fr/w/uSPTfjJSX2vhukYxKktXc1https://peertube.laas.fr/lazy-static/thumbnails/e9d8948d-08d5-4de9-8f42-2986fbbf0242.jpgSucessful posture task of the torque control scheme using TSID First success of a simple posture task in torque using TSID on Pyrene. At the end the robot falls because the contacts on the feet have been disturbed (the feet moved) breaking the constraint of TSID.https://peertube.laas.fr/static/streaming-playlists/hls/e9d8948d-08d5-4de9-8f42-2986fbbf0242/751a155f-438c-414f-bb2b-84a3f23d1776-master.m3u8https://peertube.laas.fr/videos/embed/uSPTfjJSX2vhukYxKktXc1340232021-11-23T15:57:01.497ZYESMain nramuzat channelNOhttps://peertube.laas.fr/w/aUXUaTuu9Eu3yXwSLGrG5dhttps://peertube.laas.fr/lazy-static/thumbnails/50475f8e-4f85-4b3e-97cc-35826e5310fc.jpgROB4FAM UR10First UR10 experiments with HPP, Agimus, ViSP and SoT in the frame of the REACT project. Done by Thuc Long Ha and Florent Lamirauxhttps://peertube.laas.fr/static/streaming-playlists/hls/50475f8e-4f85-4b3e-97cc-35826e5310fc/d6567c5a-c464-4540-9059-ffb9858fcee5-master.m3u8https://peertube.laas.fr/videos/embed/aUXUaTuu9Eu3yXwSLGrG5d35092021-11-24T06:16:22.602ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/55jxogyTUrstVAeUKn8itahttps://peertube.laas.fr/lazy-static/thumbnails/20fef4c1-ad6a-4ac7-871f-f85710cc2e53.jpgBenedicte Vanwanseele keynote at SB conferenceKeynote of Benedicte Vanwanseele at SB conference in St Etienne, France. Wearable technology in order to measure biomechanics and movement characteristics: applications in health and sport.https://peertube.laas.fr/static/streaming-playlists/hls/20fef4c1-ad6a-4ac7-871f-f85710cc2e53/6e1c72c2-ee07-4061-b61e-eb1a3dd056e2-master.m3u8https://peertube.laas.fr/videos/embed/55jxogyTUrstVAeUKn8ita27600482021-11-26T16:45:07.911ZYESSociété de BiomécaniqueNOhttps://peertube.laas.fr/w/uuGH6soJ3yynUVEvuQm3Echttps://peertube.laas.fr/lazy-static/thumbnails/e6c1cba9-845a-45fa-a697-278c1521f3cf.jpgChristian Hellmich keynote at SB conferenceKeynote of Christian Hellmich at SB conference in St Etienne, France. Complex biomechanics: emergent patterns from atoms to organs.https://peertube.laas.fr/static/streaming-playlists/hls/e6c1cba9-845a-45fa-a697-278c1521f3cf/c2a68f0e-1c7a-4c09-a7e3-a8b2d585cc48-master.m3u8https://peertube.laas.fr/videos/embed/uuGH6soJ3yynUVEvuQm3Ec28600122021-11-26T17:40:03.765ZYESSociété de BiomécaniqueNOhttps://peertube.laas.fr/w/d5dr1VNJ6J13v9FfWayqQVhttps://peertube.laas.fr/lazy-static/thumbnails/61c44cd1-311e-4018-a519-6abca32963c5.jpgWalter Herzog keynoteKeynote of Walter Herzog at SB conference in St Etienne, France. The three filament sarcomere model: titin-actin-myosin interaction and force production.https://peertube.laas.fr/static/streaming-playlists/hls/61c44cd1-311e-4018-a519-6abca32963c5/b052b7db-fa43-403c-b4ee-8f42d9535be2-master.m3u8https://peertube.laas.fr/videos/embed/d5dr1VNJ6J13v9FfWayqQV27620312021-11-26T19:59:00.396ZYESSociété de BiomécaniqueNOhttps://peertube.laas.fr/w/skRBnjXr1a1re7bSxXuwPUhttps://peertube.laas.fr/lazy-static/thumbnails/d5534f56-1efb-41e3-9c19-10f1911e0bc2.jpgPassive Inverse Dynamics Control using a Global Energy Tank for Torque-Controlled Humanoid Robots...The video file proposes two Gazebo simulations demonstrating the robustness of the implemented Passive Inverse Dynamics controller. I- The first simulation consists in a contact-force task scenario. In this simulation the robot creates a contact between a cylinder, hold in its left hand, and a block. The robot applies a 30N force along the z-axis on it before the block is removed. This set-up is meant to represent a first step toward complex operations with contacts. It exposes the problem of unexpected broken contact that can be due to slippage or disturbances. The simulation is decomposed in three stages: - The desired force is first set to 10N to stabilize the contact: there is some slippage between the cylinder and the block until the force applied on the block is enough - Then it is increased to 30N to have a meaningful force application - Finally the block is removed after a delay of 15s, without planification Without the passivity constraint on the system, the robot quickly falls after the removal of the block. Whereas with the implemented solution, the force task in the controller is penalized by the energy tank and thus the tracking highly deteriorated, leading to a slow motion of the hand toward the ground. Thus, the controller has the time to remove the dangerous task, ensuring the safety of the system. II- The second simulation consists in a walk of 20cm steps on flat floor. In this simulation the robot walks one meter forward on flat floor with 20cm steps, starting with the right foot. The first and last steps are only 10cm long, and the first motion to swing the CoM of the robot is done in quasi-static. The double support duration is of 0.2s and the single support duration is of 1.2s. During the quasi-static swing of the CoM, the energy tank is emptied and the beta parameter decreases to 0 around the 10th seconds. The oscillations of the parameters lead the robot to oscillate as well because the beta, gamma parameters are used...https://peertube.laas.fr/static/streaming-playlists/hls/d5534f56-1efb-41e3-9c19-10f1911e0bc2/e4114eec-95d1-4cbb-8b47-20ab2bc409d4-master.m3u8https://peertube.laas.fr/videos/embed/skRBnjXr1a1re7bSxXuwPU3380272021-12-03T13:09:30.655ZWhole-body controlpassivity controlHumanoid robottorque controlYESMain nramuzat channelNOhttps://peertube.laas.fr/w/cEjZUzbiez6os1NFsavtAbhttps://peertube.laas.fr/lazy-static/thumbnails/5e6e7f27-2cff-46f7-bd46-6079ceda73a2.jpgTorque control reactive walk on TalosTorque control reactive walk on Taloshttps://peertube.laas.fr/static/streaming-playlists/hls/5e6e7f27-2cff-46f7-bd46-6079ceda73a2/96cc91aa-7dc5-4111-8b69-272d05bbd48e-master.m3u8https://peertube.laas.fr/videos/embed/cEjZUzbiez6os1NFsavtAb1180362021-12-17T10:00:08.293ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/p4xrnShnTVtmEqkqohWc1ehttps://peertube.laas.fr/lazy-static/thumbnails/bac0cb68-36a7-4223-bf22-e23b4552ab49.jpgWhole-body MPC: preliminary experiments with table contactThis is a preliminary experimental result with Talos controlled by a whole-body model predictive controller, following the methodology defined in the project "Memory of Motion". The robot has to create new contact with the table to enlarge its area of balance. https://peertube.laas.fr/static/streaming-playlists/hls/bac0cb68-36a7-4223-bf22-e23b4552ab49/9d161374-3709-4588-a239-efcd6baf8942-master.m3u8https://peertube.laas.fr/videos/embed/p4xrnShnTVtmEqkqohWc1e40092021-12-21T11:30:23.638ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/g1QjThrkgRRizo4KaF3NAfhttps://peertube.laas.fr/lazy-static/thumbnails/7996dc91-fcbd-432d-9522-3e6763b9d0da.jpgWhole-body MPC: preliminary experiments for steping in placeWhole-body MPC: preliminary experiments for steping in placehttps://peertube.laas.fr/static/streaming-playlists/hls/7996dc91-fcbd-432d-9522-3e6763b9d0da/d49b4863-722e-4fe2-846d-20f41b1fa091-master.m3u8https://peertube.laas.fr/videos/embed/g1QjThrkgRRizo4KaF3NAf32032021-12-21T13:59:17.873ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/fYoWH678Nadf9oZt5CVkaYhttps://peertube.laas.fr/lazy-static/thumbnails/793fbb4c-b387-4ec5-a444-35bbbce28036.jpgWhole-body MPC: preliminary experiments for walking forward (10cm steps)Whole-body MPC: preliminary experiments for walking forward (10cm steps)https://peertube.laas.fr/static/streaming-playlists/hls/793fbb4c-b387-4ec5-a444-35bbbce28036/28862bb5-2c2e-41be-91f3-b304a702bc9c-master.m3u8https://peertube.laas.fr/videos/embed/fYoWH678Nadf9oZt5CVkaY33072021-12-21T14:04:25.117ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/5Wf7qtnBfz67ZR2MVXHahihttps://peertube.laas.fr/lazy-static/thumbnails/27f76a0d-11de-4be0-8cd1-ad3e7b86e1ad.jpgLouis Montaut: Accelerated collision detectionPresentation by Louis at the MPC Willow/Gepetto joint workshop on 18/jan/2022https://peertube.laas.fr/static/streaming-playlists/hls/27f76a0d-11de-4be0-8cd1-ad3e7b86e1ad/5bdb2bd6-d857-40f3-abbf-2a89c9d2c6bc-master.m3u8https://peertube.laas.fr/videos/embed/5Wf7qtnBfz67ZR2MVXHahi33150212022-01-19T10:24:37.946ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/hYitAMe96DP9iPuBjSYCc8https://peertube.laas.fr/lazy-static/thumbnails/896ea3ba-1fa8-4beb-b95c-2b2dedf01875.jpgAccurate pointing of holes in a part by localization using vision Accurate pointing of holes in a part by localization using vision https://peertube.laas.fr/static/streaming-playlists/hls/896ea3ba-1fa8-4beb-b95c-2b2dedf01875/e00d0a3a-9bfe-4d8f-93ef-2eb8859a2a24-master.m3u8https://peertube.laas.fr/videos/embed/hYitAMe96DP9iPuBjSYCc815801232022-02-02T12:10:33.613ZYESMain florent channelNOhttps://peertube.laas.fr/w/4NFbiEAN9fGsphcbcdQ8ubhttps://peertube.laas.fr/lazy-static/thumbnails/1ecfc603-b326-495a-9e23-d0700f25d47e.jpgWorkshop CosyPose - SLAMJoan Sola -IRI- Mederic Fourmy -LAAS- Cesar Debeunne -ISAE- Torsten Sattler -CTU- Josef Sivic -CTU- Workshop on high-accuracy and high-frequency vision for legged robot localization Tentative workshop date: 15/2/2022, 10:00-12:30 Objective: During Summer 2022, we are planning to work on a shared project to finalize, integrate and experimentally evaluate a SLAM application for legged robots. The objective is to obtain high-accuracy high-frequency (1 kHz) localization of a legged robot, by fusing inputs coming from i) an inertial measurement unit ii) cameras and iii) kinematic contact. Several features of this project have already been validated. We are using the SLAM toolbox WOLF developed by the team of Joan Sola in Barcelona. It features IMU processes providing high-frequency information. We integrated in a first prototype the kinematic perception of our quadruped. We also did a first experience using CosyPose features (6D accurate information based on known object) in the SLAM. Relative camera-scene poses obtained by CosyPose act as high-level visual information, providing absolute measurements (somehow similar to place recognition, although more accurate and less versatile). We also have a plan to integrate visual odometry, for example based on KLT features, to complement the information extracted from the visual input by CosyPose. Ideally, by the end of the summer, we would like to target a complete real-time integration working with the sensors of the quadruped robot Solo, or even if possible on-board the real robot. The current organisation of the project is gathering 5 researchers from Barcelona and Toulouse in a distributed set up, with most of the vision expertise in Barcelona, and the experimental expertise in Toulouse. We would be happy to collect opinions or even additional expertise to join the project. Tentative workshop schedule (each slot is 15min + 5min questions): 15/2/2022 10:00-12:30 10:00-10:20 Joan Sola: Wolf toolbox for generic SLAM...https://peertube.laas.fr/static/streaming-playlists/hls/1ecfc603-b326-495a-9e23-d0700f25d47e/a70df43c-8edb-4cbc-8409-eb42dd54b1e2-master.m3u8https://peertube.laas.fr/videos/embed/4NFbiEAN9fGsphcbcdQ8ub83270172022-02-15T13:03:20.495ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/m9euxAqoDFquPhbzUufZwXhttps://peertube.laas.fr/lazy-static/thumbnails/a31d09c7-0101-45a1-814a-9dbb7e4b41b7.jpgImproved Control Scheme for the Solo Quadruped and Experimental Comparison of Model Predictive Co...Submission for RA-L + IROS 2022. Preprint available at https://hal.laas.fr/hal-03591735 Title of article: Improved Control Scheme for the Solo Quadruped and Experimental Comparison of Model Predictive Controllers Abstract: This paper presents significant improvements to the nominal control scheme of the open-access Solo-12 quadruped and an experimental comparative study of different Model Predictive Controllers (MPC) that were implemented and tested on the robot. The modifications of the controller formulation that improved the nominal behavior and reduced tracking oscillations are first described. Thanks to them, the maximum reachable velocity of the robot was doubled and the foot placement was improved. On this basis three MPCs of increasing complexity were compared to evaluate the validity of different assumptions and heuristics. They range from a simplified linear centroidal model with contact points fixed by a heuristics, to a nonlinear one that also optimizes the contact points locations. Experimental results show that, thanks to the fast solver Crocoddyl and the proposed formulation, similar performances can be obtained with a MPC that optimizes both the center of mass trajectory and the foot placement, while taking into accounts the nonlinearity of the centroidal model, than with a modular scheme using a heuristic for foot placement and considering a linearized model. This paves the way for future work such as leveraging information about the environment to improve footsteps placement and timings.https://peertube.laas.fr/static/streaming-playlists/hls/a31d09c7-0101-45a1-814a-9dbb7e4b41b7/23e922b6-b186-4a17-b000-893b13753288-master.m3u8https://peertube.laas.fr/videos/embed/m9euxAqoDFquPhbzUufZwX1910692022-02-24T18:31:35.380Zquadrupedsolompciros2022locomotionYESMain paleziart channelNOhttps://peertube.laas.fr/w/tDLr1kN2UmdKVmQhd1Vf8chttps://peertube.laas.fr/lazy-static/thumbnails/dfeca51c-c2cf-468a-b46a-86f808e9a561.jpgConstrained Differential Dynamic Programming: A primal-dual augmented Lagrangian approachConstrained Differential Dynamic Programming: A primal-dual augmented Lagrangian approachhttps://peertube.laas.fr/static/streaming-playlists/hls/dfeca51c-c2cf-468a-b46a-86f808e9a561/362255bf-e657-496a-8c84-9d5f0732a48c-master.m3u8https://peertube.laas.fr/videos/embed/tDLr1kN2UmdKVmQhd1Vf8c5801142022-03-04T09:51:52.622ZYESWilson JalletNOhttps://peertube.laas.fr/w/8kdTr3QPkQmf77fStMPZGChttps://peertube.laas.fr/lazy-static/thumbnails/3b5f0b43-4f42-4bd3-bf2d-80dc1b251cc0.jpgPhD Alexis NicolinPlanification de tâches d’asservissement visuel en robotiquehttps://peertube.laas.fr/static/streaming-playlists/hls/3b5f0b43-4f42-4bd3-bf2d-80dc1b251cc0/9087ac55-65f7-4d0b-8402-655fce404ad3-master.m3u8https://peertube.laas.fr/videos/embed/8kdTr3QPkQmf77fStMPZGC70620142022-03-07T12:22:39.207ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/th1MsmmSKwPchb95UNVxuLhttps://peertube.laas.fr/lazy-static/thumbnails/dce3208a-38df-4fcd-9ae6-208a20f1e088.jpgPhD Noëlie RamuzatRobotics Force/Torque Control for Manufacturing Operationshttps://peertube.laas.fr/static/streaming-playlists/hls/dce3208a-38df-4fcd-9ae6-208a20f1e088/b2597ac8-1b30-4841-ad67-3e0c8f829e0b-master.m3u8https://peertube.laas.fr/videos/embed/th1MsmmSKwPchb95UNVxuL94000142022-03-07T13:29:22.455ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/bodJXxZnouMk9yzjBngRHMhttps://peertube.laas.fr/lazy-static/thumbnails/541599eb-36ca-4da2-99a3-52b3cf91cbe3.jpgIntroducing Force Feedback in Model Predictive ControlIn the literature about model predictive control (MPC), contact forces are planned rather than controlled. In this paper, we propose a novel paradigm to incorporate effort measurements into a predictive controller, hence allowing to control them by direct measurement feedback. We first demonstrate why the classical optimal control formulation, based on position and velocity state feedback, cannot handle direct feedback on force information. Following previous approaches in force control, we then propose to augment the classical formulations with a model of the robot actuation, which naturally allows to generate online trajectories that adapt to sensed position, velocity and torques. We propose a complete implementation of this idea on the upper part of a real humanoid robot, and show through hardware experiments that this new formulation incorporating effort feedback outperforms classical MPC in challenging tasks where physical interaction with the environment is crucial.https://peertube.laas.fr/static/streaming-playlists/hls/541599eb-36ca-4da2-99a3-52b3cf91cbe3/7ca36c6c-c52c-4f1b-b9b8-f6e6501fe12e-master.m3u8https://peertube.laas.fr/videos/embed/bodJXxZnouMk9yzjBngRHM590372022-03-07T16:06:02.366ZYESMain skleff channelNOhttps://peertube.laas.fr/w/jxJoVMBrqtQYty4Q14tYPBhttps://peertube.laas.fr/lazy-static/thumbnails/9632ae06-2466-46cf-9d4d-6f45ee8b4d91.jpgReactive and accurate pointing of holes in a part by localization using visionReactive and accurate pointing of holes in a part by localization using visionhttps://peertube.laas.fr/static/streaming-playlists/hls/9632ae06-2466-46cf-9d4d-6f45ee8b4d91/b524df8b-6920-482f-aac5-0d8ccf7660c3-master.m3u8https://peertube.laas.fr/videos/embed/jxJoVMBrqtQYty4Q14tYPB3500742022-03-14T17:38:44.664ZYESMain dbury channelNOhttps://peertube.laas.fr/w/bJAcbvFo6ktg1U9dyU838Thttps://peertube.laas.fr/lazy-static/thumbnails/56edb26d-e2c3-46ac-909b-61f55d10c569.jpgCOSYSLAMCOSYSLAMhttps://peertube.laas.fr/static/streaming-playlists/hls/56edb26d-e2c3-46ac-909b-61f55d10c569/45418be7-e3fa-433e-95e6-659fceba188d-master.m3u8https://peertube.laas.fr/videos/embed/bJAcbvFo6ktg1U9dyU838T2110552022-03-16T14:50:55.583ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/aiaTKYjkdqDfXT7FR7dnLQhttps://peertube.laas.fr/lazy-static/thumbnails/4b47fd09-857a-447e-aa37-c60c7d38c5bc.jpgReal time footstep planning and control of the Solo quadruped robot in 3D environmentsReal time footstep planning and control of the Solo quadruped robot in 3D environmentshttps://peertube.laas.fr/static/streaming-playlists/hls/4b47fd09-857a-447e-aa37-c60c7d38c5bc/3a6a9d8c-84f5-47f7-926f-dfa0b268afbc-master.m3u8https://peertube.laas.fr/videos/embed/aiaTKYjkdqDfXT7FR7dnLQ22401432022-03-23T11:22:55.981ZYESMain frisbourg channelNOhttps://peertube.laas.fr/w/16ocWJHhVwxNr4qYkjGNEXhttps://peertube.laas.fr/lazy-static/thumbnails/00c0675b-65f4-4b92-9d01-bd1777fe988b.jpgICRA22-1504ICRA 2022 presentation video for Differential Value Programming.https://peertube.laas.fr/static/streaming-playlists/hls/00c0675b-65f4-4b92-9d01-bd1777fe988b/82a700c7-c967-4c55-a490-6b2dcd215d12-master.m3u8https://peertube.laas.fr/videos/embed/16ocWJHhVwxNr4qYkjGNEX237062022-04-06T16:13:40.523ZYESMain aparag channelNOhttps://peertube.laas.fr/w/8wPavZthto9SfAan36LV65https://peertube.laas.fr/lazy-static/thumbnails/3cfd5980-ce38-4721-b644-61f0e85fbcca.jpgDeepFactors, presenté par Moussa Bendjilali, cours Robotic@Supaero 2022DeepFactors, presenté par Moussa Bendjilali, cours Robotic@Supaero 2022https://peertube.laas.fr/static/streaming-playlists/hls/3cfd5980-ce38-4721-b644-61f0e85fbcca/91a0a34b-81df-4265-9991-fe81dfe9a485-master.m3u8https://peertube.laas.fr/videos/embed/8wPavZthto9SfAan36LV65721092022-04-07T08:58:16.707ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/cYdnWMAtCh6bwSfK3Dxyh1https://peertube.laas.fr/lazy-static/thumbnails/60edce08-2b7f-43e7-9366-ed57cdab4f48.jpgKangaroo hip: problem with the constraintKangaroo hip: problem with the constrainthttps://peertube.laas.fr/static/streaming-playlists/hls/60edce08-2b7f-43e7-9366-ed57cdab4f48/7457ef1b-478a-4a6e-86aa-47a1dc351132-master.m3u8https://peertube.laas.fr/videos/embed/cYdnWMAtCh6bwSfK3Dxyh184032022-04-14T21:54:57.331ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/2CoBonw7qt5bxJuhs2WwXNhttps://peertube.laas.fr/lazy-static/thumbnails/0d2dd92d-5914-4ea4-9cfc-96557a38ec9c.jpgReading report on "Do diff-sim give better policy gradient?", paper by Tedrake's team, red by Fab...Reading report on "Do diff-sim give better policy gradient?", paper by Tedrake's team, red by Fabian Schram, INRIA Parishttps://peertube.laas.fr/static/streaming-playlists/hls/0d2dd92d-5914-4ea4-9cfc-96557a38ec9c/d850ab40-4999-40b4-aca5-6536b509d683-master.m3u8https://peertube.laas.fr/videos/embed/2CoBonw7qt5bxJuhs2WwXN28640242022-04-26T15:05:40.988ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/aB2sFNq8BdVC7bfsEVU42ghttps://peertube.laas.fr/lazy-static/thumbnails/4dc62e01-a995-47d8-9cb9-a585fabed565.jpgSimple 2d models mimicking Kangaroo actuation, although with less joints and incorrect sizesSimple 2d models mimicking Kangaroo actuation, although with less joints and incorrect sizeshttps://peertube.laas.fr/static/streaming-playlists/hls/4dc62e01-a995-47d8-9cb9-a585fabed565/0eb1bbd8-9191-4611-b3da-d25218f3fcf8-master.m3u8https://peertube.laas.fr/videos/embed/aB2sFNq8BdVC7bfsEVU42g180262022-04-27T14:40:08.588ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/8mHyvUtRGc384AcwiRHL6jhttps://peertube.laas.fr/lazy-static/thumbnails/3b94756a-9fdf-4316-83e2-c682a5d4de7c.jpgECOLAASTICOT_VDEFPrésentation du collectif [Ecolaas](https://www.laas.fr/projects/ecolaas/) qui a pour but de soutenir toute démarche de développement durable et de préservation de l'environnement dans le cadre du LAAShttps://peertube.laas.fr/static/streaming-playlists/hls/3b94756a-9fdf-4316-83e2-c682a5d4de7c/9584e42f-1814-49a8-9bda-1e68dceb310b-master.m3u8https://peertube.laas.fr/videos/embed/8mHyvUtRGc384AcwiRHL6j2360272022-05-05T14:25:45.882ZMobilitéEcologieDéveloppement durableBiodiversitéEthiqueYESMain marido channelNOhttps://peertube.laas.fr/w/58MhY9pLDWnPvhQ9kAAidghttps://peertube.laas.fr/lazy-static/thumbnails/217aac6e-3969-4058-8cc8-0cccadca827b.jpgImproved Control Scheme for the Solo Quadruped and Experimental Comparison of Model Predictive Co...Submission for RA-L + IROS 2022. Preprint available at https://hal.laas.fr/hal-03591735 Title of article: Improved Control Scheme for the Solo Quadruped and Experimental Comparison of Model Predictive Controllers Abstract: This paper presents significant improvements to the nominal control scheme of the open-access Solo-12 quadruped and an experimental comparative study of different Model Predictive Controllers (MPC) that were implemented and tested on the robot. The modifications of the controller formulation that improved the nominal behavior and reduced tracking oscillations are first described. Thanks to them, the maximum reachable velocity of the robot was doubled and the foot placement was improved. On this basis three MPCs of increasing complexity were compared to evaluate the validity of different assumptions and heuristics. They range from a simplified linear centroidal model with contact points fixed by a heuristics, to a nonlinear one that also optimizes the contact points locations. Experimental results show that, thanks to the fast solver Crocoddyl and the proposed formulation, similar performances can be obtained with a MPC that optimizes both the center of mass trajectory and the foot placement, while taking into accounts the nonlinearity of the centroidal model, than with a modular scheme using a heuristic for foot placement and considering a linearized model. This paves the way for future work such as leveraging information about the environment to improve footsteps placement and timings.https://peertube.laas.fr/static/streaming-playlists/hls/217aac6e-3969-4058-8cc8-0cccadca827b/71cefce8-fd58-4828-9adf-e2b02ae7fab7-master.m3u8https://peertube.laas.fr/videos/embed/58MhY9pLDWnPvhQ9kAAidg2260502022-05-28T20:10:23.492Zquadrupedsolompclocomotioniros2022 YESMain paleziart channelNOhttps://peertube.laas.fr/w/aAV1fc9iMR8hhobsPs4C7ohttps://peertube.laas.fr/lazy-static/thumbnails/4dc2337d-476f-4108-a2a4-5c7e1eaffe7a.jpgPyrene reaches to an object by leaning on a tableThis video demonstrates an algorithm that computes paths for a humanoid robot that should reach to an object on a table and that lean on the table to reach the object. The ultimate goal of this algorithm is to provide learning input for computing a memory of motion.https://peertube.laas.fr/static/streaming-playlists/hls/4dc2337d-476f-4108-a2a4-5c7e1eaffe7a/11365bc1-74f4-4c4c-a9f3-5bd07b673c73-master.m3u8https://peertube.laas.fr/videos/embed/aAV1fc9iMR8hhobsPs4C7o145202022-06-16T13:54:31.849ZYESMain florent channelNOhttps://peertube.laas.fr/w/vuSFq4TfjxTqE3umqQeRwWhttps://peertube.laas.fr/lazy-static/thumbnails/eee1143f-73d3-4e58-966e-8b6633f241ee.jpgstairs_downstairs_downhttps://peertube.laas.fr/static/streaming-playlists/hls/eee1143f-73d3-4e58-966e-8b6633f241ee/b1daedc5-f6f7-422d-809c-a2323caabcce-master.m3u8https://peertube.laas.fr/videos/embed/vuSFq4TfjxTqE3umqQeRwW300112022-06-19T14:33:07.026ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/vqeoaeofyUoPsmLDQ1mUQwhttps://peertube.laas.fr/lazy-static/thumbnails/ee3b1e5c-cf97-44a2-83bf-dbc847b768ae.jpgMini tutorial of optimal control for bipeds: from trajectory optimization to whole-body model pre...Mini tutorial of optimal control for bipeds: from trajectory optimization to whole-body model predictive controlhttps://peertube.laas.fr/static/streaming-playlists/hls/ee3b1e5c-cf97-44a2-83bf-dbc847b768ae/37aad3f4-5d49-4256-a28b-b943b8146a56-master.m3u8https://peertube.laas.fr/videos/embed/vqeoaeofyUoPsmLDQ1mUQw1870162022-06-21T07:23:53.828ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/qqPDEuDVbhfbdQ5e8VDCQvhttps://peertube.laas.fr/lazy-static/thumbnails/c5d28b15-0a5a-4f03-b933-df0f1f4a72c5.jpgTalos stable multicontactUsing whole-body Model Predictive Control, Talos is making contact with a table and applying 50N on its surface. https://peertube.laas.fr/static/streaming-playlists/hls/c5d28b15-0a5a-4f03-b933-df0f1f4a72c5/d661e3c2-eead-4d5c-b8ec-bb3ee64576d9-master.m3u8https://peertube.laas.fr/videos/embed/qqPDEuDVbhfbdQ5e8VDCQv250122022-06-21T12:19:14.077ZYESMain edantec channelNOhttps://peertube.laas.fr/w/nx9LoyHHnyzcyB8QhK8Qt1https://peertube.laas.fr/lazy-static/thumbnails/ae695edc-b4d6-4b06-9ab0-daa3f971ec26.jpgMemmo: experiments with Talos doing torque-control stuffsMemmo: experiments with Talos doing torque-control stuffshttps://peertube.laas.fr/static/streaming-playlists/hls/ae695edc-b4d6-4b06-9ab0-daa3f971ec26/16354fa2-a877-4884-a3f6-4c8630b371e5-master.m3u8https://peertube.laas.fr/videos/embed/nx9LoyHHnyzcyB8QhK8Qt1300172022-06-21T16:59:50.471ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/4yfMaJSC2hFdZXnwy9aXWEhttps://peertube.laas.fr/lazy-static/thumbnails/1ccc5308-c708-47d8-aac6-5adaf49b6806.jpgICP Localization and Walking Experiments on a TALOS Humanoid RobotAbstract : This system paper describes the integration and the evaluation of an ICP-based localization system on the TALOS humanoid robot. The new generation of flash LiDAR systems, here an Ouster OS1-64, have made it possible to obtain 3D clouds at 10 Hz. Coupled with an Intel RealSense T265 providing visual-inertial odometry it is possible to localize the robot and use this information to generate foot steps in real time to reach specific points. The approach is validated with a Qualisys motion capture system. It is also used to generate real-time walking motion on the TALOS humanoid robot. This paper is an integration paper showing that it is now feasible to accurately guide a humanoid robot in an environment in real time using a LiDAR system.https://peertube.laas.fr/static/streaming-playlists/hls/1ccc5308-c708-47d8-aac6-5adaf49b6806/0809c8f2-7820-4109-8fa9-b8c562a9551d-master.m3u8https://peertube.laas.fr/videos/embed/4yfMaJSC2hFdZXnwy9aXWE1450152022-06-21T18:20:32.338ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/oFEKzRA8rc8qABJnVfJWpkhttps://peertube.laas.fr/lazy-static/thumbnails/b7b2f060-ad10-4a62-b33c-4d76b00441b1.jpgRehearsal Review Meeting MemmoRehearsal Review Meeting Memmohttps://peertube.laas.fr/static/streaming-playlists/hls/b7b2f060-ad10-4a62-b33c-4d76b00441b1/5ac25480-532e-4e12-b9ed-d31af7d99b75-master.m3u8https://peertube.laas.fr/videos/embed/oFEKzRA8rc8qABJnVfJWpk1687042022-06-30T10:08:06.037ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/m2Q7LkE24REVRcTceadmr7https://peertube.laas.fr/lazy-static/thumbnails/a2382b7e-4a7f-454b-8dcc-6c93b27a8a50.jpgFrom the Study of Table Trajectories during Collaborative Carriages toward Pro-active Human-Robot...Submitted to ICHR 2022 The study of human-human interactions is essential for a better understanding of human behaviour during collaborative tasks. This knowledge is not only interesting in life science but can also be useful in robotic science. Indeed, to efficiently assist a human partner during a human-robot collaboration, the robot needs to be as reactive as a human would be. This can only be achieved by embedding a model of human behaviour into the robot control scheme. In this paper, a human-humanoid robot collaboration to carry a table is tackled. First, the experimental Center of Mass (CoM) trajectories of a table carried by 20 pairs of subjects to various goal positions are studied and modeled using an optimal control problem. Then, based on this model, a prediction process which accurately predicts the table trajectories is designed. Finally, this prediction process is coupled with the robot Walking Pattern Generator (WPG). Using a torque whole-body controller, this framework is tested in simulation on Gazebo on a TALOS humanoid robot model. In this simulation, the robot actively assists a simulated human partner in lifting and carrying a table to an unknown goal position.https://peertube.laas.fr/static/streaming-playlists/hls/a2382b7e-4a7f-454b-8dcc-6c93b27a8a50/896ece1c-842e-4dd6-b4df-314a157e35ea-master.m3u8https://peertube.laas.fr/videos/embed/m2Q7LkE24REVRcTceadmr71740112022-07-01T10:41:51.864ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/r4uA52hrEHfErjdTN5GyZVhttps://peertube.laas.fr/lazy-static/thumbnails/caf150bf-878b-40d9-88db-710b71730f9f.jpgWhole-Body Model Predictive Control for Biped Locomotion on a Torque-Controlled Humanoid RobotIn this video, the humanoid robot Talos performs various walking motions, including stairstep crossing, using a whole-body model predictive control scheme based on the Crocoddyl library.https://peertube.laas.fr/static/streaming-playlists/hls/caf150bf-878b-40d9-88db-710b71730f9f/3726f7c1-0d79-4a6d-bfd8-121ab8e2f07f-master.m3u8https://peertube.laas.fr/videos/embed/r4uA52hrEHfErjdTN5GyZV10801552022-07-15T09:52:30.495ZYESMain edantec channelNOhttps://peertube.laas.fr/w/pDo2j2tCu8xfZrpivVavfdhttps://peertube.laas.fr/lazy-static/thumbnails/bf7a47d4-072c-4ae3-92da-8f08450f31e4.jpgPyrene, the first TALOS, crossing the debris in torque control modeMotion Planing realized thanks to Pierre Fernbach during his PhD using C-CROC, and with PAL-Robotics task space inverse dynamics.https://peertube.laas.fr/static/streaming-playlists/hls/bf7a47d4-072c-4ae3-92da-8f08450f31e4/4d9e6de5-318d-4df3-80ce-ea4abaa99333-master.m3u8https://peertube.laas.fr/videos/embed/pDo2j2tCu8xfZrpivVavfd34042022-07-18T13:22:09.022ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/ewRCsBdxB5XUjGud9Uhb9Hhttps://peertube.laas.fr/lazy-static/thumbnails/6d95b34c-ce35-4201-9586-d510c729f121.jpgCentroidal MPC + stabilizer + TSID Nice first walk for Pyrène, the first TALOS, to perform large stride with centroidal MPC.https://peertube.laas.fr/static/streaming-playlists/hls/6d95b34c-ce35-4201-9586-d510c729f121/d3553d6e-9886-464f-8a65-9d052bdcf2e8-master.m3u8https://peertube.laas.fr/videos/embed/ewRCsBdxB5XUjGud9Uhb9H85052022-07-18T13:26:35.994ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/5hqKtpfc64ZGDMWEaPcHTKhttps://peertube.laas.fr/lazy-static/thumbnails/22afb517-ee8c-45ee-ae6c-c1cef70cba45.jpgStephane Caron: Motion control bits for homemade robotsStephane Caron: Motion control bits for homemade robotshttps://peertube.laas.fr/static/streaming-playlists/hls/22afb517-ee8c-45ee-ae6c-c1cef70cba45/4a200191-0120-4aaf-a7b5-7f4baa3eaf4c-master.m3u8https://peertube.laas.fr/videos/embed/5hqKtpfc64ZGDMWEaPcHTK33590232022-07-22T17:06:33.318ZYESGepetto Scientific MeetingsNOhttps://peertube.laas.fr/w/taWiZ6KwoWdYaCFjP7BVCphttps://peertube.laas.fr/lazy-static/thumbnails/dc09e853-7c36-4c1c-9856-1193578e52eb.jpgTorque-control locomotion achieved in TALOSThis video shows the locomotion obtained on the robot TALOS as a result of the studies carried out in "Torque Controlled Locomotion of a Biped Robot with Link Flexibility", submitted to Humanoids 2022.https://peertube.laas.fr/static/streaming-playlists/hls/dc09e853-7c36-4c1c-9856-1193578e52eb/ad36b33f-45b2-4945-80fd-c1e26c765633-master.m3u8https://peertube.laas.fr/videos/embed/taWiZ6KwoWdYaCFjP7BVCp1635332022-07-29T23:33:27.555ZTalosTorque controlYESMain nvilla channelNOhttps://peertube.laas.fr/w/w6VCbWqymGeZDfends3Qdhhttps://peertube.laas.fr/lazy-static/thumbnails/3e62eccc-660b-40d8-be0a-2a6a07ba5e0c.jpgSeamless integration of Optitrack motion capture with ROS by Aarsh Thakker (L2S)This work proposes a new tool to smoothly integrate the latest versions of Motive software for OptiTrack motion capture system to ROS1. The current development uses the NatNet SDK 4.0 interface to transmit and convert the data from Motive software to the ROS topics over the shared network. The package promises user-friendliness and greater functionalities than currently available open-source packages within a single package, such as tracking of individual passive markers, Skeleton data, markers as a pointcloud, etc. Individual passive marker tracking increases the range of detection, the confidence in the position along with the cost reduction of the entire system.https://peertube.laas.fr/static/streaming-playlists/hls/f3c5ecf2-a811-498f-866b-c6b68b5a4cb8/a1d34f3f-953d-4854-ad8c-e1231c8e9fc6-master.m3u8https://peertube.laas.fr/videos/embed/w6VCbWqymGeZDfends3Qdh3200432022-08-09T05:51:53.959ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/uqtizcq1LECCMb9pAnbQgChttps://peertube.laas.fr/lazy-static/thumbnails/7165bc2b-cd73-4606-a5ea-ad85b382c6cb.jpgYASMIN: Yet Another State MachINe library for ROS 2 by Vicente OliveraState machines are a common mechanism for defining behaviors in robots, defining them based on identifiable stages. There are several libraries available for easing the implementation of states machines in ROS 1, as SMACH or SMACC, but there are fewer alternatives for ROS 2. YASMIN is yet another library specifically designed for ROS 2 for easing the design of robotic behaviors using state machines. It is available in C++ and Python, provides some default states to speed up the development, and a web viewer for monitoring the execution of the system and helping in the debugging.https://peertube.laas.fr/static/streaming-playlists/hls/e62a8f1b-8800-4416-8ca4-b9d7e0b3a12a/1510aa7d-aa15-4801-aaae-444b0d054b4b-master.m3u8https://peertube.laas.fr/videos/embed/uqtizcq1LECCMb9pAnbQgC7720572022-08-09T06:21:50.719ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/cXzZoVtQ2f7tsoWWZ5p1bBhttps://peertube.laas.fr/lazy-static/thumbnails/fb17dc87-e8ee-443b-ab4a-3727cfbea6ef.jpgethercat_driver_ros2: EtherCAT compatible module integration with ros2_control by Maciej Bednarcz...EtherCAT fieldbus protocol provides applications with the capacity of reliable, real-time communication between systems and is therefore a common industrial standard. In order to simplify the development/deployment of new application using EtherCAT modules, the ethercat_driver_ros2 package allows to combine them with ros2_control. This driver proposes a generic ways to parametrize and assemble Hardware Interfaces based on EtherCAT protocole compatible modules that can be defined using parameter files.https://peertube.laas.fr/static/streaming-playlists/hls/60d76122-350c-49a9-be7a-9133ff769f5f/94901957-5e74-4397-8242-4f55c306cd39-master.m3u8https://peertube.laas.fr/videos/embed/cXzZoVtQ2f7tsoWWZ5p1bB8150422022-08-09T06:39:55.467ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/dAmVEo9GrJLrcwLpashtZehttps://peertube.laas.fr/lazy-static/thumbnails/412519a4-053b-4dec-9af8-1e76eccf3a2c.jpgROS2-Control: An overviewros2_control is a hardware-agnostic control framework with a focus on both real-time performance and sharing of controllers. The framework has become one of the main utility for abstracting hardware and low-level control for 3rd party solutions like MoveIt2 and Nav2 systems. The presentation provides a practical tips to use ros2_control, from creating a robot description, writing hardware drivers to configuring standard controllers. Some of the hot-new features, like controller chaining, will be shown. Furthermore, you will get introduced to concepts like modular reuse of hardware drivers, multi-robot architectures and parameters injection for controllers.https://peertube.laas.fr/static/streaming-playlists/hls/65f9d903-cc94-4ac6-af33-077678498643/bce5d6b2-5848-4d6b-9fc1-c31f64ae96be-master.m3u8https://peertube.laas.fr/videos/embed/dAmVEo9GrJLrcwLpashtZe386802042022-08-12T05:58:00.181ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/mSaKa3RKEA3D3gQimAv2oPhttps://peertube.laas.fr/lazy-static/thumbnails/2c771b52-8519-4a47-91c4-ebf5c712d8c8.jpgFaire des merveilles avec Hawksbill et Jellyfish: 22.04 et les nouveautés de CoreLors de la conception d’une machine industrielle, les questions de temps réel et de sécurité s’imposent très rapidement. De plus, l’utilisation de ROS peut s’avérer complexe dès lors que la machine possède de multiples actionneurs. Nous présentons ici nos préconisations en termes d’architecture système, utilisant ROS et des organes tiers comme des automates et automates de sécurité. A travers les usages que nous avons pu avoir de ROS, nous présenterons les verrous techniques rencontrés et les solutions qui ont été mise en oeuvre.https://peertube.laas.fr/static/streaming-playlists/hls/a8f7f779-6169-4900-ab03-2aeb16109eb7/fa596f0a-c938-4d50-b15f-a401a84a1e13-master.m3u8https://peertube.laas.fr/videos/embed/mSaKa3RKEA3D3gQimAv2oP2056012022-08-12T06:40:01.762ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/v51KDfye67kDtDFU8C8pRfhttps://peertube.laas.fr/lazy-static/thumbnails/847f322b-6a5d-446d-b511-2ea6b07ca91d.jpgRoboStack - true cross-platform package management for ROSThe ROS ecosystem consists of hundreds of interdependent packages. RoboStack is a new distribution of the ROS 1 Noetic and ROS 2 Galactic packages that leverages the success of the conda-forge scientific packaging community and the mamba package manager. Contrary to the default ROS packages, RoboStack packages work across many Linux distributions as well as macOS and Windows. Additionally, the mamba package manager supports the creation of virtual environments that makes it easy to work with multiple different ROS versions side-by-side. Contrary to containers, the RoboStack packages run directly on the host system which makes working with GUI applications seamless. Because the package cache is shared between different environments, this is also more space efficient than running in containers. The RoboStack distribution is built on top of packages maintained by the conda-forge community. conda-forge is a packaging community that focuses on scientific applications and data science. Therefore, many bleeding edge data science and machine learning tools can be found – readily packaged – on conda-forge and they all work seamlessly with the RoboStack packages. The talk will show the automated package building infrastructure in use by the RoboStack project, the usage of the RoboStack packages and how robot developers can start building and publishing their own packages on top of the RoboStack ROS distribution.https://peertube.laas.fr/static/streaming-playlists/hls/eb6875be-4f68-45ab-9deb-13fe16db2b9c/37aa5a52-3254-4acd-8667-78cb10feed3a-master.m3u8https://peertube.laas.fr/videos/embed/v51KDfye67kDtDFU8C8pRf27190202022-08-12T06:52:19.403ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/wupQ86N2tnyekjwXw5buXvhttps://peertube.laas.fr/lazy-static/thumbnails/2bab9e5c-60ec-4c64-950f-2c4575f2a317.jpgAnatomy of a marine simulation - Carlos Aguero - OSRFTerrestrial simulations have been historically the main use case for Gazebo. However, marine applications can take extra benefit from the well-known advantages of using a simulator given the complexity of the environment and the costs associated with deploying robots at the ocean. This presentation will navigate through the different components required to simulate maritime applications and the recent features added to Gazebo.https://peertube.laas.fr/static/streaming-playlists/hls/f6e9abc2-3485-4b91-bd66-07b77e0595d3/469c4ca4-c4fc-44f2-996d-c423425c9430-master.m3u8https://peertube.laas.fr/videos/embed/wupQ86N2tnyekjwXw5buXv33730122022-08-12T08:08:41.514ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/im8EXnpgWJuiA4GszXLLJNhttps://peertube.laas.fr/lazy-static/thumbnails/ba7b279c-ae88-495e-a3cb-a69822a70645.jpgPrésentation éclaire - Guillaume Doisy (Wyca) ros2-cartographerGuillaume Doisy de Wyca Robotics présente les dernières extensions de cartographer portées sur ROS2.https://peertube.laas.fr/static/streaming-playlists/hls/8c7af5de-cb56-4192-8015-203b01d3e452/7b64eac9-4b96-4483-b3d2-87513e158460-master.m3u8https://peertube.laas.fr/videos/embed/im8EXnpgWJuiA4GszXLLJN144082022-08-12T08:55:57.947ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/xc8N3uBfpacrExtjN5D7z5https://peertube.laas.fr/lazy-static/thumbnails/49a7454f-7b8a-4fb1-8784-674994d8f281.jpgArchitecture et performances de ROS pour des applications robotiques nécessitant des comportement...par Julien Viaud - Capacités SAS Lors de la conception d’une machine industrielle, les questions de temps réel et de sécurité s’imposent très rapidement. De plus, l’utilisation de ROS peut s’avérer complexe dès lors que la machine possède de multiples actionneurs. Nous présentons ici nos préconisations en termes d’architecture système, utilisant ROS et des organes tiers comme des automates et automates de sécurité. A travers les usages que nous avons pu avoir de ROS, nous présenterons les verrous techniques rencontrés et les solutions qui ont été mise en oeuvre.https://peertube.laas.fr/static/streaming-playlists/hls/fc994876-6d63-4ed7-843b-0f9d539ac81e/97126651-221a-4cc2-9875-fffdf36dad40-master.m3u8https://peertube.laas.fr/videos/embed/xc8N3uBfpacrExtjN5D7z516690122022-08-12T09:11:35.428ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/kG7de5DCZPtsD77uvjBbachttps://peertube.laas.fr/lazy-static/thumbnails/c8403a2b-991b-49f0-8531-3550afec0d9f.jpgBonnes pratiques ROS2 pour la conception d’un joueur d’échecs robotiquepar Ludovic Deval - IRT Jules Verne Le but de cette présentation est de revenir sur les bonnes pratiques générales concernant les développements autour de ROS et en particulier ROS2. Elle montrera comment l’application de ces bonnes pratiques a permis la réalisation d’un robot joueur d’échec rapidement et facilement.https://peertube.laas.fr/static/streaming-playlists/hls/9f77367e-c65f-4298-8a60-d569bfb77d35/bf678dea-2d1c-4830-91e3-668e0464b8e9-master.m3u8https://peertube.laas.fr/videos/embed/kG7de5DCZPtsD77uvjBbac1330092022-08-12T09:23:48.181ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/2iNQsmsnsrTAehS3RTFKKGhttps://peertube.laas.fr/lazy-static/thumbnails/16a833ae-10ce-4a76-bb70-51c0d6325182.jpgROS pour Unreal Engine 4 par Adrien Vigne (LAAS, CNRS)Nous présentons ici un plugin pour le moteur de jeu vidéo Unreal Engine afin de rendre possible l’utilisation de ROS à la fois en programmation graphique que via du code C++. A la différence des solutions existante, notre contribution tend à se rapprocher de l’interface de ROScpp avec notamment l’utilisation des services ROS de manière synchrone. Nous illustrons l’intérêt de cette contribution avec l’intégration de Unreal Engine dans une architecture robotique entièrement basée sur ROS et l’accès à une base de connaissance pour pouvoir configurer un environnement virtuel.https://peertube.laas.fr/static/streaming-playlists/hls/0a95a567-0287-4818-bf39-f623d7efc45a/c353352c-f1d3-417e-a330-54c362309bef-master.m3u8https://peertube.laas.fr/videos/embed/2iNQsmsnsrTAehS3RTFKKG9340192022-08-13T06:47:12.399ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/eMMnddKtGs84QmUJDwSGg5https://peertube.laas.fr/lazy-static/thumbnails/7ae181e2-b19a-48aa-ab7a-342fea978b34.jpgROS2 pour le prototypage appliqué à l’exploration spatiale au CNES par Raphaël Viards (Magellium)Le CNES dispose d’un atelier logiciel (EDRES) dédié à la robotique d’exploration reposant sur de nombreuses années de R&D. Parmi ces outils figurent des algorithmes pour la perception, la localisation et la navigation des rovers utilisés dans des missions réelles (e.g. système de navigation autonome à bord de la mission Exomars). Afin de faciliter le prototypage des futurs systèmes pour la navigation autonome pour les rovers, le CNES et Magellium travaillent à l’intégration d’EDRES au sein de ROS2. Il est possible de tester ces algorithmes qualifiés pour le vol dans des contextes différents, et de faciliter l’intégration sur les démonstrateurs du CNES.https://peertube.laas.fr/static/streaming-playlists/hls/6fab3ad6-94c6-4730-9987-e3025b44355a/fc149182-5708-43f3-83c2-b5caa37ce6ae-master.m3u8https://peertube.laas.fr/videos/embed/eMMnddKtGs84QmUJDwSGg521840102022-08-13T17:33:17.672ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/hmXQcQ57JXpy41MQ5kw7eahttps://peertube.laas.fr/lazy-static/thumbnails/6f888a2d-c599-4258-86e6-8aa5544e2837.jpgPrésentation éclairsPrésentation de la demo live du jeu d'échecs sous ROS-2 Présentation de la simulation du rover sur la lune https://peertube.laas.fr/static/streaming-playlists/hls/847f8048-0a51-4748-a064-46206b352bb3/46b0e0d6-8269-4048-aabc-ffcd16b2c981-master.m3u8https://peertube.laas.fr/videos/embed/hmXQcQ57JXpy41MQ5kw7ea816062022-08-13T20:49:21.760ZYESROSConFr 2022NOhttps://peertube.laas.fr/w/eK3eNgxeLxG5fP64jEK8mVhttps://peertube.laas.fr/lazy-static/thumbnails/7fed9afa-5dee-4236-8e18-0b414e074bd3.jpgACTION : Cooperation between heterogeneous robots for patrolling missionsThe Action project aims at performing patrolling missions with cooperating terrestrial, aerial and marine autonomous robots. The complementary skills of the various vehicles are integrated to enhance the achievement of area monitoring missions. In this first aeroterrestrial scenario, the Autonomous Aerial Vehicle RMax/ReSSAC from ONERA cooperates with the Autonomous Ground Vehicle Mana from LAAS-CNRS to detect, localize and track a mobile tarket while minimizing the intervention of the operator.https://peertube.laas.fr/static/streaming-playlists/hls/6f4929f1-654b-4668-ba10-6167acfcdd51/238bc197-20f2-45a8-8134-c335d97f19fc-master.m3u8https://peertube.laas.fr/videos/embed/eK3eNgxeLxG5fP64jEK8mV2580112022-08-23T14:16:37.086ZcooperationresearchMulti-robot cooperationdroneRobotYESArchives Robotique NOhttps://peertube.laas.fr/w/t1BSmgf8Bn8p1HeomzDdZDhttps://peertube.laas.fr/lazy-static/thumbnails/01aa67e5-dbb2-411e-bb40-564afe4e767b.jpgFirst result with Crocoddyl and whole-body predictive control (WB-MPC) on Solo, at LAASFirst result with Crocoddyl and whole-body predictive control (WB-MPC) on Solo, at LAAShttps://peertube.laas.fr/static/streaming-playlists/hls/dabcd92b-4e24-481d-be0d-7a936b91d117/526b82dc-da03-45df-8e11-0d67cae205b2-master.m3u8https://peertube.laas.fr/videos/embed/t1BSmgf8Bn8p1HeomzDdZD500282022-09-08T16:36:43.424ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/tfqwHJoQnpP3YToHSaxAKEhttps://peertube.laas.fr/lazy-static/thumbnails/c635be28-f617-49b7-9590-ce2a1fb10df0.jpg20220912_172835Experiments on solohttps://peertube.laas.fr/static/streaming-playlists/hls/dcaa4606-28f8-441b-8a11-147456935c94/197ed69b-10dd-4599-a216-0e5136676c0d-master.m3u8https://peertube.laas.fr/videos/embed/tfqwHJoQnpP3YToHSaxAKE93072022-09-19T16:56:23.306ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/hJ4odfrTR53CCuCesovkcDhttps://peertube.laas.fr/lazy-static/thumbnails/b9cffab0-64cb-4ea2-a7d4-34780e1c95e8.jpg20220912_172243Exp2 on solohttps://peertube.laas.fr/static/streaming-playlists/hls/87718aae-0485-4b3c-ad90-0df15108d3b7/2180c10a-39aa-4e94-9ebf-ce5eba32234b-master.m3u8https://peertube.laas.fr/videos/embed/hJ4odfrTR53CCuCesovkcD6270162022-09-20T08:43:09.932ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/drc4tTpot4gnikTTADiKCLhttps://peertube.laas.fr/lazy-static/thumbnails/9e6affde-8de8-4b1d-a47f-78f761b8a757.jpgICRA2022 - Implicit Differential Dynamic ProgrammingICRA2022 - Implicit Differential Dynamic Programminghttps://peertube.laas.fr/static/streaming-playlists/hls/64b212fb-335a-4297-913a-7183c4cd7bd8/501abdd6-684f-4394-aaf9-c0a766269f15-master.m3u8https://peertube.laas.fr/videos/embed/drc4tTpot4gnikTTADiKCL227052022-09-23T10:30:20.158ZYESWilson JalletNOhttps://peertube.laas.fr/w/93W5exAMfG4oJKq7i2KKJJhttps://peertube.laas.fr/lazy-static/thumbnails/88a7aa18-d263-4537-8543-5adbf3b7eecd.jpgTorque Controlled Locomotion of a Biped Robot with Link FlexibilityVideo related to the article "Torque Controlled Locomotion of a Biped Robot with Link Flexibility" of the 2022 IEEE-RAS International Conference on Humanoid Robots (Humanoids 2022)https://peertube.laas.fr/static/streaming-playlists/hls/4131eba4-eaf7-4ad7-b9c5-029f57b980a2/59e56e5d-e237-4bbb-8b81-b50fd086804a-master.m3u8https://peertube.laas.fr/videos/embed/93W5exAMfG4oJKq7i2KKJJ25701172022-11-02T09:49:04.392ZTalostorque controldynamic walkhip bendingYESMain nvilla channelNOhttps://peertube.laas.fr/w/3zKd5ohGdynnKmcQ1X7VuChttps://peertube.laas.fr/lazy-static/thumbnails/3573e178-e7f2-48fc-91be-5ad6fa6c677a.jpgJaxon from JSK - 2nd of November 2022 - IROS 2022 (Kyoto), the robot is controlled in positionJaxon is crossing an uneven robot while being in equilibrium.https://peertube.laas.fr/static/streaming-playlists/hls/14e87321-7489-4f13-a416-ec9589ed97d0/28689a82-f6f6-4e98-bef4-311f32cb4d82-master.m3u8https://peertube.laas.fr/videos/embed/3zKd5ohGdynnKmcQ1X7VuC670452022-11-02T13:28:03.339ZYESMissions Olivier RobotsNOhttps://peertube.laas.fr/w/3dkCkMsZveZBCmu4iDJYnXhttps://peertube.laas.fr/lazy-static/thumbnails/254b2514-e137-4c97-bcef-d99e7ae13937.jpgRobot FanucThis robot is doing a new pallet from two others by choosing the next box to put. This video was taken on Mujin premises the 31th of October 2022.https://peertube.laas.fr/static/streaming-playlists/hls/11eb4c40-cf8d-4911-af36-9e9a4da4db19/f3b2dd97-8153-4b0f-a9f2-b71111765bef-master.m3u8https://peertube.laas.fr/videos/embed/3dkCkMsZveZBCmu4iDJYnX168032022-11-03T02:04:27.881ZYESMissions Olivier RobotsNOhttps://peertube.laas.fr/w/82cM1C1KEqxGXtDEM161nDhttps://peertube.laas.fr/lazy-static/thumbnails/f0330ec0-57b9-4048-9985-44280e594777.jpgTALOS slope - 4TALOS slope - 4https://peertube.laas.fr/static/streaming-playlists/hls/38daf8bd-2bd6-49c3-a583-350c91164fcf/1f2fb7e2-023c-4b8b-81cb-65d1c0ebfe13-master.m3u8https://peertube.laas.fr/videos/embed/82cM1C1KEqxGXtDEM161nD2040112022-11-09T16:21:28.795ZtalosgepettoYESWilson JalletNOhttps://peertube.laas.fr/w/wFygm3HqkkYSrc7b75hBVYhttps://peertube.laas.fr/lazy-static/thumbnails/bc053cc0-2036-48e2-9aca-b61d06b589f7.jpgWhole-Body MPC without Foot References for the Locomotion of an Impedance-Controlled Robothttps://gepettoweb.laas.fr/articles/assirelli_icra22.htmlhttps://peertube.laas.fr/static/streaming-playlists/hls/f8780cf3-0a9a-4b76-adac-400f822c1b26/2e7bc312-4c77-4c43-b42f-b027d97190d1-master.m3u8https://peertube.laas.fr/videos/embed/wFygm3HqkkYSrc7b75hBVY1630522022-11-10T13:52:55.465ZYESMain frisbourg channelNOhttps://peertube.laas.fr/w/hsRcuZPfq83Hj7gc2KfF24https://peertube.laas.fr/lazy-static/thumbnails/0c2605b7-eb9e-483d-a785-22df44367c1d.jpgWhole-Body Control and Estimation of Humanoid Robots with Link FlexibilityVideo published at Humanoids22 with the article "Whole-Body Control and Estimation of Humanoid Robots with Link Flexibility" From Giulio Romualdi, Nahuel Villa, Stefano Dafarra, Daniele Pucci and Olivier Stasse.https://peertube.laas.fr/static/streaming-playlists/hls/8551e047-b26f-4e15-b4d6-17d45e07f679/d6dfa654-9183-4c84-a2a9-fac6716f6fdb-master.m3u8https://peertube.laas.fr/videos/embed/hsRcuZPfq83Hj7gc2KfF24232032022-11-15T11:03:07.902ZTalosWhole-Body DynamicsInverse DynamicsFlexible robotTask Space Inverse DynamicsYESMain nvilla channelNOhttps://peertube.laas.fr/w/9rWWqSRw5aEhwm18Vggorchttps://peertube.laas.fr/lazy-static/thumbnails/b7a1b694-98cf-4d84-8367-1cf50c786f86.jpgWhole-Body Model Predictive Control Locomotion on TalosUsing a 14 DoF model and a MPC scheme based on the optimal control library Crocoddyl, Talos performs dynamic walking motions with and without foot reference trajectories.https://peertube.laas.fr/static/streaming-playlists/hls/44688f7f-8d5a-479c-a6f3-91b541f438f5/1029e157-3f9e-493f-bb96-d70e0153a606-master.m3u8https://peertube.laas.fr/videos/embed/9rWWqSRw5aEhwm18Vggorc900272022-11-17T09:30:59.594ZYESMain edantec channelNOhttps://peertube.laas.fr/w/mY94m7B3tRdA2WdWvz55tKhttps://peertube.laas.fr/lazy-static/thumbnails/6aca5439-692f-4366-8edb-caff63e61c5c.jpgPeau Artificielle LAAS 1977Présentation de la peau artificielle réalisée au LAAS du CNRS en 1977https://peertube.laas.fr/static/streaming-playlists/hls/a9cd63da-b372-46cd-b8b1-4a54f2af9d29/7d0f68bb-0b4b-443a-b2cb-db8d4e5120be-master.m3u8https://peertube.laas.fr/videos/embed/mY94m7B3tRdA2WdWvz55tK2785192022-11-24T01:22:34.153ZYESArchives Robotique NOhttps://peertube.laas.fr/w/ajNAUmLJ6seXPTCtTyV7cQhttps://peertube.laas.fr/lazy-static/thumbnails/b8cf246f-5897-4b1f-b9ce-b17a033e2ddc.jpgextracteur-1980extracteur-1980https://peertube.laas.fr/static/streaming-playlists/hls/4b825aeb-e1f7-40c7-aa07-db41a2276c6e/8cd4ffb8-3662-4ae5-ad6a-4d8582e603d2-master.m3u8https://peertube.laas.fr/videos/embed/ajNAUmLJ6seXPTCtTyV7cQ66062024-04-05T15:46:54.136ZYESArchives Robotique NOhttps://peertube.laas.fr/w/5pU3RBZxiDDhbCQEWTSXjQhttps://peertube.laas.fr/lazy-static/thumbnails/51cb5c18-402c-47ca-b2fa-bc11dd80333c.jpghilare-planification-1981-82hilare-planification-1981-82https://peertube.laas.fr/static/streaming-playlists/hls/23babce2-66f5-4b14-ac07-047f9125c240/61d9a244-ec20-4558-8549-6d310d2edc0a-master.m3u8https://peertube.laas.fr/videos/embed/5pU3RBZxiDDhbCQEWTSXjQ2175292022-11-24T01:22:37.808ZYESArchives Robotique NOhttps://peertube.laas.fr/w/nFm7rSv5y25yEHSwBFCosxhttps://peertube.laas.fr/lazy-static/thumbnails/9fda1be6-3814-45b7-b071-4fd11fd9c7c4.jpgModelisation of a Human-Exoskeleton Interaction for Cerebral Palsy"Modelisation of a Human-Exoskeleton Interaction for Cerebral Palsy" - Bonnefoy, Otmani, et al. Submitted to ISMR 2023https://peertube.laas.fr/static/streaming-playlists/hls/af8e5014-ee45-43e6-8db7-8bcd26dc648b/545faeb0-e014-4c2c-9d20-3fc0adb4d5f7-master.m3u8https://peertube.laas.fr/videos/embed/nFm7rSv5y25yEHSwBFCosx1400132022-12-07T17:01:16.260ZYESMain abonnefoy channelNOhttps://peertube.laas.fr/w/iYBBmHeFmcxBtJxHFZPcrehttps://peertube.laas.fr/lazy-static/thumbnails/aa897f7e-70ae-4c30-9461-7a7510a8edfc.jpgPhD Sabrina OtmaniPhD Sabrina Otmanihttps://peertube.laas.fr/static/streaming-playlists/hls/9192f41b-1a84-456b-bcc6-747e1cc4f94b/c101386b-1d7f-4007-b3a1-5605851bf623-master.m3u8https://peertube.laas.fr/videos/embed/iYBBmHeFmcxBtJxHFZPcre5978072022-12-22T12:58:36.816ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/qezHhvZjZ812zWy8oswDcGhttps://peertube.laas.fr/lazy-static/thumbnails/11432e95-9d62-41a0-ad44-2d5a6a3e8bc7.jpgPhD Jason CheminPhD Jason Cheminhttps://peertube.laas.fr/static/streaming-playlists/hls/c440c5c1-d124-4a94-99a0-69ba62ef28aa/38f9508f-2099-4b4e-aee3-599b6aa3c954-master.m3u8https://peertube.laas.fr/videos/embed/qezHhvZjZ812zWy8oswDcG7141082022-12-22T14:09:32.324ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/tv5J86Jnem2DgryaV2FzYdhttps://peertube.laas.fr/lazy-static/thumbnails/6f6cfa18-cfcd-4ea5-a51a-3a7419af87e2.jpgPhD Pierre-Alexandre LéziartPhD Pierre-Alexandre Léziarthttps://peertube.laas.fr/static/streaming-playlists/hls/deb639ce-4416-4f6e-8bf0-be3f6739a4e8/a6688e38-ba1e-4193-9d72-4a6cf42eb872-master.m3u8https://peertube.laas.fr/videos/embed/tv5J86Jnem2DgryaV2FzYd68340242022-12-22T14:41:36.925ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/uXgfVKh61qXPJutKUXWdf4https://peertube.laas.fr/lazy-static/thumbnails/077c8a80-cfc7-4be2-90a4-b42a020dd2af.jpgPhD Florent ForgetPhD Florent Forgethttps://peertube.laas.fr/static/streaming-playlists/hls/ea773148-4daa-4a88-aab9-475e1c17f47f/0dff0599-b4ef-4708-af02-bd23f9d631b4-master.m3u8https://peertube.laas.fr/videos/embed/uXgfVKh61qXPJutKUXWdf42727022022-12-22T14:54:22.293ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/uFQpxvnnSTRF1KGrd58of7https://peertube.laas.fr/lazy-static/thumbnails/2fba59b4-3d40-4768-b480-589f940ff1b9.jpgPhD Mathieu GeisertPhD Mathieu Geiserthttps://peertube.laas.fr/static/streaming-playlists/hls/e84fb880-dc3a-42e8-ad34-d47d13f57262/19c5d6c4-ad67-4ded-8cb5-f46ac2dcb977-master.m3u8https://peertube.laas.fr/videos/embed/uFQpxvnnSTRF1KGrd58of77370072022-12-22T15:27:55.735ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/c2qwwygWGjzAGWyC1do5kRhttps://peertube.laas.fr/lazy-static/thumbnails/41901588-0e6d-486b-9958-ebf2f311602e.jpgPhD Isabelle MarogerPhD Isabelle Marogerhttps://peertube.laas.fr/static/streaming-playlists/hls/59476248-3959-4094-9ccd-68304dbc9c3f/efcda41a-5906-4d82-bdfd-6fcb23339e07-master.m3u8https://peertube.laas.fr/videos/embed/c2qwwygWGjzAGWyC1do5kR7718092022-12-22T16:04:23.383ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/13CzUtzZAyE4qs2XC8rbBuhttps://peertube.laas.fr/lazy-static/thumbnails/fb0ae9e5-109f-458d-9099-7b2ef3dd3d60.jpgPhD Martin JacquetPhD Defense of Martin Jacquet, 23/08/2022 "Methods for Online Predictive Control of Multi-rotor Aerial Robots with Perception-driven Tasks subject to Sensing and Actuation Constraints" https://www.theses.fr/2022ISAT0021https://peertube.laas.fr/static/streaming-playlists/hls/005e0898-a340-437a-a957-5e2a7b83c78a/a53de951-d893-47e0-b3d4-5149071fcc5a-master.m3u8https://peertube.laas.fr/videos/embed/13CzUtzZAyE4qs2XC8rbBu10408022023-02-22T19:43:52.149ZYESMain mjacquet channelNOhttps://peertube.laas.fr/w/fdNoEYswhZd8a3dgPYAHzVhttps://peertube.laas.fr/lazy-static/thumbnails/34fdca5b-5e03-4237-8f00-a5a314ed4e35.jpgTowards Zero-Shot Transfer Learning Between Robots by Samuel BeaussantAbstract : The Reinforcement Learning (RL) field has been successfully applied to a wide range of problems in the past years, demonstrating both its versatility and efficiency. The robotic domain in particular benefited from the tremendous progresses made in RL. Despite numerous improvement regarding its sample-efficiency, learning a policy from scratch still requires millions (if not dozens of millions) of interactions with the environment to converge to a high-reward policy. This is usually because the agent does not have any prior information about the task or its own physical embodiment. In general, the canonical way to address and mitigate data-hungriness is to use Transfer Learning (TL), a method leveraging prior experience or knowledge to speed up learning of a distinct but related task. This is currently extensively used in deep learning based Computer Vision or Natural Language Processing. However, finding a practical and general approach for pre-training and transfer learning in the context of RL policies, is still an open research problem. In this work, we explore TL in the context of RL with the specific purpose of transferring policies from one agent to another, even in the presence of morphology discrepancies or different state-action spaces. In other words, we wish to reuse knowledge acquired by an agent (source) on a task to speed up (or even avoid) the learning process of a dissimilar agent (target) on the same task. We highlight the particular challenges raised by the application of TL in the context of cross-robot skill transfer and, inspired by prior works, propose an efficient method to address these matters. https://peertube.laas.fr/static/streaming-playlists/hls/732974b4-e3fd-4f66-ac01-089d8c1e4363/0558828a-8110-42aa-a6fc-eea86afcda5d-master.m3u8https://peertube.laas.fr/videos/embed/fdNoEYswhZd8a3dgPYAHzV2984062023-04-11T15:54:16.188ZYESSeminars in GepettoNOhttps://peertube.laas.fr/w/bzAHYBkMTo4RZQBdk6kC6bhttps://peertube.laas.fr/lazy-static/thumbnails/5d368253-cc5f-4ef6-b615-5c3ccb3b0f29.jpgWBMPC with PROXDDP - Experimental reels (april 21 2023)WBMPC with PROXDDP - Experimental reels (april 21 2023)https://peertube.laas.fr/static/streaming-playlists/hls/55ac548c-46f4-4279-b866-3f8d553317e4/292c1f76-8d10-4738-b0bb-a0b8f555b2c9-master.m3u8https://peertube.laas.fr/videos/embed/bzAHYBkMTo4RZQBdk6kC6b2030642023-05-14T13:20:56.142ZYESWilson JalletNOhttps://peertube.laas.fr/w/ibQaE94Zw2hHz3LDNx3p9Rhttps://peertube.laas.fr/lazy-static/thumbnails/93c5b3f1-e563-4452-b536-16d848995716.jpgOverworld: Assessing the geometry of the world for Human-Robot InteractionFor a robot to interact with humans in a given environment, a key need is to understand its environment in terms of the objects composing it, the other agents acting in it, and the relations between all of them. The capability is often called the ...https://peertube.laas.fr/static/streaming-playlists/hls/8b2e7a84-9fd5-431b-ab31-96d52150e17d/e6aebc54-795e-4416-b544-f8ada5498d8e-master.m3u8https://peertube.laas.fr/videos/embed/ibQaE94Zw2hHz3LDNx3p9R106002023-05-22T11:34:31.330ZYESMain matthieu channelNOhttps://peertube.laas.fr/w/hnAWBo9oWXaBfMnPXdvvrLhttps://peertube.laas.fr/lazy-static/thumbnails/4f984d71-3bbe-4e85-acfe-c7cec8e5169e.jpgThe Director Task:a Psychology-Inspired Task to Assess Cognitive and Interactive Robot ArchitecturesAuthors: G. Sarthou, A. Mayima, G. Buisan, K. Belhassein, A. Clodic Assessing robotic architecture for Human-Robot Interaction can be challenging due to the number of features a robot has to endow to perform an acceptable interaction. While everyday-inspired tasks are interesting as reflecting a realistic use of such robots, they often contain a lot of unknown and uncontrolled conditions and specific robot behavior can be hard to test. In this paper, we propose a new psychology-inspired task, gathering perspective-taking, planning, knowledge representation with theory of mind, manipulation, and communication. Along with a precise description of the task allowing its replication, we present a cognitive robot architecture able to perform it in its nominal cases. We finally suggest some challenges and evaluations for the Human-Robot Interaction research community, all derived from this easy-to-replicate task. Accepted in the 30th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2021) https://ro-man2021.org/https://peertube.laas.fr/static/streaming-playlists/hls/84965f08-b33d-463b-85c7-55ca8285fad2/5f024085-67d0-4400-a5f3-2f3577bd2555-master.m3u8https://peertube.laas.fr/videos/embed/hnAWBo9oWXaBfMnPXdvvrL184032023-05-22T15:37:20.428ZYESMain matthieu channelNOhttps://peertube.laas.fr/w/hQkdojd7dsoc6sxqMxZwpzhttps://peertube.laas.fr/lazy-static/thumbnails/7294f42f-71e9-4a45-aec5-467fcbf893ed.jpgvideoComets-720x576Final demonstration of the Comets project (May 2005)https://peertube.laas.fr/static/streaming-playlists/hls/8851c2a1-97c9-4c02-8785-bfb87435b807/d9da73ae-7959-4612-ac3d-10eddc668d22-master.m3u8https://peertube.laas.fr/videos/embed/hQkdojd7dsoc6sxqMxZwpz209012023-05-22T15:40:55.634ZFire MonitoringArial RoboticsYESArchives Robotique NOhttps://peertube.laas.fr/w/5cMkJPoYydtrGnTTnzLv9Uhttps://peertube.laas.fr/lazy-static/thumbnails/10842ee5-ac8e-4f91-88dc-94f2d590a83a.jpgpotentiel-640x480-15fpsReactive navigation with potential fields (1998)https://peertube.laas.fr/static/streaming-playlists/hls/2209ad96-1696-44a3-b42e-943ad2cd0a68/c46f1dd0-fd0a-4de6-9ed0-22a0b728c453-master.m3u8https://peertube.laas.fr/videos/embed/5cMkJPoYydtrGnTTnzLv9U184032023-05-22T15:42:33.512Znavigationlamaoutdoors roboticsYESArchives Robotique NOhttps://peertube.laas.fr/w/t2cNxEBrUxm3sbKGXHJP5Hhttps://peertube.laas.fr/lazy-static/thumbnails/0e37e0c3-6a8e-4508-952f-a8e17ebdc141.jpgspaceCity-640x480-15fpsLama in the "Space City" museum (2000) (3 min 20 sec sequence - no sound) This one is not very illustrative, as it only shows Lama roving without any visual explanation of the involved algorithms. It was recorded in the garden of the Cité de l'Espace museum of Toulouse, during a week-end organized within the temporary "Destination Mars" exposition. It was the first time that Lama evolved autonomously in public: very impressed, Lama was not in its best shape, and only accepted to evolve slowly, wavering along its paths. Related publications Simon Lacroix, Anthony Mallet, David Bonnafous, Gérard Bauzil, Sara Fleury, Matthieu Herrb and Raja Chatila. Autonomous Rover Navigation on Unknown Terrains. Demonstrations in the Space Museum ``Cité de l'Espace'' at Toulouse. In 7th International Symposium on Experimental Robotics. Honolulu, HI (USA), 2000. https://peertube.laas.fr/static/streaming-playlists/hls/dad1c2da-a8bc-4c00-b601-262651a695ad/fb574522-3983-455b-99a1-85ecfe3e057e-master.m3u8https://peertube.laas.fr/videos/embed/t2cNxEBrUxm3sbKGXHJP5H198562023-05-22T16:18:07.006ZYESArchives Robotique NOhttps://peertube.laas.fr/w/nZrXPuNBYfrubCgspmYHTHhttps://peertube.laas.fr/lazy-static/thumbnails/5a464f7c-0de7-4265-a275-e7647af85513.jpgassemblageassemblagehttps://peertube.laas.fr/static/streaming-playlists/hls/b2154e80-3af3-48fd-b256-2a15402bf5db/546269e9-2810-4959-9553-aea02442c84c-master.m3u8https://peertube.laas.fr/videos/embed/nZrXPuNBYfrubCgspmYHTH661032023-05-25T10:06:22.230ZrobotiqueassemblageYESArchives Robotique NOhttps://peertube.laas.fr/w/6tXH9VwHmE7Tm1d5DuZz4Phttps://peertube.laas.fr/lazy-static/thumbnails/38dff806-f0b8-425d-99a9-d142dc21e8cb.jpgIdentification et manipulation de pièces d'HorlorgerieFilmes CNRS - Antenne 2 - 1982https://peertube.laas.fr/static/streaming-playlists/hls/2c651b79-4856-453f-8516-0b2be870ee49/6b8be331-ebc6-4d53-bb32-47850f646bef-master.m3u8https://peertube.laas.fr/videos/embed/6tXH9VwHmE7Tm1d5DuZz4P48012023-05-30T16:12:13.811ZassemblagemanipulationidentificationYESArchives Robotique NOhttps://peertube.laas.fr/w/hHMNETLrcsfEbrE8vPxCcihttps://peertube.laas.fr/lazy-static/thumbnails/111e707d-f92f-4309-8cbb-9b1aa430c240.jpgAssemblage automatique Commande avec retour d'effortsFims CNRS - Antenne 2 - 1982 https://peertube.laas.fr/static/streaming-playlists/hls/8767f0f6-403d-4fb4-82d9-4adebf871f47/bd6ffd9c-d90b-4351-b444-a1165e2ee4b5-master.m3u8https://peertube.laas.fr/videos/embed/hHMNETLrcsfEbrE8vPxCci157012023-05-30T16:14:16.072Zretour d'effortsassemblagecommandeYESArchives Robotique NOhttps://peertube.laas.fr/w/mND4NKt63Ysy2UnrZHZgXMhttps://peertube.laas.fr/lazy-static/thumbnails/135feadf-a9c1-4027-bacf-eedcc79c6bc8.jpgcompliance-active-19821982https://peertube.laas.fr/static/streaming-playlists/hls/a879d441-3bfe-40b4-9f7e-ec40cd712397/67ccfe32-c4ee-4e25-a463-97d36a1871fe-master.m3u8https://peertube.laas.fr/videos/embed/mND4NKt63Ysy2UnrZHZgXM208002023-05-30T16:18:11.402ZYESArchives Robotique NOhttps://peertube.laas.fr/w/v1w4qE3XKtRcSU57useZb8https://peertube.laas.fr/lazy-static/thumbnails/0e36fc4e-09fa-490c-a020-b1903ed985ba.jpgAssemblage - Compliance passive1979https://peertube.laas.fr/static/streaming-playlists/hls/eaeb8bb2-5077-4380-9047-94c551ab2ff7/72cb2f5f-54d2-413a-8b84-ae4e6d30109e-master.m3u8https://peertube.laas.fr/videos/embed/v1w4qE3XKtRcSU57useZb8139012023-05-30T16:18:53.974Zcompliance passiveassemblageYESArchives Robotique NOhttps://peertube.laas.fr/w/ab4kgPbXpXGnY49rAoivtUhttps://peertube.laas.fr/lazy-static/thumbnails/bdcbdebe-b8fd-4cc0-9a04-1ad606f1aed1.jpgAssemblage dans un univers de cubes - Génération de plansFilm CNRS - Antenne 2 - 1982https://peertube.laas.fr/static/streaming-playlists/hls/4a49bd3e-7d28-44d1-8441-7eaf9e6805ee/d2495f8a-8341-4799-825f-1e9a28b748a2-master.m3u8https://peertube.laas.fr/videos/embed/ab4kgPbXpXGnY49rAoivtU113042023-05-30T16:20:51.807ZcubesassemblageplanificationYESArchives Robotique NOhttps://peertube.laas.fr/w/kQjwfAtpRE1zd8eP2xpLPehttps://peertube.laas.fr/lazy-static/thumbnails/4d4ad880-f53c-40a2-8737-61ce30f06006.jpgExtracteur de contours - 1980Extracteur de contours - 1980https://peertube.laas.fr/static/streaming-playlists/hls/a09cbff4-c914-413e-8395-72f54862224b/1f1f6f15-47d9-47ba-b524-5f66237b3b00-master.m3u8https://peertube.laas.fr/videos/embed/kQjwfAtpRE1zd8eP2xpLPe62522023-05-30T16:24:43.565ZYESArchives Robotique NOhttps://peertube.laas.fr/w/riXe7SJpw3QHaFYaWLifdHhttps://peertube.laas.fr/lazy-static/thumbnails/0b3e9ba0-ffb1-49c5-81b8-bae00c55afa8.jpgHilare - Suivi de parois par ultrasons1979https://peertube.laas.fr/static/streaming-playlists/hls/ccf6251a-5a46-44b8-b8f0-34bffafc3f41/a63fc34b-91c8-4115-920a-f24721362c1a-master.m3u8https://peertube.laas.fr/videos/embed/riXe7SJpw3QHaFYaWLifdH1415152023-05-30T16:25:18.497Zsuiviultra-sonshilareYESArchives Robotique NOhttps://peertube.laas.fr/w/gTJkohzkXhN38iWieLGTFAhttps://peertube.laas.fr/lazy-static/thumbnails/23a90c02-844b-4861-bbf4-1e5f6605b4ca.jpgla peau artificielleReconnaissance d'objets avec une pince à mors parallèles (travail effectué en 1977) Film CNRS - Antenne 2 - 1982https://peertube.laas.fr/static/streaming-playlists/hls/80b219ff-76d9-407e-9ea6-ff8b6e45d584/51273bb9-1169-4902-be4e-517e1b17be49-master.m3u8https://peertube.laas.fr/videos/embed/gTJkohzkXhN38iWieLGTFA85022023-05-30T16:26:00.833ZYESArchives Robotique NOhttps://peertube.laas.fr/w/ey24oR7YvnTVJAmybUkTQAhttps://peertube.laas.fr/lazy-static/thumbnails/2e138e91-b6b8-49f4-af70-c31f444ec3c9.jpgHilare et les autres-a2-cnrs-1982Hilare et les autres-a2-cnrs-1982https://peertube.laas.fr/static/streaming-playlists/hls/6dbf416b-f1b6-421e-bd4b-86d7e8f155a6/aeefb2d8-31ef-496a-acbd-203e288b0a29-master.m3u8https://peertube.laas.fr/videos/embed/ey24oR7YvnTVJAmybUkTQA14910272023-05-30T16:35:28.464ZYESArchives Robotique NOhttps://peertube.laas.fr/w/a8vJgSKZSNXpsgWX9AsLPohttps://peertube.laas.fr/lazy-static/thumbnails/54c59013-a0f0-489f-bcfb-8e7ed95c2e52.jpgHistory of Robotics & Automation- Jean-Paul LaumondIn this interview, Jean Paul Laumond discusses his movement from mathematics to robotics and his career contributions to the field, especially in regards to motion planning and anthropomorphic motion. Describing his involvement at CNRS and in other robotics projects, such as HILARE, he comments on the distinction in perception between the robotics approach and a mathematics one. Full interview available on IEEE Robotics And Automation History Site- https://www.ieee-ras.org/roboticshistory/https://peertube.laas.fr/static/streaming-playlists/hls/49eec67f-e523-4ff9-8b70-e9a76b0993dc/32e08ea1-d7a2-47de-8665-b36cac7cfe41-master.m3u8https://peertube.laas.fr/videos/embed/a8vJgSKZSNXpsgWX9AsLPo1180132023-05-30T16:44:55.191ZYESArchives Robotique NOhttps://peertube.laas.fr/w/kgnTqZRJ9G65DYzcFV3AZYhttps://peertube.laas.fr/lazy-static/thumbnails/4dfd339d-76ee-4a07-8c26-793aade45800.jpgRobotique : agir par le mouvement - Jean-Paul LaumondDirecteur de recherche au CNRS, Laboratoire d'analyse et d'architecture des systèmes (LAAS-CNRS), Toulouse Inter-section des applications des scienceshttps://peertube.laas.fr/static/streaming-playlists/hls/9c03477e-74ef-4390-ac41-b442d253112a/881ba41b-0b56-4850-bf74-0df0937a5578-master.m3u8https://peertube.laas.fr/videos/embed/kgnTqZRJ9G65DYzcFV3AZY509062023-05-30T16:53:34.563ZsciencesfrancetechnologieactualitéacadémieYESArchives Robotique NOhttps://peertube.laas.fr/w/xxHah14ymuSL5bjd1YnWethttps://peertube.laas.fr/lazy-static/thumbnails/6fb46175-c90b-445c-ad25-e263d739d29e.jpgsteo-640x480-15fpssteo-640x480-15fpshttps://peertube.laas.fr/static/streaming-playlists/hls/ff78b895-e3fc-43f0-becf-8c45ed10e36d/7e6488bb-254c-429a-a866-290b708adc38-master.m3u8https://peertube.laas.fr/videos/embed/xxHah14ymuSL5bjd1YnWet78042023-05-30T16:53:36.703ZYESArchives Robotique NOhttps://peertube.laas.fr/w/bbSfNo83h5DvJjcEEuENVQhttps://peertube.laas.fr/lazy-static/thumbnails/5118d35f-fdad-4cce-8f6a-1b0d2affee60.jpgbin-picking-tlessbin-picking-tlesshttps://peertube.laas.fr/static/streaming-playlists/hls/527fcb8e-bf43-4ee9-a497-bbb95d8d611a/3fc83951-bc29-4f5d-a861-3dec29e4e654-master.m3u8https://peertube.laas.fr/videos/embed/bbSfNo83h5DvJjcEEuENVQ116082023-06-29T15:34:57.279ZYESMain florent channelNOhttps://peertube.laas.fr/w/qVj3yMhLQ8BHG2qaS2DvLRhttps://peertube.laas.fr/lazy-static/thumbnails/b0ba1529-d869-4d63-b17a-4f418936bb56.jpgRobin Deits: Momentum and Manipulation with Atlas (talk at JNRH 2023, Bordeaux, France)This talk was given during the JNRH (https://jnrh2023.sciencesconf.org/), in July 2023, in Bordeaux, France, at the Robocup. Robin Deits is Principal Software Engineer in the humanoid team of Boston Dynamics, working with Atlas. Title of the talk: Momentum and Manipulation with Atlas Abstract: We have spent the last few years building a model-predictive controller for Atlas that can walk, run, jump, dance, and backflip. More recently, we have extended that controller to allow Atlas to lift, carry, and even throw heavy objects by integrating them directly into our MPC. In this talk I will discuss how we have built a model-predictive controller for manipulation which also manages to be better at walking, jumping, dancing, and flipping than any of our previous controllers. I will also discuss how Atlas perceives the world around it and how we integrate perception and high-level decision making into the robot's behaviors. https://peertube.laas.fr/static/streaming-playlists/hls/c9ccde28-2334-4a6a-a91d-0136bc550695/bed10b25-c0e8-47b0-bcde-3777843e7d36-master.m3u8https://peertube.laas.fr/videos/embed/qVj3yMhLQ8BHG2qaS2DvLR243551432023-07-11T18:54:02.650ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/5dU9kZvHeymewidRDRTJeyhttps://peertube.laas.fr/lazy-static/thumbnails/6ad03256-32f6-4cb8-8179-72b783c8b17e.jpgTrajectory on Digit legTrajectory on Digit leghttps://peertube.laas.fr/static/streaming-playlists/hls/22319d5b-eddf-4b54-9a1e-bf845a578262/0641d984-8b9c-477d-8844-c7d807bce72c-master.m3u8https://peertube.laas.fr/videos/embed/5dU9kZvHeymewidRDRTJey8082023-07-13T06:42:46.081ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/fpayYc3ZjzdPQsNHDx7ziohttps://peertube.laas.fr/lazy-static/thumbnails/3c97a8ff-3ed5-4e94-b54c-426da51c2360.jpgTrajectory on the Disney Bipedal Robot legTrajectory on the Disney Bipedal Robot leghttps://peertube.laas.fr/static/streaming-playlists/hls/749bf1d8-0c62-4d2f-b56e-5e8d03b4d0d4/60286d81-d3b9-4e93-abc0-6e8b2c40e0ec-master.m3u8https://peertube.laas.fr/videos/embed/fpayYc3ZjzdPQsNHDx7zio8092023-07-13T06:42:27.438ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/pGyKfnPeVZtAxQxmZiFDXyhttps://peertube.laas.fr/lazy-static/thumbnails/9826b1e1-d4fd-493c-af0a-f4d3b46b2867.jpgTrajectory on Kangaroo legTrajectory on Kangaroo leghttps://peertube.laas.fr/static/streaming-playlists/hls/bfec1ec5-c68e-449e-b21c-7defa1f68612/f282dfba-fee5-4f4e-a3eb-6bac2c02d004-master.m3u8https://peertube.laas.fr/videos/embed/pGyKfnPeVZtAxQxmZiFDXy8092023-07-13T06:42:09.080ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/nCcb1ae1mG4AiWAeM1dED6https://peertube.laas.fr/lazy-static/thumbnails/557dd1ab-bcf2-429d-a961-80805a8eaab4.jpgTrajectory on Talos legTrajectory on Talos leghttps://peertube.laas.fr/static/streaming-playlists/hls/af1d92a6-8791-445d-b20a-75b1bb1c88ff/4fc201c9-a72c-48f1-8149-82233801dd96-master.m3u8https://peertube.laas.fr/videos/embed/nCcb1ae1mG4AiWAeM1dED68062023-07-13T06:41:54.787ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/w652e7piifwSim6ofNEUPAhttps://peertube.laas.fr/lazy-static/thumbnails/c5ee2c10-0312-4af3-a7d8-2efaa5ac5afc.jpgTrajectory on WL16 legTrajectory on WL16 leghttps://peertube.laas.fr/static/streaming-playlists/hls/f3a75b54-e98f-475e-8cc0-6eda070623a8/be4342ec-d1e4-4b4e-acee-7233d4ee9a70-master.m3u8https://peertube.laas.fr/videos/embed/w652e7piifwSim6ofNEUPA8062023-07-13T06:41:37.978ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/r6ZZvFgaf7EegwNVWdkWUdhttps://peertube.laas.fr/lazy-static/thumbnails/055cd380-09cf-4b17-a20d-1f44531fb7b5.jpgDivergent belief, HRI, LAAS-CNRS with PR2 robotWe try here to build an environment for the robot using spark. This software uses Kinect as input to track human, pr2 ros nodes to get robot posture and position and viman to get object recogniton and position. It can happen that the robot and the human have divergent belief on an object position.https://peertube.laas.fr/static/streaming-playlists/hls/cb4aec86-beca-43bf-9468-ce301d728524/279416c7-04b6-4777-8ed5-159fb353ae7b-master.m3u8https://peertube.laas.fr/videos/embed/r6ZZvFgaf7EegwNVWdkWUd104052023-08-04T15:25:58.524Zpr2researchrobotlaascnrsYESArchives Robotique NOhttps://peertube.laas.fr/w/oKscgvR2w8QNpnshXogYsNhttps://peertube.laas.fr/lazy-static/thumbnails/319cb22a-3870-4cf6-a5dd-fc082fe44a5a.jpg1: Geometry1: Geometryhttps://peertube.laas.fr/static/streaming-playlists/hls/b83a2ce8-5a6a-4f24-a074-ca29c525bb0a/276b6fdf-5941-4bf6-b4d8-9e69901e2fc9-master.m3u8https://peertube.laas.fr/videos/embed/oKscgvR2w8QNpnshXogYsN25060222023-08-22T10:27:08.509ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/ncxzCyoagVNy9oo2S3pvrghttps://peertube.laas.fr/lazy-static/thumbnails/7fec8e82-97a4-434e-8be3-58cfe4034eb2.jpg2: Quaternions, SE(3)2: Quaternions, SE(3)https://peertube.laas.fr/static/streaming-playlists/hls/abac8e1a-994a-4fa8-b0e0-0e513c4de305/46910d81-153a-4a31-86fe-9549c30d48a7-master.m3u8https://peertube.laas.fr/videos/embed/ncxzCyoagVNy9oo2S3pvrg2529092023-08-22T10:42:19.084ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/1tZbfXXkd3eDHHfMuWTEYahttps://peertube.laas.fr/lazy-static/thumbnails/7f485678-828f-4e44-a99a-91fd589305b6.jpg3: kinematic tree, joint map, forward geometry3: kinematic tree, joint map, forward geometryhttps://peertube.laas.fr/static/streaming-playlists/hls/03e8517b-0492-4400-909d-6f313caa3029/fe844c69-dd2f-4fe5-bfd7-684406396082-master.m3u8https://peertube.laas.fr/videos/embed/1tZbfXXkd3eDHHfMuWTEYa2649082023-08-22T10:59:31.639ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/mymA955C8fKgN8cuvzXihYhttps://peertube.laas.fr/lazy-static/thumbnails/16759508-75d5-40ac-9a93-ff1f7198b908.jpg4: inverse geometry, gradient descent, newton descent, levenberg-marquardt4: inverse geometry, gradient descent, newton descent, levenberg-marquardthttps://peertube.laas.fr/static/streaming-playlists/hls/a67b4313-ad5e-4375-b1cb-b51b13976d84/f1b0cd11-3c6e-4d3c-847a-d1458ff8bfbe-master.m3u8https://peertube.laas.fr/videos/embed/mymA955C8fKgN8cuvzXihY30260102023-08-22T11:17:35.215ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/3eLo4SHzkmzUgSGHq9sycwhttps://peertube.laas.fr/lazy-static/thumbnails/68d22c30-f96f-4dbc-8adf-8140bd8b9e4b.jpg5: trust region, quasi-newton, levenberg-marquardt5: trust region, quasi-newton, levenberg-marquardthttps://peertube.laas.fr/static/streaming-playlists/hls/121e4bf8-8ff4-4872-9f37-33dc738d32ec/68746469-177f-411b-bd47-7f8c1ee0fa00-master.m3u8https://peertube.laas.fr/videos/embed/3eLo4SHzkmzUgSGHq9sycw2734062023-08-22T11:36:21.211ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/jkdxEdZZB9drV14PSGvKEMhttps://peertube.laas.fr/lazy-static/thumbnails/a2974a2c-9136-4e5b-a10e-b3c1bc849230.jpg6: optimization in Lie groups6: optimization in Lie groupshttps://peertube.laas.fr/static/streaming-playlists/hls/94735bf2-06c0-4fcc-8893-92e641b9635d/3fbf94df-9ba8-4591-99d8-073d9806bec7-master.m3u8https://peertube.laas.fr/videos/embed/jkdxEdZZB9drV14PSGvKEM32790132023-08-22T11:54:48.497ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/8ULRd7q2TKvg5J8UGJRAgehttps://peertube.laas.fr/lazy-static/thumbnails/124f5934-2740-4932-b4e2-855f8879de67.jpg7: velocity in SE(3), adjoint map and group action, velocity vector field7: velocity in SE(3), adjoint map and group action, velocity vector fieldhttps://peertube.laas.fr/static/streaming-playlists/hls/400e4915-937e-473c-a27a-0ca82c8a1e03/4aaae130-bce3-413b-b1bd-b2b83b98fc58-master.m3u8https://peertube.laas.fr/videos/embed/8ULRd7q2TKvg5J8UGJRAge26720102023-08-28T14:59:25.090ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/qJn7EntFXPfuhQSya8sfJohttps://peertube.laas.fr/lazy-static/thumbnails/b7000a09-bba5-44ae-af4f-a29600dfefc5.jpg8: adjoint map finalization8: adjoint map finalizationhttps://peertube.laas.fr/static/streaming-playlists/hls/c8459423-ca56-42b6-8eba-666a78bb5cb2/927c4054-1f2d-40fb-a3fa-5c3f14897775-master.m3u8https://peertube.laas.fr/videos/embed/qJn7EntFXPfuhQSya8sfJo2733072023-08-28T15:13:00.236ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/rffJEQq3WbX3M6LWNhwpFShttps://peertube.laas.fr/lazy-static/thumbnails/f38543b4-9656-404a-a4bf-c2dfea099771.jpg9: forward kinematics of the robot, jacobian9: forward kinematics of the robot, jacobianhttps://peertube.laas.fr/static/streaming-playlists/hls/cc71f5e1-221a-483c-b447-94a77170b234/e0f49f9c-2584-4b35-8481-5f4dc86c5101-master.m3u8https://peertube.laas.fr/videos/embed/rffJEQq3WbX3M6LWNhwpFS27430172023-08-28T15:28:57.939ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/kMh6ueGnrVqAtmxVQYNi2Thttps://peertube.laas.fr/lazy-static/thumbnails/71ae3fc8-1ab7-49ca-83ac-5ed03f960834.jpg10: inverse kinematics, pseudo inverse, linear least-square minimization10: inverse kinematics, pseudo inverse, linear least-square minimizationhttps://peertube.laas.fr/static/streaming-playlists/hls/a03005d8-d3c7-498c-bb34-a9f419bc7741/d3d17b57-5937-4bff-88c6-2e6852146c9d-master.m3u8https://peertube.laas.fr/videos/embed/kMh6ueGnrVqAtmxVQYNi2T2886092023-08-28T15:47:54.422ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/72h5mB7vb9Tqt5rbtBeCvkhttps://peertube.laas.fr/lazy-static/thumbnails/8554eae5-f796-4083-b262-5d821a1e556e.jpg11: inverse kinematics and inverse geometry11: inverse kinematics and inverse geometryhttps://peertube.laas.fr/static/streaming-playlists/hls/30c47b7b-b926-4d10-915a-460c78a0c3cd/6c8b50ee-dbdf-4ebd-9de5-d91194684b7c-master.m3u8https://peertube.laas.fr/videos/embed/72h5mB7vb9Tqt5rbtBeCvk2853052023-08-28T16:08:43.875ZYESRobotics LecturesNOhttps://peertube.laas.fr/w/juX3ozSUDUs2qppr3qycXFhttps://peertube.laas.fr/lazy-static/thumbnails/6706e43e-64e6-4454-ab23-ee72d04d1df0.jpgPhD Ewen DantecPhD Ewen Dantechttps://peertube.laas.fr/static/streaming-playlists/hls/95cf3de5-6ff6-4e8a-9ce5-0e136fb38fa9/b3f74e7c-497b-4719-b507-e44e4f0c5677-master.m3u8https://peertube.laas.fr/videos/embed/juX3ozSUDUs2qppr3qycXF5998082023-08-31T13:51:09.801ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/3si8jf3e9hspdegKaPxbzkhttps://peertube.laas.fr/lazy-static/thumbnails/000e739d-7f13-456d-b572-f98b578105dd.jpgFête de la Science 2023 - Annonce - Christian BergaudFête de la Science 2023 - Annonce - Christian Bergaudhttps://peertube.laas.fr/static/streaming-playlists/hls/13de2b70-4307-4e3a-ae64-bcf7bb97d99d/071780b5-9f8f-46fc-bff9-7416860635a6-master.m3u8https://peertube.laas.fr/videos/embed/3si8jf3e9hspdegKaPxbzk215062023-10-06T14:50:43.241ZYESGTEthiqueNOhttps://peertube.laas.fr/w/5ytSmLNePzrn2mhFryHHdchttps://peertube.laas.fr/lazy-static/thumbnails/3ce8d098-6046-42d9-a86c-b5d6a36ed5ca.jpgConférence : Les implants dans le cerveau, entre mythe et réalité par Christian BergaudConférence : Les implants dans le cerveau, entre mythe et réalité par Christian Bergaudhttps://peertube.laas.fr/static/streaming-playlists/hls/24ed879a-1f02-40c5-a974-1f6e0052a24f/996b8336-5950-40ea-8543-20cb910e44f9-master.m3u8https://peertube.laas.fr/videos/embed/5ytSmLNePzrn2mhFryHHdc2190242023-10-11T15:39:44.583ZYESMain marido channelNOhttps://peertube.laas.fr/w/hSD3qZ6jWYzMT3SzretsCvhttps://peertube.laas.fr/lazy-static/thumbnails/e59478a0-d3fa-4c83-b785-2b441b0035cd.jpgConférence : chatGPT, entre fascination et inquiétude par Malik GhallabConférence : chatGPT, entre fascination et inquiétude par Malik Ghallabhttps://peertube.laas.fr/static/streaming-playlists/hls/88a43c25-89ac-4e6a-a84b-3622e7cdcdd5/1a236fe0-8b5b-4e73-8b6b-4147f9a4e82b-master.m3u8https://peertube.laas.fr/videos/embed/hSD3qZ6jWYzMT3SzretsCv2290332023-10-11T15:47:58.163ZYESMain marido channelNOhttps://peertube.laas.fr/w/hr9FJbACLDC88vMx2jGAwrhttps://peertube.laas.fr/lazy-static/thumbnails/9effae81-e456-42bf-a2c3-ecf7caaf7e7e.jpgQuadratrure Encoder Interface HardwareThe Quadrature Encoder Interface (QEI) module provides the interface to incremental encoders for obtaining mechanical position data. https://os.mbed.com/users/fblanc/code/qei_hw_motor/https://peertube.laas.fr/static/streaming-playlists/hls/85152a44-271e-4182-9e7d-c53376f455ed/47733183-2d1d-4ecb-8b68-98b6a663c22a-master.m3u8https://peertube.laas.fr/videos/embed/hr9FJbACLDC88vMx2jGAwr42072023-10-11T18:17:25.428ZYESMain fblanc channelNOhttps://peertube.laas.fr/w/bixFd7FCWc6cHUAjCWzQqLhttps://peertube.laas.fr/lazy-static/thumbnails/1999df7a-4c69-497b-bd39-a8ad64bc10a7.jpgFête de la science 2023 - teaser conférence 5G - Philippe OwezarskiFête de la science 2023 - teaser conférence 5G - Philippe Owezarskihttps://peertube.laas.fr/static/streaming-playlists/hls/536e8d3e-09a3-4b23-891e-e14730781ee4/7e3fd454-3b58-4abf-a807-b69526188fb3-master.m3u8https://peertube.laas.fr/videos/embed/bixFd7FCWc6cHUAjCWzQqL1810352023-10-13T08:57:10.318ZFête de la scienceSARARISCYESLAAS-CNRS MainNOhttps://peertube.laas.fr/w/9HoFdHzhHQNfMJrbJxu2F1https://peertube.laas.fr/lazy-static/thumbnails/ed0f1e77-ab52-4613-aacf-3f692bfd9e24.jpgComparative metrics of advanced serial/parallel biped design and characterization of the main con...Compagnon video of Comparative metrics of advanced serial/parallel biped design and characterization of the main contemporary architectures: https://hal.science/hal-04191553https://peertube.laas.fr/static/streaming-playlists/hls/4690941b-eb73-45fe-bdc6-381136d67c8a/02afec9f-42b6-4e33-8649-3e84340e94f1-master.m3u8https://peertube.laas.fr/videos/embed/9HoFdHzhHQNfMJrbJxu2F1910212023-10-27T12:36:25.009ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/aeb3SJPHsP18KKpkWNzgt5https://peertube.laas.fr/lazy-static/thumbnails/c2f01017-040f-41d9-94e8-7b76a23b5d5d.jpgLe LAAS-CNRSLe laboratoire d'analyse et d'architecture des systèmes du CNRS vous présente ses activités de recherche, ancrées dans les grands défis de demain dans les domaines de l'automatique, l'informatique, la robotique et les micro et nanoscienceshttps://peertube.laas.fr/static/streaming-playlists/hls/4ab91c37-079c-4e04-93d2-2356c3789046/6ea06030-08d7-4e87-9802-0d41f4fcf9d6-master.m3u8https://peertube.laas.fr/videos/embed/aeb3SJPHsP18KKpkWNzgt5175011292023-10-31T15:49:45.584ZYESLAAS-CNRS MainNOhttps://peertube.laas.fr/w/3cnPBzehYXYKrbZHz3t1CShttps://peertube.laas.fr/lazy-static/thumbnails/85e7bac8-da6d-4ea2-a645-fc9d62c7bbb2.jpgANF-ROS-2-Install-HumbleCette vidéo décrit comment installer ROS-2 Humble sur une machine Linux Ubuntu 22.04 LTS. Elle est un peu longue, car elle fait suite aux nombreuses questions que j'ai à chaque fois que je fais une formation. 0:00 Présentation 0:30 Pourquoi Humble ? 2:50 Les types d'installation 4:30 Les étapes importantes de la procédure d'installation 6:06 Définir le language utilisé: en_US.UTF-8 10:32 Définir les sources apt 14:44 Installation des paquets ROS-2 Humble 16:44 Changer les variables d'environnement 18:50 Vérification avec turtlesim ! https://peertube.laas.fr/static/streaming-playlists/hls/11c8e80a-71c7-4109-be59-2470328c3512/f67e60a4-c503-4343-92b8-0fa0f5df9402-master.m3u8https://peertube.laas.fr/videos/embed/3cnPBzehYXYKrbZHz3t1CS11690122023-11-06T06:12:58.316ZYESROS 2 - Tutoriels en FrançaisNOhttps://peertube.laas.fr/w/n4aBF3mA63RpsfBFBL6yrihttps://peertube.laas.fr/lazy-static/thumbnails/7e4d316f-d1b8-4619-abcf-722886aa4da9.jpgBin picking TLESS object with robot Franka EmikaPreliminary result with the robot Franka Emika for bin picking TLESS objects with Cosypose.https://peertube.laas.fr/static/streaming-playlists/hls/aa811193-83bc-48d3-8d19-cd57c18219e3/46052fb8-9ce8-4a27-b806-09b11b08b157-master.m3u8https://peertube.laas.fr/videos/embed/n4aBF3mA63RpsfBFBL6yri590232023-11-07T10:14:33.228ZYESMain dbaudu channelNOhttps://peertube.laas.fr/w/7W26AEi2xv7VkU7Abr5pGFhttps://peertube.laas.fr/lazy-static/thumbnails/f655b604-e23f-41bb-abce-2e50db51c13a.jpgTalos WB-MPC push recoveryby Ewen Dantechttps://peertube.laas.fr/static/streaming-playlists/hls/3821abd9-8d55-41a6-8cee-f8bc2b72c863/3cd9bde4-9183-4d70-83e3-ed78f2b9a8ba-master.m3u8https://peertube.laas.fr/videos/embed/7W26AEi2xv7VkU7Abr5pGF420122023-11-24T14:36:44.279ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/iHL9jRBDBCehAuQXnqZTTehttps://peertube.laas.fr/lazy-static/thumbnails/f6959ebb-3a5b-4b17-94be-6f3223444d3b.jpgPhd Gabriele FadiniPhd Gabriele Fadinihttps://peertube.laas.fr/static/streaming-playlists/hls/8f800e63-d004-46db-be1f-f8e5c582240f/6c915c93-9cd5-49f5-8fdb-dafe100b64b1-master.m3u8https://peertube.laas.fr/videos/embed/iHL9jRBDBCehAuQXnqZTTe61070182023-11-28T16:49:29.955ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/pVMyD5mMasxfk5245nVgyxhttps://peertube.laas.fr/lazy-static/thumbnails/c373b2d5-0f13-4f82-84aa-fe8df900f74a.jpgPhD Thibaud LasguignesPhD Thibaud Lasguigneshttps://peertube.laas.fr/static/streaming-playlists/hls/c1c4b022-ae5c-48d5-86f6-a748d0609ed3/965f9a89-e88f-4dd1-a10d-6c7b9f62d013-master.m3u8https://peertube.laas.fr/videos/embed/pVMyD5mMasxfk5245nVgyx76010122023-11-28T20:21:18.920ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/neiUCKo86T2jmKwX9w72Jwhttps://peertube.laas.fr/lazy-static/thumbnails/3a277dde-8e31-48fc-9f6b-b7f57459a7bf.jpgQui cherche cherche, Louise Travé-Massuyès - automaticienneSérie "Portraits de chercheurs" par Jacques Mitsch, avec le soutien de Science Animation Mars 2021https://peertube.laas.fr/static/streaming-playlists/hls/abeb9de2-eabf-401c-9a05-bb1a370b6e56/5d11a0a4-47d6-45bd-9bf9-bc8ea55b3e33-master.m3u8https://peertube.laas.fr/videos/embed/neiUCKo86T2jmKwX9w72Jw2100302023-12-19T13:54:52.451ZautomatiqueYESLAAS-CNRS ChannelNOhttps://peertube.laas.fr/w/5PCddEh8wCzgTkp9ruBRiphttps://peertube.laas.fr/lazy-static/thumbnails/041f47e3-c042-451f-bd7d-68d8a89e68b5.jpgQui cherche cherche, Juan Cortès - roboticienSérie "Portraits de chercheurs" par Jacques Mitsch, avec le soutien de Science Animation Juin 2016https://peertube.laas.fr/static/streaming-playlists/hls/270ad3d3-3d5b-4cfa-8fab-94f18cdc2e2d/b8866ab3-8469-4806-b40d-efa4fb3a6b9d-master.m3u8https://peertube.laas.fr/videos/embed/5PCddEh8wCzgTkp9ruBRip1910282023-12-19T14:01:32.577ZalgorithmiquerobotiqueYESLAAS-CNRS ChannelNOhttps://peertube.laas.fr/w/iQTnrz6xVM6sMRP4t3maSFhttps://peertube.laas.fr/lazy-static/thumbnails/3ebf00cb-c916-4f2a-95f2-4b4e31ded837.jpgQui cherche cherche, Sandra Devin - roboticienneSérie "Portraits de chercheurs" par Jacques Mitsch, avec le soutien de Science Animation Juin 2016https://peertube.laas.fr/static/streaming-playlists/hls/907eb742-db40-4cdb-a512-de262b0bb21f/23196b80-b0ce-4039-bc97-ccb3e87db618-master.m3u8https://peertube.laas.fr/videos/embed/iQTnrz6xVM6sMRP4t3maSF1270562023-12-19T15:51:05.745ZrobotiqueYESLAAS-CNRS ChannelNOhttps://peertube.laas.fr/w/aM8JZK7T4j9Jdw31d8oQFzhttps://peertube.laas.fr/lazy-static/thumbnails/6ef9b0eb-17dd-454a-a139-9c0cae58e273.jpgConférence "How not to destroy the world with AI" par Stuart RussellConférence "How not to destroy the world with AI" par Stuart Russell, professeur d'informatique Cycle « Penser les technosciences » 5 Novembre 2020 https://peertube.laas.fr/static/streaming-playlists/hls/4f2f7d03-ae0c-4bd5-ac61-8b95bbf21117/72b7b30b-9e79-4948-ab13-0025d343cfd2-master.m3u8https://peertube.laas.fr/videos/embed/aM8JZK7T4j9Jdw31d8oQFz54190642023-12-19T16:51:52.711ZaiYESLAAS-CNRS ChannelNOhttps://peertube.laas.fr/w/4fPGPFVe8W4fTi9BFvKKRThttps://peertube.laas.fr/lazy-static/thumbnails/74188e58-ce9c-41a3-bbf2-39c158f050cc.jpgLe LAAS-CNRSLe laboratoire d'analyse et d'architecture des systèmes du CNRS vous présente ses activités de recherche, ancrées dans les grands défis de demain dans les domaines de l'automatique, l'informatique, la robotique et les micro et nanosciences https://peertube.laas.fr/static/streaming-playlists/hls/1a5d3a2f-b5e9-491d-8583-1a45899c8901/a9f99f95-d8b8-4a63-8ff9-6e65456d890b-master.m3u8https://peertube.laas.fr/videos/embed/4fPGPFVe8W4fTi9BFvKKRT17501102023-12-19T18:09:42.993ZYESLAAS-CNRS ChannelNOhttps://peertube.laas.fr/w/cNYrfAq7TaX39eZnRiXGv2https://peertube.laas.fr/lazy-static/thumbnails/d9903d5a-226d-44c6-9f77-65f38681f7fb.jpgFête de la science 2023 - teaser conférence 5G - Philippe OwezarskiFête de la science 2023 - teaser conférence 5G - Philippe Owezarskihttps://peertube.laas.fr/static/streaming-playlists/hls/5fa384a9-abae-4300-a3c9-204433da7b3b/90dc07de-1a09-4e77-8dd8-50f57229af4b-master.m3u8https://peertube.laas.fr/videos/embed/cNYrfAq7TaX39eZnRiXGv21820722023-12-19T18:16:55.498ZCONFÉRENCEFête de la scienceYESLAAS-CNRS ChannelNOhttps://peertube.laas.fr/w/g3yX2SVDooWGhYvpUisNFthttps://peertube.laas.fr/lazy-static/thumbnails/3ad3d91f-e066-4289-a8f0-7b8bcae2cd65.jpgAgimus Winter School 2023 - Plenary : Task and Motion PlanningAgimus Winter School 2023 - Plenary : Task and Motion Planninghttps://peertube.laas.fr/static/streaming-playlists/hls/79d4df75-15f3-4517-b0e0-cb1b1d38b849/64cba459-74fb-4e2b-a6c7-882f069f2f99-master.m3u8https://peertube.laas.fr/videos/embed/g3yX2SVDooWGhYvpUisNFt3997092023-12-21T14:24:22.856ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/aycsiQWBk1oifJrze3uZzzhttps://peertube.laas.fr/lazy-static/thumbnails/844bd29e-9087-4b3e-b18a-e8a453e257b2.jpgAgimus Winter School 2023 - Plenary : ROS2Agimus Winter School 2023 - Plenary : ROS2https://peertube.laas.fr/static/streaming-playlists/hls/4d611b6a-df58-4958-b6a6-161b202c02ff/ebb0000f-1a9f-4448-bf0a-cced230161e5-master.m3u8https://peertube.laas.fr/videos/embed/aycsiQWBk1oifJrze3uZzz2575062023-12-21T14:56:45.875ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/uh5XLPeLoyNfKJo1hUnVa1https://peertube.laas.fr/lazy-static/thumbnails/ad9afc89-a6c2-478f-b27b-f452fb54dcfe.jpgAgimus Winter School 2023 - Keynote: Optimization and Learning for Reactive Robotic BehaviorsAgimus Winter School 2023 - Keynote: Optimization and Learning for Reactive Robotic Behaviorshttps://peertube.laas.fr/static/streaming-playlists/hls/e4fed72a-8a90-472d-ab3c-c5291d01b806/bef5f9ee-f717-4c13-88a6-de1cf104ab6a-master.m3u8https://peertube.laas.fr/videos/embed/uh5XLPeLoyNfKJo1hUnVa14057092023-12-21T16:48:21.927ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/cqw21UQZBV6ydJLYC8Twpnhttps://peertube.laas.fr/lazy-static/thumbnails/11a93cf9-877d-45b8-ba9f-992cc51e2040.jpgAgimus Winter School 2023 - Plenary : Collision DetectionAgimus Winter School 2023 - Plenary : Collision Detectionhttps://peertube.laas.fr/static/streaming-playlists/hls/5c80dfeb-9f5b-426e-a338-7b49f4bf316b/455dbc40-0820-4891-b6cc-874093d84ef2-master.m3u8https://peertube.laas.fr/videos/embed/cqw21UQZBV6ydJLYC8Twpn3501032023-12-21T17:26:49.425ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/tgX3s6QsbUNsL3DaYpMsdwhttps://peertube.laas.fr/lazy-static/thumbnails/6381d989-e373-466a-a612-f06858d4ed3d.jpgAgimus Winter School 2023 - Keynote: Optimization AlgorithmsAgimus Winter School 2023 - Keynote: Optimization Algorithmshttps://peertube.laas.fr/static/streaming-playlists/hls/dce0d244-681b-4652-9cd0-c807054ba7b6/ca88f4e2-53e0-420f-8e58-ce05f0985a6e-master.m3u8https://peertube.laas.fr/videos/embed/tgX3s6QsbUNsL3DaYpMsdw4133082023-12-21T18:04:04.900ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/1PbYuUeYWseMjC6j36EWSEhttps://peertube.laas.fr/lazy-static/thumbnails/f039ba4b-4f28-4e1c-865c-90fdbe32c242.jpgAgimus Winter School 2023 - Plenary : Constrained OptimizationAgimus Winter School 2023 - Plenary : Constrained Optimizationhttps://peertube.laas.fr/static/streaming-playlists/hls/0696b860-a3a2-484a-b772-31e82fc5b892/c319724a-37bc-4de9-96d5-94124a98628f-master.m3u8https://peertube.laas.fr/videos/embed/1PbYuUeYWseMjC6j36EWSE3247082023-12-21T18:40:05.973ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/76ffnp9ggpGoB1u2sgJozjhttps://peertube.laas.fr/lazy-static/thumbnails/fbc9ddbb-bd25-42ba-b1dd-bd45c82a6020.jpgAgimus Winter School 2023 - Plenary : Constrained Trajectory OptimizationAgimus Winter School 2023 - Plenary : Constrained Trajectory Optimizationhttps://peertube.laas.fr/static/streaming-playlists/hls/315254cf-8d3c-44c2-a8f8-f6ed99492ba4/b863b761-a765-4ae2-bec3-48794fe2f034-master.m3u8https://peertube.laas.fr/videos/embed/76ffnp9ggpGoB1u2sgJozj3486092023-12-21T19:09:36.413ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/1ojboUyttZbQyWnf5UoVNShttps://peertube.laas.fr/lazy-static/thumbnails/4d8a6c02-cec4-4b6f-bff3-69798b4ff1a6.jpgAgimus Winter School 2023 - Plenary: Robotics Under Planetary ConstraintsAgimus Winter School 2023 - Plenary: Robotics Under Planetary Constraintshttps://peertube.laas.fr/static/streaming-playlists/hls/031d90f8-00fa-424c-8471-0b9549ef0a42/05fd162a-aa8b-4a89-96b7-408d0358e392-master.m3u8https://peertube.laas.fr/videos/embed/1ojboUyttZbQyWnf5UoVNS3771052023-12-21T19:41:51.772ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/kZwmMC8Pht72iadnrfCtMfhttps://peertube.laas.fr/lazy-static/thumbnails/5bab3e3d-263b-479e-9c7b-f1211dd09360.jpgAgimus Winter School 2023 - Plenary: PerceptionAgimus Winter School 2023 - Plenary: Perceptionhttps://peertube.laas.fr/static/streaming-playlists/hls/a1e5bd0b-33f0-4ad7-9700-0eea325fb66c/d9e27c98-e37f-4df8-94ba-e3046b7555e5-master.m3u8https://peertube.laas.fr/videos/embed/kZwmMC8Pht72iadnrfCtMf5075062023-12-21T20:20:52.559ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/rsLA7kymGpCV13jBSLh1E3https://peertube.laas.fr/lazy-static/thumbnails/84fdcc7b-d762-49a2-aa40-ac36a3b3bf3f.jpgAgimus Winter School 2023 - Plenary: Contact DynamicsAgimus Winter School 2023 - Plenary: Contact Dynamicshttps://peertube.laas.fr/static/streaming-playlists/hls/ce31486c-9732-4a5c-b1de-a0e399f460de/f1df8399-9dc7-41d0-bace-6dc72436e6c1-master.m3u8https://peertube.laas.fr/videos/embed/rsLA7kymGpCV13jBSLh1E343000182023-12-21T21:05:47.650ZYESAgimus Winter School 2023NOhttps://peertube.laas.fr/w/8NwVkejbLHkSWBEy6dMCsWhttps://peertube.laas.fr/lazy-static/thumbnails/fbd21b58-2db4-4e4d-9318-be1e711c6ed4.jpgModel predictive control under hard collision avoidance constraintVideo for the following article : Model predictive control under hard collision avoidance constrainthttps://peertube.laas.fr/static/streaming-playlists/hls/3f2f3d26-3afd-4099-9949-56d3c0116712/900ad2a9-1a39-4c53-b7cb-1a3f728605ea-master.m3u8https://peertube.laas.fr/videos/embed/8NwVkejbLHkSWBEy6dMCsW730872024-01-29T15:34:51.830ZYESMain ahaffemaye channelNOhttps://peertube.laas.fr/w/t9fbs8BFH5NdcLqkpMp2pwhttps://peertube.laas.fr/lazy-static/thumbnails/3ed1e924-88e4-470f-aa88-3acce1c4283e.jpg04-USRL-Presentation-Jean-SCIARE04-USRL-Presentation-Jean-SCIAREhttps://peertube.laas.fr/static/streaming-playlists/hls/dbcd6ecd-c338-479f-8f72-a000d2d08600/7570c2d2-8681-44f0-aa30-d27507a4aa86-master.m3u8https://peertube.laas.fr/videos/embed/t9fbs8BFH5NdcLqkpMp2pw827042024-02-01T18:18:17.958ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/fb1oUrDWKuwWaXa58PCu8phttps://peertube.laas.fr/lazy-static/thumbnails/e8f7ffb9-3d8a-4fa2-8f67-391e423795b5.jpg02-wildfires-Melanie-ROCHOUX02-wildfires-Melanie-ROCHOUXhttps://peertube.laas.fr/static/streaming-playlists/hls/72c59f4f-67d6-4ee0-afff-acba11a43d0d/a6cf45d5-5703-4041-9b12-e2b2dd57d1ad-master.m3u8https://peertube.laas.fr/videos/embed/fb1oUrDWKuwWaXa58PCu8p2350062024-02-03T20:18:06.497ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/iQqTRv7yNBgBfWMtPA3pAKhttps://peertube.laas.fr/lazy-static/thumbnails/14b85d03-082e-4893-b1ab-3e9d7d201845.jpg03-cas-d'usage-GRTgaz-Elodie-ROUSSET-Michel-PINET03-cas-d'usage-GRTgaz-Elodie-ROUSSET-Michel-PINEThttps://peertube.laas.fr/static/streaming-playlists/hls/906e6650-a6d2-4e8d-8e7f-7505bc24562b/4f08b459-355e-4cab-b12d-5e540e21cd43-master.m3u8https://peertube.laas.fr/videos/embed/iQqTRv7yNBgBfWMtPA3pAK1727052024-02-03T21:38:26.805ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/92zhVuGzYQokHrLhBYFcGDhttps://peertube.laas.fr/lazy-static/thumbnails/6c018610-50ad-4376-a597-aa05e32996fc.jpg05-MICROMEGAS-BriceBarret05-MICROMEGAS-BriceBarrethttps://peertube.laas.fr/static/streaming-playlists/hls/41015ead-1614-41b4-8ee0-c6c31aa0b739/238d1aea-24be-43cf-b683-e8fb6c1dacd4-master.m3u8https://peertube.laas.fr/videos/embed/92zhVuGzYQokHrLhBYFcGD2154012024-02-03T22:24:57.931ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/m4vhWmNfJWBy4TgUo9WNDKhttps://peertube.laas.fr/lazy-static/thumbnails/6f306d7d-303d-4e6c-83f0-e125da868f14.jpg06-SIMAGAZ-Jean-Yves-FOUCHER06-SIMAGAZ-Jean-Yves-FOUCHERhttps://peertube.laas.fr/static/streaming-playlists/hls/a2740e6d-8ce9-448f-a973-5f43efe78935/512050f0-76a0-458c-b239-aa8d8bb83289-master.m3u8https://peertube.laas.fr/videos/embed/m4vhWmNfJWBy4TgUo9WNDK1956022024-02-03T23:16:08.989ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/p4aJ6NwNjHwbU5yevLqfA4https://peertube.laas.fr/lazy-static/thumbnails/61c64505-41c9-4eca-8cd6-9ba04ea63a90.jpg07-quantification-GES-lilian-JOLY07-quantification-GES-lilian-JOLYhttps://peertube.laas.fr/static/streaming-playlists/hls/bab36a0d-4fec-4bd4-a402-5cff9b7ffa8f/b3014c33-625a-4585-bf88-552cbfa06328-master.m3u8https://peertube.laas.fr/videos/embed/p4aJ6NwNjHwbU5yevLqfA41408042024-02-03T23:59:13.423ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/45EY5NzXDpeuhMmpqcoetdhttps://peertube.laas.fr/lazy-static/thumbnails/8560de5e-f6f0-49af-b883-e0dcfaedd920.jpg08-NEPHELAE-PANACHE-Gautier-HATTENBERGER08-NEPHELAE-PANACHE-Gautier-HATTENBERGERhttps://peertube.laas.fr/static/streaming-playlists/hls/18f267c1-49f6-4467-984d-b440ff191dde/75997983-b4da-4a7f-ac94-2ddf6305074c-master.m3u8https://peertube.laas.fr/videos/embed/45EY5NzXDpeuhMmpqcoetd1860022024-02-04T00:38:21.923ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/bfuuXVhYZo37GZziX2nPjxhttps://peertube.laas.fr/lazy-static/thumbnails/3f35b8c9-c9a9-480a-9938-bb88d04e4dd7.jpg09-DESHIR-Francois-GUERIN-Brice-BERTHELOT09-DESHIR-Francois-GUERIN-Brice-BERTHELOThttps://peertube.laas.fr/static/streaming-playlists/hls/53015cdd-0832-4a19-a2dc-fc3578aabb47/11335a35-4b2b-4928-abfe-45c55e6ecd50-master.m3u8https://peertube.laas.fr/videos/embed/bfuuXVhYZo37GZziX2nPjx1970022024-02-04T01:24:38.077ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/c3WUYEgzwiVRmBkAiZxzDxhttps://peertube.laas.fr/lazy-static/thumbnails/60321b6a-19b8-40ef-aaaf-f890dd386046.jpg10-drone-longue-endurance-Renaud-KIEFFER10-drone-longue-endurance-Renaud-KIEFFERhttps://peertube.laas.fr/static/streaming-playlists/hls/597ddab8-c3bf-4c4f-b2d9-da3b3f9aa02d/589afab2-3c11-420f-9919-b74619197815-master.m3u8https://peertube.laas.fr/videos/embed/c3WUYEgzwiVRmBkAiZxzDx1310042024-02-04T02:06:05.684ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/3rKpMLyzLdP8zuiGtsFLmbhttps://peertube.laas.fr/lazy-static/thumbnails/f82ace5c-df98-4f2d-bad5-06e95e00c4fd.jpg11-discussion11-discussionhttps://peertube.laas.fr/static/streaming-playlists/hls/13ca9fc0-6a85-4cd9-bb88-7833ccdb94da/2f5e40e3-2d10-4f49-b10b-5018c0517e60-master.m3u8https://peertube.laas.fr/videos/embed/3rKpMLyzLdP8zuiGtsFLmb516022024-02-04T02:30:34.296ZYESWorkshop Panache - décembre 2023NOhttps://peertube.laas.fr/w/oThj2wBLRZkFvLwyEJTPJThttps://peertube.laas.fr/lazy-static/thumbnails/cef3fc59-a470-48cf-8a84-05fc14028f74.jpgFirst steps of Pyrène inside the newly refurbished Gérard Bauzil RoomFirst steps of Pyrène inside the newly refurbished Gérard Bauzil Roomhttps://peertube.laas.fr/static/streaming-playlists/hls/b95208e0-9412-40ff-9265-0e73f25188ab/f188f382-edd1-4b53-99fa-0be0b907d4e5-master.m3u8https://peertube.laas.fr/videos/embed/oThj2wBLRZkFvLwyEJTPJT140172024-02-08T16:56:15.535ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/oGjpvExD8D4i9sEkJhrRbVhttps://peertube.laas.fr/lazy-static/thumbnails/4cfe5127-7ec1-477f-9715-7a95d138688e.jpgCellule Flexible d'AssemblageVideo réalisée par Solange d'HALLOY en 1986 dans le cadre du programme ARAhttps://peertube.laas.fr/static/streaming-playlists/hls/b7ca24df-4832-4f95-9344-57589261ad45/aa975c1a-9972-42f2-96d1-9b11e9c84bba-master.m3u8https://peertube.laas.fr/videos/embed/oGjpvExD8D4i9sEkJhrRbV5460102024-02-20T17:29:25.596ZYESArchives Robotique NOhttps://peertube.laas.fr/w/ktx5JAL5sGUKLMLYWqzim5https://peertube.laas.fr/lazy-static/thumbnails/178b42f3-de36-4631-8531-823fa39911e6.jpgCoordination multi-robotsFilm réalisé dans le cadre du projet Martha en 1997https://peertube.laas.fr/static/streaming-playlists/hls/9db5defe-0ef2-4307-b562-2a33e9e80958/7de7d92b-077d-4b72-916a-dcde32dfb0aa-master.m3u8https://peertube.laas.fr/videos/embed/ktx5JAL5sGUKLMLYWqzim52170142024-02-20T17:58:25.562ZYESArchives Robotique NOhttps://peertube.laas.fr/w/kt8TcFJC64vhS8VSsw17xLhttps://peertube.laas.fr/lazy-static/thumbnails/8fc7d12f-1251-4bcc-98c5-20675e849571.jpglama2008lama2008https://peertube.laas.fr/static/streaming-playlists/hls/9da79303-39fb-4e7f-8f87-4967f5bf282a/ca27d3c0-31e8-4a3a-8ba5-b4b2b644f02f-master.m3u8https://peertube.laas.fr/videos/embed/kt8TcFJC64vhS8VSsw17xL2470142024-02-29T17:18:28.132ZYESArchives Robotique NOhttps://peertube.laas.fr/w/rmojtBkcQDaHgLoDhJeekwhttps://peertube.laas.fr/lazy-static/thumbnails/171919aa-5f65-472c-ba69-0971ca78b402.jpgPyrene Climbing Stairs @ROBOCup2023Video provided by Francesco Ferrohttps://peertube.laas.fr/static/streaming-playlists/hls/cd4d18a0-4f62-4c04-92ca-8e10d11a5e28/3b280b75-364d-40c0-85d9-d5ed22a7f5ee-master.m3u8https://peertube.laas.fr/videos/embed/rmojtBkcQDaHgLoDhJeekw260172024-03-06T20:08:06.503ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/bgjZnkCgCgv2YxRwH2wTpehttps://peertube.laas.fr/lazy-static/thumbnails/5f49581d-0637-452c-9f4e-26f4d7f6146a.jpgSteen Jany: Integrating deep learning with physics and control theoryRecent technological progress is supported by the generalization of numerical tools for simulating, controlling, and observing physical systems. Yet, by focusing on more and more complex phenomena, our conventional tools are falling short of meeting the growing expectations of engineers, whether in terms of accuracy or computation time. Data-driven approaches, in particular neural networks, offer promising alternatives to address these new challenges. These models can capture complex, nonlinear relationships in physical systems, and shift the burden from manual derivation of tedious mathematical formulas towards large-scale data collection. However, these methods often sacrifice stability, robustness, precision, and more generally guarantees classically offered by traditional approaches. In this thesis, we propose combining the fields of physics, deep learning, and control theory to propose new hybrid methods, taking advantage of the expressivity of neural networks, while relying on inductive biases from physics. We describe theoretical tools (discussed in Part 1) related to the simulation of dynamical systems and connect them to neural network design. In a second time (Part 2), we leverage these insights to design control algorithms and simulation techniques addressing the resolution of complex problems related to partial differential equations. Finally, in Part 3, we focus on larger-scale simulations such as fluid dynamics and counterfactual reasoning. Our work has been presented at scientific conferences in the field of artificial intelligence and control theory. By bridging the gap between physics and machine learning, we believe that this paves the way toward a new generation of methods for the simulation and control of physical systems. About the speaker: Steeven Janny just completed his PhD at INSA Lyon within the LIRIS and LAGEPP research labs, specializing in the interdisciplinary realms of physics, control, and machine learning. He harbors a profound...https://peertube.laas.fr/static/streaming-playlists/hls/531f3edf-9e6f-4f9f-a423-ab2b4169e0cf/9e8e094c-73ed-46c3-8a73-a214aff00425-master.m3u8https://peertube.laas.fr/videos/embed/bgjZnkCgCgv2YxRwH2wTpe20170312024-03-11T17:45:48.396ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/hVQyuHAHC4Pr3hR2ZW7h7Chttps://peertube.laas.fr/lazy-static/thumbnails/84599bf0-a085-4ad6-a200-0a7dff109478.jpgcurrent_democurrent_demohttps://peertube.laas.fr/static/streaming-playlists/hls/8916908f-c623-4feb-83bd-b806ec513b70/aaa3fb6d-9590-4143-ab63-eb88e99d7130-master.m3u8https://peertube.laas.fr/videos/embed/hVQyuHAHC4Pr3hR2ZW7h7C16062024-04-04T16:10:54.321ZYESMain tmartinezf channelNOhttps://peertube.laas.fr/w/dctBj1U5C1N5kVeP22GKJihttps://peertube.laas.fr/lazy-static/thumbnails/dba81c63-4a7c-4679-bfe4-3c43168a03b9.jpgStep Toward Deploying the Torque-Controlled Robot TALOS on Industrial Operations.This paper tackles the use of torque controlled humanoid robot TALOS in the context of industrial manufacturing. It demonstrates that it is possible to use Whole Body Model Predictive Control (WBMPC) to reliably insert a tool in the holes of an aircraft structure with an accuracy of few millimeters. This result is based on the use of Crocoddyl, an optimal control library that exploits differential dynamic programming (DDP) to achieve high numerical efficiency. The focus of this article is put on the procedure that was undertaken to shape the cost function of the optimal controller. Our approach has first been validate in a low performance setting on the humanoid robot TALOS. Then, a strategy to improve the performances by reinjecting information about the posture of the robot from previous experiments is showed in simulation.https://peertube.laas.fr/static/streaming-playlists/hls/62c7dc23-b1cf-48b1-979c-6c99487c88d1/75712690-a541-4e31-a702-9cd8507df044-master.m3u8https://peertube.laas.fr/videos/embed/dctBj1U5C1N5kVeP22GKJi52082024-05-06T20:02:40.751ZYESMain ostasse channelNOhttps://peertube.laas.fr/w/3juBBk8We55jTmEPFTBSBYhttps://peertube.laas.fr/lazy-static/thumbnails/a37f6df7-a172-4847-bcca-48d85c947059.jpgIntroduction au packaging, avec CMakeIntroduction au packaging, avec CMakehttps://peertube.laas.fr/static/streaming-playlists/hls/12c74c95-549a-49e8-ab68-dfab848530f6/882289f3-4da9-4f99-a6e0-450ea876d687-master.m3u8https://peertube.laas.fr/videos/embed/3juBBk8We55jTmEPFTBSBY3495052024-05-17T09:33:41.261ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/1X6d6MNwJEj6fXt3jjMxwAhttps://peertube.laas.fr/lazy-static/thumbnails/56b02f44-2488-4a9e-bf67-23d7148dcbe3.jpgPython Packaging, for users and devsPython Packaging, for users and devshttps://peertube.laas.fr/static/streaming-playlists/hls/07b11e05-b62d-46fa-aa10-79763c4c36b2/f2916e3a-df6c-42ae-9cd8-7a987a0321da-master.m3u8https://peertube.laas.fr/videos/embed/1X6d6MNwJEj6fXt3jjMxwA45790212024-05-17T16:10:14.857ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/1oVRC3dqz72m62DCziqKBfhttps://peertube.laas.fr/lazy-static/thumbnails/4bed69d9-28c1-4950-b546-c07ef1e204f9.jpgRust: Bases & ExamplesRust: Bases & Exampleshttps://peertube.laas.fr/static/streaming-playlists/hls/03338d76-ef95-471d-8b05-d6993a5818f8/07e807cb-4141-4f45-aa01-260d0d6c365e-master.m3u8https://peertube.laas.fr/videos/embed/1oVRC3dqz72m62DCziqKBf58630122024-06-07T16:22:03.167ZYESMain gsaurel channelNOhttps://peertube.laas.fr/w/69urtmnYMXdXaGY8WHnjRhhttps://peertube.laas.fr/lazy-static/thumbnails/52c7c152-3321-4fa9-812f-bed25d8760a6.jpgPlateforme RobotsPlateforme Robotshttps://peertube.laas.fr/static/streaming-playlists/hls/29ad2b72-a612-4e00-9ae8-5014844a7a0a/9827701c-dd89-4e83-9dbe-b8252c8bcbd5-master.m3u8https://peertube.laas.fr/videos/embed/69urtmnYMXdXaGY8WHnjRh2080262024-07-05T15:57:04.819ZYESTech Days 2024NOhttps://peertube.laas.fr/w/3coUkUmYv1Rbvm4vu5FfvKhttps://peertube.laas.fr/lazy-static/thumbnails/4f5c6fc9-85a6-49e1-a18a-7693bdfc69a1.jpgInspection task by a cable-driven parallel robotMotion planning for an inspection task by a cable driven parallel robot. The motion is planned by the software platform HPP (https://humanoid-path-planner.github.io/hpp-doc). This work is the result of a collaboration with LIRMM and Tecnalia France.https://peertube.laas.fr/static/streaming-playlists/hls/11c992ac-0749-420c-87fe-062ee870574d/883faae6-ace7-4181-b194-3870a4ff7ca1-master.m3u8https://peertube.laas.fr/videos/embed/3coUkUmYv1Rbvm4vu5FfvK35052024-07-08T14:26:19.160ZYESMain florent channelNOhttps://peertube.laas.fr/w/q6yyixK7hfbSsBEtsSLUkqhttps://peertube.laas.fr/lazy-static/thumbnails/77134799-f12f-45dd-a88c-023e12704096.jpgManipulation of boxes by a cable-driven parallel robotThe motion displayed in this movie has been computed using the task and motion planning algorithms implemented in the software platform HPP (https://humanoid-path-planner.github.io/hpp-doc). This work is the result of a collaboration with LIRMM and Tecnalia France.https://peertube.laas.fr/static/streaming-playlists/hls/c3221c51-671e-4806-97b8-1fa56ae724b6/52a6f811-e674-48a3-b006-d48556ab8d95-master.m3u8https://peertube.laas.fr/videos/embed/q6yyixK7hfbSsBEtsSLUkq35062024-07-08T14:25:41.923ZYESMain florent channelNOhttps://peertube.laas.fr/w/nL8ezANfT8y6WEkQLcG52Nhttps://peertube.laas.fr/lazy-static/thumbnails/12479389-507b-405e-95eb-702fa028aa10.jpgCleaning robotMotion planning for a cleaning robot in 2D environment. This work is the result of a collaboration with BA Systèmes.https://peertube.laas.fr/static/streaming-playlists/hls/b039188e-c25a-42aa-b4e3-2d51400b6be8/17835e80-297d-4eb3-b4e5-06284788c142-master.m3u8https://peertube.laas.fr/videos/embed/nL8ezANfT8y6WEkQLcG52N340102024-07-08T14:33:33.924ZYESMain florent channelNOhttps://peertube.laas.fr/w/dg1PJZJUKiDZ7jCSRykv3thttps://peertube.laas.fr/lazy-static/thumbnails/f69d34cf-2768-45ea-b500-c7a76e308751.jpgtiago-deburringTask sequencing for a mobile manipulator performing deburring by the Generalized Traveling Salesman Problem.https://peertube.laas.fr/static/streaming-playlists/hls/634653e6-b7c4-40bd-920f-daa111ffd0bb/75be4ecf-46b3-4929-815b-41d00c58f49c-master.m3u8https://peertube.laas.fr/videos/embed/dg1PJZJUKiDZ7jCSRykv3t920142024-07-10T11:22:58.710ZYESMain florent channelNOhttps://peertube.laas.fr/w/ua6c6i7oHFkmNKPiFZKu4Xhttps://peertube.laas.fr/lazy-static/thumbnails/74b1f75a-a5e4-4577-87bb-4b2c4cedc557.jpgFDS2023_LAASCNRS_Teaser4K_©DufonDrone&ProdRetour en images sur la journée portes ouvertes du LAAS-CNRS à l'occasion de la Fête de la science 2023https://peertube.laas.fr/static/streaming-playlists/hls/e404c68e-ecb2-4a96-b908-6315045a503d/8fb4144d-6e52-4ad4-b7f0-419ef514ecc9-master.m3u8https://peertube.laas.fr/videos/embed/ua6c6i7oHFkmNKPiFZKu4X30092024-07-11T06:49:48.002ZYESLAAS-CNRS MainNOhttps://peertube.laas.fr/w/1Cn8fCgj5hWToRj2Cfo8NXhttps://peertube.laas.fr/lazy-static/thumbnails/e7c8c9e8-fa68-46a3-843e-47f379e5da0f.jpgFête de la science 2023Fête de la science 2023https://peertube.laas.fr/static/streaming-playlists/hls/0513cb63-7bd7-4986-8b80-bc9baaf9f3af/a953dcba-247d-49d0-9139-d2e95bab9349-master.m3u8https://peertube.laas.fr/videos/embed/1Cn8fCgj5hWToRj2Cfo8NX1190862024-07-11T07:35:20.059ZYESLAAS-CNRS ChannelNOhttps://peertube.laas.fr/w/n5XhfoDNTmna5w9mAmW32uhttps://peertube.laas.fr/lazy-static/thumbnails/3514cde3-0cc5-43dd-b912-37e8ec488780.jpgPrésentation de la plateforme de caractérisation du LAAS-CNRSPrésentation des quatre zones de la Plateforme de Caractérisation du LAAS-CNRS.https://peertube.laas.fr/static/streaming-playlists/hls/aac0f45c-7fa5-43df-b33d-7afabdcdc68e/bbb7ebe0-9c2a-43e5-b8e7-d02716c2ab31-master.m3u8https://peertube.laas.fr/videos/embed/n5XhfoDNTmna5w9mAmW32u2400132024-07-15T13:19:07.287ZYESMain bary channelNOhttps://peertube.laas.fr/w/mZqJgKnhCdj59p9gL9WGgUhttps://peertube.laas.fr/lazy-static/thumbnails/171f6f8d-bc10-445b-b7f4-942ad486c47d.jpgMultiple grasps of TLESS objects inside a boxMultiple grasps of TLESS objects inside a box using vision, pose estimator, HPP and panda controller.https://peertube.laas.fr/static/streaming-playlists/hls/a9fb6863-5b60-444e-bab8-5c5bb24f6e6a/c439cdbf-d306-4625-9618-b1ce22ce0c37-master.m3u8https://peertube.laas.fr/videos/embed/mZqJgKnhCdj59p9gL9WGgU1620102024-07-31T09:19:11.558ZYESMain dbaudu channelNOhttps://peertube.laas.fr/w/exTGkvx7NPdPccKbCsYodahttps://peertube.laas.fr/lazy-static/thumbnails/e52b6e65-7a50-4539-aa13-100ae7e74cbf.jpgnot_really_working_symmetriesnot_really_working_symmetrieshttps://peertube.laas.fr/static/streaming-playlists/hls/6dbab7c8-aafa-4f69-a864-e962162ef1b9/8bcc8dd5-3e80-4edb-8e0c-c9ec71ea03f4-master.m3u8https://peertube.laas.fr/videos/embed/exTGkvx7NPdPccKbCsYoda114032024-08-14T13:20:33.433ZYESMain kwojciecho channelNOhttps://peertube.laas.fr/w/gdcoWrw4pZvYTJAEnqopXZhttps://peertube.laas.fr/lazy-static/thumbnails/8b4fa3d0-4d3b-45e1-a2f5-b1d68b66a0e3.jpgROS2 Nav2 Behavior Tree "Navigate To Pose With Replanning and Recovery"Exemple of a ROS2 Nav2 BT translated in BT2Fiacre and a simulated trace execution. See https://docs.nav2.org/behavior_trees/overview/detailed_behavior_tree_walkthrough.html and also https://redmine.laas.fr/projects/bt2fiacre/pages/indexhttps://peertube.laas.fr/static/streaming-playlists/hls/7b2d0721-fa1a-40f7-9551-0bc291937c7b/3edfbe27-4cf9-49fd-8017-647d3e3ca4ed-master.m3u8https://peertube.laas.fr/videos/embed/gdcoWrw4pZvYTJAEnqopXZ1550302024-08-30T13:19:33.057ZROS2-Nav2 HippoFiacreBeahavior TreeYESBT2FiacreNOhttps://peertube.laas.fr/w/iZE3BGPsnnz9Dz8dUcEu2Zhttps://peertube.laas.fr/lazy-static/thumbnails/1f33c9cc-ec6b-452f-9ab9-6a279e8f15e7.jpgBT Fiacre HippoVideo of a drone (using GenoM3 components) eexecuting a Behavior Tree which has been translated to Fiacre and is run with Hippo. See: https://redmine.laas.fr/projects/bt2fiacre/pages/indexhttps://peertube.laas.fr/static/streaming-playlists/hls/91b832bf-6cf1-471f-b750-e57a301d7603/229b2b4d-6669-4780-b68b-906a25808080-master.m3u8https://peertube.laas.fr/videos/embed/iZE3BGPsnnz9Dz8dUcEu2Z430222024-08-30T14:47:52.451ZBehavior TreeHippoFiacreGazeboBT2FiacreYESBT2FiacreNOhttps://peertube.laas.fr/w/oQJ5WnLNDc6rE37ydG6faPhttps://peertube.laas.fr/lazy-static/thumbnails/5f54c953-f8f4-458a-be52-c0c8d6134e04.jpgdrone-bt2f-hippoScreencast from the drone2 example of this page: https://redmine.laas.fr/projects/bt2fiacre/pages/indexhttps://peertube.laas.fr/static/streaming-playlists/hls/b8f6aff6-f977-4863-af3e-584246c46bf9/7217caf4-05cc-4c07-9352-8ee2b2c23ce2-master.m3u8https://peertube.laas.fr/videos/embed/oQJ5WnLNDc6rE37ydG6faP139092024-08-30T14:50:58.299ZDroneHippoBT2FiacreYESMain felix channelNOhttps://peertube.laas.fr/w/bF9CdS249qWMSZwZw5SaAFhttps://peertube.laas.fr/lazy-static/thumbnails/1102c5c0-15a0-4b3d-aafa-75611e9b86db.jpgdrone3-bt2f-hippoDrone3 example from this page: https://redmine.laas.fr/projects/bt2fiacre/pages/index Six runs are shown in this video (with random errors generated by the simulation): - Localization failure while flying the mission (0:10) - Camera tracking failure, the flying continues (because one success is enough in the parallel), but the whole mission fails later, because of a localization failure again (1:12) - Camera track success, and the whole mission is a success (3:17) - Localization failure again…​ (5:40) - Localization failure again…​ (Sorry) (6:38) - Camera tracking failure, the flying mission finish, but the last Eval fails and so does the mission (7:00). https://peertube.laas.fr/static/streaming-playlists/hls/5672b56b-b956-441d-9c00-04dc8b2c872f/89f37ddc-691b-418d-ba20-4863b172e763-master.m3u8https://peertube.laas.fr/videos/embed/bF9CdS249qWMSZwZw5SaAF559052024-08-30T15:01:13.254ZYESMain felix channelNOhttps://peertube.laas.fr/w/6ttaHsYRhWrSeyFUYuk1tchttps://peertube.laas.fr/lazy-static/thumbnails/d1d17a61-1819-43cd-9f10-30507f55621d.jpg2024-09-05 12-32-452024-09-05 12-32-45https://peertube.laas.fr/static/streaming-playlists/hls/2c538485-1748-4dfa-bd2d-42cf2929e061/48811b7c-9fa4-4925-85f6-ae43d7bbe807-master.m3u8https://peertube.laas.fr/videos/embed/6ttaHsYRhWrSeyFUYuk1tc99052024-09-05T10:37:10.064ZYESMain kwojciecho channelNOhttps://peertube.laas.fr/w/tkmZHt4rbu1CYZkwwAJhifhttps://peertube.laas.fr/lazy-static/thumbnails/d2273d15-b908-4151-858f-f0f0d23501a4.jpgManta "Flappy-Blimp" robot at LAAS-CNRSWork of 8 young apprentice researchers (10-16 yo) on a sunny July afternoonhttps://peertube.laas.fr/static/streaming-playlists/hls/dd5ad06a-de09-46fa-b4b7-8547bab8a198/22412b88-7394-4fe8-84d7-ce675f229d94-master.m3u8https://peertube.laas.fr/videos/embed/tkmZHt4rbu1CYZkwwAJhif110102025-03-28T12:37:47.175ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/sWFV5kMUp5zUvKUyVbkXWRhttps://peertube.laas.fr/lazy-static/thumbnails/b6d06c28-8d6c-4d78-806a-c491a0dec2df.jpgThree-dimensionnal aspects of gaseous detonations: experimental observations and a model, and tra...Seminar by Vianney Monnier presented 16/09/2024: The presentation will sum up previous studies on fluid mechanics and gaseous detonation, introduce salient results from Vianney's work and will propose directions for research in mechanics and mechanical design to discuss at ROB.  We have analyzed the cellular patterns of a steady gaseous detonation using frontal and longitudinal and soot plates in tubes whose cross sections have the same area of 16 cm2 but different shapes, i.e., round and square. The reactive mixture is stoechiometric hydrogen-oxygen, diluted or not by a 40% volume of argon. The results show that, for large enough initial pressures p0, all front-view patterns are irregular and independent of the cross-section shapes. Therefore, the notion of regularity depends not only on the mixture but also on both p0 and the cross-sectional shape. They also show that the longitudinal records for the considered mixture show regular patterns independently of p0 and the cross-sectional shape. That raises questions about the ability of longitudinal recordings alone to characterize cell structure. They certainly include how the transverse waves interact with each other as well as the walls. We have developed a model to predict the mean cell width for a cell quantity on the detonation front, or equivalently, p0, sufficiently large. The ingredients are graph theory, geometric probabilities and the Zeldovich-Von Neuman-Döring model. The predictions agree well with measurements, at least within the experimental uncertainties, depending on the mixture and the scheme of chemical kinetics considered. We have also studied the influence of the shape of the tube cross-section on the transient phenomena resulting from the diffraction of a steady detonation through a single-hole orifice plate, depending on the blockage ratio, initial pressure and argon dilution of the mixture. The shape of the tube cross-section induces marked qualitative and quantitative differences, a...https://peertube.laas.fr/static/streaming-playlists/hls/da305e06-52ae-4815-a6c8-ff2d262e2be1/58b4408e-7caa-4f82-8443-d0782167ff59-master.m3u8https://peertube.laas.fr/videos/embed/sWFV5kMUp5zUvKUyVbkXWR22390102024-09-17T14:58:27.058ZYESSeminars in GepettoNOhttps://peertube.laas.fr/w/973MxtA6PjVi5ZJVsJL1bAhttps://peertube.laas.fr/lazy-static/thumbnails/d39116ae-f231-4f97-a585-aa4b8df9fd11.jpgFête de la Science 2024 - Annonce - Vincent RaimbaultFête de la Science 2024 - Annonce - Vincent Raimbaulthttps://peertube.laas.fr/static/streaming-playlists/hls/41a149d1-6e56-4160-8bbd-e40fddee6966/bbb98abd-6078-4193-bf2c-0e7dafe7b7d7-master.m3u8https://peertube.laas.fr/videos/embed/973MxtA6PjVi5ZJVsJL1bA1720372024-09-26T09:35:02.939ZYESGTEthiqueNOhttps://peertube.laas.fr/w/nDHiaAU1LTfxfYGs5sQW7Ahttps://peertube.laas.fr/lazy-static/thumbnails/0ea23fac-b410-40ab-b476-814467d1d0ee.jpgFête de la Science 2024 - Annonce - Peter WiechaFête de la Science 2024 - Annonce - Peter Wiechahttps://peertube.laas.fr/static/streaming-playlists/hls/af53e181-df1b-4b9d-b6d7-9c6e4e933f36/737448f3-9fb1-4270-afa7-2c1020e00e72-master.m3u8https://peertube.laas.fr/videos/embed/nDHiaAU1LTfxfYGs5sQW7A2090502024-09-26T13:09:14.556ZYESGTEthiqueNOhttps://peertube.laas.fr/w/aiHzvcPWhiRmfcFkAuMQSdhttps://peertube.laas.fr/lazy-static/thumbnails/225aa9da-f279-47f1-9a7b-ed56b0d16e05.jpgFête de la Science 2023 - Annonce - Malik GhallabFête de la Science 2023 - Annonce - Malik Ghallabhttps://peertube.laas.fr/static/streaming-playlists/hls/4b5b83e1-dd2a-44ce-9771-5432a7bc7768/a6e7fe0d-6dd0-427a-8807-865393d08404-master.m3u8https://peertube.laas.fr/videos/embed/aiHzvcPWhiRmfcFkAuMQSd229072024-09-26T13:23:25.540ZYESGTEthiqueNOhttps://peertube.laas.fr/w/e2ZadmG8LyEW1cAxUf5vYMhttps://peertube.laas.fr/lazy-static/thumbnails/d6854eb0-f6f6-4bec-bc04-4dc15a759089.jpgFête de la Science 2023 - Annonce - Philippe OwezarskiFête de la Science 2023 - Annonce - Philippe Owezarskihttps://peertube.laas.fr/static/streaming-playlists/hls/698dc590-c1df-44e0-9e2d-a0d7c9cdc7b1/b8f96388-fd29-4119-b0c4-27a5d16011af-master.m3u8https://peertube.laas.fr/videos/embed/e2ZadmG8LyEW1cAxUf5vYM181022024-09-26T14:44:49.945ZYESGTEthiqueNOhttps://peertube.laas.fr/w/p3G99FbwfZuSAX4CxW73W7https://peertube.laas.fr/lazy-static/thumbnails/61f1ebcd-c6e1-49fb-8fbc-8b657687a872.jpgFête de la Science 2024 - Annonce - Olivier StasseFête de la Science 2024 - Annonce - Olivier Stassehttps://peertube.laas.fr/static/streaming-playlists/hls/baa26a08-38dd-4970-93c2-67c9604166ba/aa372abb-74dc-4755-9280-84e48084a707-master.m3u8https://peertube.laas.fr/videos/embed/p3G99FbwfZuSAX4CxW73W71650492024-09-26T14:59:03.180ZYESGTEthiqueNOhttps://peertube.laas.fr/w/uXSFcyJzP371qdGbLzqMYfhttps://peertube.laas.fr/lazy-static/thumbnails/345c193c-c6b5-4177-990f-49d8c93cf65f.jpg01 - IntroductionIntroduction à la journée, présentation du réseau [²RM](https://2rm.cnrs.fr/) par François Marmoiton, animateur du réseau. https://peertube.laas.fr/static/streaming-playlists/hls/ea8d051a-50b6-4eff-a86e-565c66b324e2/efd0d2f4-6ee4-4991-8556-f0be2ba86fb0-master.m3u8https://peertube.laas.fr/videos/embed/uXSFcyJzP371qdGbLzqMYf3330122024-09-28T15:27:04.006Z2RMIntroductionYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/aYS1ZFNWEBQnfdcGUMZBEJhttps://peertube.laas.fr/lazy-static/thumbnails/a719dfa6-1901-43a3-bffe-c6c9c1e99b1c.jpg02 - Mesures physiologique pour la robotique collaborativePrésentation à la journée technique [Mesures Physiologiques et Études Utilisateurs](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy) du réseau de métier [²RM](https://2rm.cnrs.fr/) [Slides](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy?action=AttachFile&do=view&target=presentation_2RM_MRihet.pdf) Auteurs: Mathias Rihet (ISAE / CNRS-LAAS), Aurélie Clodic (CNRS-LAAS), Raphaëlle N. Roy (ISAE) https://peertube.laas.fr/static/streaming-playlists/hls/50d2b925-1e78-4a19-b611-1be4751ac16a/1d180eb8-cd78-469e-8948-1392a3a58946-master.m3u8https://peertube.laas.fr/videos/embed/aYS1ZFNWEBQnfdcGUMZBEJ16450122024-09-29T11:06:20.966Z2rmmesures physiologiquesRobotiqueYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/8PSWCbJBLKB69ugH3M6nyahttps://peertube.laas.fr/lazy-static/thumbnails/98d58d80-17eb-4a62-b8b0-1a2fb722005b.jpg03 - L'apport de la capture de mouvement pour l'étude de la co-représentation entre Humains et Ro...Présentation à la journée technique [Mesures Physiologiques et Études Utilisateurs](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy) du réseau de métier [²RM](https://2rm.cnrs.fr/) [Slides](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy?action=AttachFile&do=view&target=2RMBelhassein.pdf) Auteur: Kathleeen Belhassein (Institut PPrime) https://peertube.laas.fr/static/streaming-playlists/hls/3f5f5261-c0dc-4971-8dd0-bfe34611fad5/73790866-92a6-49f9-b219-f33f158e9aea-master.m3u8https://peertube.laas.fr/videos/embed/8PSWCbJBLKB69ugH3M6nya21410102024-09-29T13:32:49.195Zinteraction humain-robot2rmcapture de mouvementYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/uxLzhKPQxetHqRJDDJ1isYhttps://peertube.laas.fr/lazy-static/thumbnails/8eb7a617-68cc-4767-bfeb-60945f41c9bd.jpg04 - Commandes vocales spontanées et déplacement guidé vers une position 3D : première étape pour...Présentation à la journée technique [Mesures Physiologiques et Études Utilisateurs](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy) du réseau de métier [²RM](https://2rm.cnrs.fr/) [Slides](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy?action=AttachFile&do=view&target=HENRY_Allan_Presentation.pdf) Auteur : Allan Henry (Gipsa-lab)https://peertube.laas.fr/static/streaming-playlists/hls/e72f68b5-8b94-40a8-bcb6-5b41f984f780/d8f8e8fa-1e77-48cf-a3bf-77a535aaa4c3-master.m3u8https://peertube.laas.fr/videos/embed/uxLzhKPQxetHqRJDDJ1isY1382072024-09-29T14:07:04.778Zcommande vocale2rmrobotiquedroneYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/xeS6qMghY6cMhNAKF9h8gLhttps://peertube.laas.fr/lazy-static/thumbnails/1d3afd03-c7a0-4d08-82f9-222147e1dc2d.jpg05 - Travailler avec un robot collaboratif ou un exosquelette : évaluer l'impact sur la santé ph...Présentation à la journée technique [Mesures Physiologiques et Études Utilisateurs](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy) du réseau de métier [²RM](https://2rm.cnrs.fr/) [Slides](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy?action=AttachFile&do=view&target=Pr%C3%A9sentation_Lemonnier.pdf) Auteurs : Sophie Lemonnier, Kévin Bouillet, Elissa El Khalil, Pauline Meurice, Guillaume Mornieux - Université de Lorraine, Inriahttps://peertube.laas.fr/static/streaming-playlists/hls/fcfad6b7-140f-4bb7-894e-ea3c466991ae/f3df4b44-06db-4f09-a36c-8ec2bb5ee4f6-master.m3u8https://peertube.laas.fr/videos/embed/xeS6qMghY6cMhNAKF9h8gL22480122024-10-01T10:20:24.593Z2rmrobotiqueexosquelettesantéYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/23aq63F63UTwqybTrdQ93vhttps://peertube.laas.fr/lazy-static/thumbnails/86250247-39ed-4cb1-baf7-cd2642303344.jpg06 - Exploring User Preferences in Multimodal Human-Robot Interaction for Human-Centered Design o...Présentation à la journée technique [Mesures Physiologiques et Études Utilisateurs](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy) du réseau de métier [²RM](https://2rm.cnrs.fr/) [Slides](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy?action=AttachFile&do=view&target=Prez_Icam.pdf) Auteur: Simona D'Attanasio (ICAM) https://peertube.laas.fr/static/streaming-playlists/hls/08666db7-7460-431a-9e48-3688816cf251/722e2e9a-ec43-4b1e-b7ab-594c31ff49f6-master.m3u8https://peertube.laas.fr/videos/embed/23aq63F63UTwqybTrdQ93v2066052024-09-29T17:56:40.706ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/bTpGwMHWHwzJyRVBi3xLDnhttps://peertube.laas.fr/lazy-static/thumbnails/05dc12be-e3d8-419e-8d0f-1f9928daff31.jpg08 - Acceptabilité d'un robot à domicile pour les enfants sourds porteurs d'implants cochléaires ...Présentation à la journée technique [Mesures Physiologiques et Études Utilisateurs](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy) du réseau de métier [²RM](https://2rm.cnrs.fr/) [Slides](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy?action=AttachFile&do=view&target=Journ%C3%A9e+Robotique+et+Sciences+Cognitives+v2.pdf) Auteurs : Sabrina Stiti (Cerco / CLEE), Loïc Caroux (CLEE), Pascal Gaillard (CLEE), Pierre-Vincent Paubel (CLEE), Pascal Barone (Cerco), Olivier Deguine (CHU Toulouse) https://peertube.laas.fr/static/streaming-playlists/hls/5828ec7c-c648-4bee-a200-ada6b261a77f/86ef85ab-7f25-4894-9eaa-53c0adf26b17-master.m3u8https://peertube.laas.fr/videos/embed/bTpGwMHWHwzJyRVBi3xLDn20370122024-09-29T21:19:02.643Zrobotenfants sourdsimplants cochléaires2RMYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/2TTPEeghrUEXFr9JsLiqt2https://peertube.laas.fr/lazy-static/thumbnails/1c5b16d1-8317-4dd9-a662-f2ea3c887cc4.jpg09 - L’utilisation d’une navette autonome dans le cadre des recherches en psychologiePrésentation à la journée technique [Mesures Physiologiques et Études Utilisateurs](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy) du réseau de métier [²RM](https://2rm.cnrs.fr/) [Slides](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy?action=AttachFile&do=view&target=LMotak+LAPSCO+20240918+navettes.pdf) Auteurs: Océane Thevenet (Lapsco), Ladislav Motak (Lapsco), François Marmoiton (Institut Pascal)https://peertube.laas.fr/static/streaming-playlists/hls/0f5801d7-6314-41ac-85f9-536c206384a7/31ecedd3-2b29-492d-a852-be18fafda87f-master.m3u8https://peertube.laas.fr/videos/embed/2TTPEeghrUEXFr9JsLiqt22278082024-09-30T21:31:18.581ZNavette autonome2RMPsychologieYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/pxa4Lh6bSSFzAAFbEadA8yhttps://peertube.laas.fr/lazy-static/thumbnails/62a571b1-a0ff-4cd7-9b59-9f89b9e8775c.jpg07 Human-Autonomy Teaming for drone control and supervision - Methodoloy and use case definitionPrésentation à la journée technique [Mesures Physiologiques et Études Utilisateurs](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy) du réseau de métier [²RM](https://2rm.cnrs.fr/) [Slides](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy?action=AttachFile&do=view&target=Zieba_Human-Autonomy+Teaming+for+drone+control+and+supervision_no_videos.pdf) Auteur: Stéphane ZIEBA - Thales Grouphttps://peertube.laas.fr/static/streaming-playlists/hls/be9bd51d-b291-49d2-be7d-d031317b2fae/934c9b53-5167-477c-b3f8-cf80ca125c3e-master.m3u8https://peertube.laas.fr/videos/embed/pxa4Lh6bSSFzAAFbEadA8y1537082024-10-08T13:13:33.112ZYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/w5J29SxGNSkrE3Sa9DYtaghttps://peertube.laas.fr/lazy-static/thumbnails/282c59fe-02b6-40db-a016-5d3fbf182508.jpg10 - La réalité virtuelle pour étudier la sélection des informations visuelles dans un espace 3DPrésentation à la journée technique [Mesures Physiologiques et Études Utilisateurs](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy) du réseau de métier [²RM](https://2rm.cnrs.fr/) [Slides](https://wiki.2rm.cnrs.fr/JT_MesuresPhysioUserStudy?action=AttachFile&do=view&target=Pr%C3%A9sentation_VR_ND.pdf) Auteurs: Dylan Naceur (LAPSCO Université de Clermont Auvergne)https://peertube.laas.fr/static/streaming-playlists/hls/f39b07d2-1ece-4649-b03b-09e786f32d35/0a9fd534-f482-4497-8b4d-724b2a03d89d-master.m3u8https://peertube.laas.fr/videos/embed/w5J29SxGNSkrE3Sa9DYtag19770122024-10-01T06:17:39.753Z2RMRéalité virtuelleinteraction humain robotYESRéseau de Métier Robotique et MécatroniqueNOhttps://peertube.laas.fr/w/j5iiiyiK7QANSAjNUGcn15https://peertube.laas.fr/lazy-static/thumbnails/e80b44ad-734f-46ba-a8c3-be8331db30a1.jpgFête de la Science 2024 - Conférence - Vincent RaimbaultFête de la Science 2024 - Conférence - Vincent Raimbaulthttps://peertube.laas.fr/static/streaming-playlists/hls/925e21a5-62cd-40e4-8bfd-f7334aa09d30/29696cb6-276a-44bd-9bd7-b07bd7320399-master.m3u8https://peertube.laas.fr/videos/embed/j5iiiyiK7QANSAjNUGcn152088092024-10-08T14:16:31.311ZYESGTEthiqueNOhttps://peertube.laas.fr/w/iFYwpqi1hb7nezSrpVX6n5https://peertube.laas.fr/lazy-static/thumbnails/a59912ac-b907-4d94-86ae-a5d3de5cfc00.jpgFête de la Science 2024 - Conférence - Peter WiechaFête de la Science 2024 - Conférence - Peter Wiechahttps://peertube.laas.fr/static/streaming-playlists/hls/8f4032d2-b42d-477d-8069-fc1f0f0a2b02/d53cca93-794a-45fd-aa9b-99bd8e301764-master.m3u8https://peertube.laas.fr/videos/embed/iFYwpqi1hb7nezSrpVX6n515780142024-10-08T14:54:48.630ZYESGTEthiqueNOhttps://peertube.laas.fr/w/beMZQM4yTHmQP9oG9fAdAAhttps://peertube.laas.fr/lazy-static/thumbnails/a1b0fe3d-952e-4283-8b44-f0664dd5c3d3.jpgFête de la Science 2024 - Conférence - Olivier StasseFête de la Science 2024 - Conférence - Olivier Stassehttps://peertube.laas.fr/static/streaming-playlists/hls/52e86705-7d11-4848-abbc-b507fd53e1b6/86183d87-0a28-49fb-9461-4c0c3aa573ce-master.m3u8https://peertube.laas.fr/videos/embed/beMZQM4yTHmQP9oG9fAdAA17460222024-10-09T11:03:08.683ZYESGTEthiqueNOhttps://peertube.laas.fr/w/bRD7oEYgYL2VKz6D1QpKP8https://peertube.laas.fr/lazy-static/thumbnails/6ac22448-8eca-42db-a2ff-d16666b2ac3f.jpgmulti-model SWIKA (Sliding Windows Inverse Kinematics Algorithm) [Adjel, 2023]multi-model SWIKA (Sliding Windows Inverse Kinematics Algorithm) [Adjel, 2023]https://peertube.laas.fr/static/streaming-playlists/hls/57e9b388-1ddf-4e4d-ba91-536d55aee311/13b925ee-d91a-473b-8ea0-4bf88b02832f-master.m3u8https://peertube.laas.fr/videos/embed/bRD7oEYgYL2VKz6D1QpKP8170892024-10-22T13:50:21.423ZYESMain vbonnet channelNOhttps://peertube.laas.fr/w/gMYL69JAepoZb1cFbYEanFhttps://peertube.laas.fr/lazy-static/thumbnails/f19316bb-656b-4950-81de-449bf770477c.jpgPhD Wilson JalletPhD Wilson Jallethttps://peertube.laas.fr/static/streaming-playlists/hls/7fe4877c-0651-4df6-8d40-eee31b87801d/00ee9360-96ea-4315-9216-99d2156b35f9-master.m3u8https://peertube.laas.fr/videos/embed/gMYL69JAepoZb1cFbYEanF64830752024-11-19T17:03:31.258ZYESSoutenances de Thèse GepettoNOhttps://peertube.laas.fr/w/duwe4WXVmBcrBwzCtZBK2ahttps://peertube.laas.fr/lazy-static/thumbnails/cb047204-9f42-485c-b0be-c1d4e784ae61.jpgGeometric calibration of Talos robot by contacts with planesThis videos explains how we calibrated robot Pyrene by making plane contacts using admittance controlhttps://peertube.laas.fr/static/streaming-playlists/hls/65291dd2-47a2-4357-bb59-05f1f848acb7/8c140304-c476-4bcc-87fd-a9976e274543-master.m3u8https://peertube.laas.fr/videos/embed/duwe4WXVmBcrBwzCtZBK2a16801212024-12-20T12:12:29.163ZYESMain florent channelNOhttps://peertube.laas.fr/w/tTFDBNKp7oSQiQEimT3zXfhttps://peertube.laas.fr/lazy-static/thumbnails/884a5b25-eb7e-4cb1-9687-ee7674f5b483.jpgAutomatiqueStageSeconde2024AutomatiqueStageSeconde2024https://peertube.laas.fr/static/streaming-playlists/hls/e1de1c42-a90b-4917-a5d3-aa9e173f7068/b18eaf13-cbe4-43bc-b25e-949287718248-master.m3u8https://peertube.laas.fr/videos/embed/tTFDBNKp7oSQiQEimT3zXf1620182025-01-24T16:02:19.246ZYESMain lbaudoui channelNOhttps://peertube.laas.fr/w/hGJuytPEMUy6NWzbd8LQokhttps://peertube.laas.fr/lazy-static/thumbnails/5f37eaa6-5e5a-4e2c-912c-099585921d9c.jpgPLT - Bernard Stiegler - Penser éthiquement du point de vue du néguanthropocèneConférence Penser Les Technosciences (PLT) Résumé : A la fin du XVIIIème siècle, Kant élaborait les bases de la philosophie moderne en écrivant ce que l'on appelle “les trois critiques” de la raison, dans un cadre scientifique transformé par la physique newtonienne. Le monde numérique impose aujourd’hui une nouvelle critique qui doit appréhender les questions des limites de l'anthropocène, et de la puissance de l'homme qui se retourne contre l'homme. Sa finalité sera de sortir de l'Anthropocène pour entrer dans ce que l'on appellera le Néguanthropocène. Cette conférence tentera de montrer quels sont les enjeux de cette nouvelle critique, pourquoi elle requiert une recombinaison des enjeux épistémologiques et éthiques, ainsi que de nouvelles critiques de l'économie politique et du jugement.https://peertube.laas.fr/static/streaming-playlists/hls/874227ff-5b95-4082-b91a-e51fcd5da89f/a9a56d04-3582-4b38-823d-227b732e46a0-master.m3u8https://peertube.laas.fr/videos/embed/hGJuytPEMUy6NWzbd8LQok4320052025-01-28T15:53:04.840ZYESGTEthiqueNOhttps://peertube.laas.fr/w/9bzwC631y5YpX76DchQKSYhttps://peertube.laas.fr/lazy-static/thumbnails/b67afece-eea7-4325-8c7a-47ba0fcbab07.jpgPLT - Bernadette Bensaude-Vincent - Technosciences et conflits de valeurConférence Penser Les Technosciences (PLT) Résumé : La recherche technoscientifique se caractérise par un régime de recherche largement soumis aux normes et valeurs dominantes dans la société. Compétitivité, rentabilité, viennent brouiller les critères traditionnels de l’excellence, imposer toutes sortes de contraintes éthiques et bousculer le temps long de la recherche. Grande est la tentation de dénoncer une ‘contamination’ de la science par le marché pour « sauver la recherche ». On montrera que cette attitude repose sur l’illusion qu’a existé ou pourrait exister une science pure, libre et autonome. Ne serait-il pas plus pertinent d’aborder autrement les conflits de normes et de valeurs suscités par le régime actuel de recherche ? On explorera quelques pistes sur le cas précis des nanobiotechnologies. https://peertube.laas.fr/static/streaming-playlists/hls/42433596-4f2e-4225-a2cc-cb73c902dab8/c475d5b4-d511-4ba7-86ad-f23f90ff57ba-master.m3u8https://peertube.laas.fr/videos/embed/9bzwC631y5YpX76DchQKSY4086032025-01-28T17:36:13.890ZYESGTEthiqueNOhttps://peertube.laas.fr/w/rkvYs7i5QfmDPvsfh2qvJmhttps://peertube.laas.fr/lazy-static/thumbnails/345ca526-94e7-4c87-ac09-8e6f3300f1d0.jpgPLT - Marc Hunyadi - Peut-il y avoir une machine morale ?Conférence Penser Les Technosciences (PLT) Résumé : Je montrerai pourquoi ce qu’on appelle des « agents moraux explicites », c'est à dire des machines capables de faire des choix éthiques, ne sont ni agents, ni moraux. Sur un plan plus fondamental, je montrerai quelles conditions, exigées par la nature même du raisonnement moral, une machine devrait remplir pour être véritablement morale. La conception d’une hypothétique machine morale nécessiterait en particulier que sa programmation lui permettent d'avoir accès à ce que j’appelle la contrefactualité, qui est le « ce au nom de quoi » une action est entreprise.https://peertube.laas.fr/static/streaming-playlists/hls/cd2e11df-a5ee-43c5-99e9-8495e1bb40fc/c1d6235c-7d05-4b2e-b44b-f21af35b634c-master.m3u8https://peertube.laas.fr/videos/embed/rkvYs7i5QfmDPvsfh2qvJm3713042025-01-28T18:06:24.276ZYESGTEthiqueNOhttps://peertube.laas.fr/w/6FpnsHPAEGnrpEcjZ4oeUUhttps://peertube.laas.fr/lazy-static/thumbnails/f1a141ff-23cc-4443-8809-201a0df65938.jpgPLT - Edward A. Lee - The Coevolution of Humans and MachinesConférence Penser Les Technosciences (PLT) Résumé : Are humans defining technology, or is technology defining humans ? In this talk, Edward A. Lee considers the case that we are less in control of the trajectory of technology than we think. It shapes us as much as we shape it, and it may be more defensible to think of technology as the result of a Darwinian coevolution than the result of top-down intelligent design. Richard Dawkins famously said that a chicken is an egg's way of making another egg. Is a human a computer's way of making another computer ? To understand this question requires a deep dive into how evolution works, how humans are different from computers, and how the way technology develops resembles the emergence of a new life form on our planet.https://peertube.laas.fr/static/streaming-playlists/hls/2dfe1a44-c254-4c37-b2b7-da6beaec9a10/90ddd3b5-1f75-46f0-87cc-adba0a382888-master.m3u8https://peertube.laas.fr/videos/embed/6FpnsHPAEGnrpEcjZ4oeUU3799022025-01-28T18:56:06.033ZYESGTEthiqueNOhttps://peertube.laas.fr/w/eGBLQAbkLDBtNNtUcHjZnihttps://peertube.laas.fr/lazy-static/thumbnails/d911ff23-ecbd-4e10-a0b6-1ad3c6655a23.jpgPLT - Stuart Russell - How not to destroy the world with AIConférence Penser Les Technosciences (PLT) Résumé : I will briefly survey recent and expected developments in AI and their implications. Some are enormously positive, while others, such as the development of autonomous weapons and the replacement of humans in economic roles, may be negative. Beyond these, one must expect that AI capabilities will eventually exceed those of humans across a range of real-world-decision making scenarios. Should this be a cause for concern, as Elon Musk, Stephen Hawking, and others have suggested? And, if so, what can we do about it? While some in the mainstream AI community dismiss the issue, I will argue that the problem is real and that the technical aspects of it are solvable if we replace current definitions of AI with a version based on provable benefit to humans.https://peertube.laas.fr/static/streaming-playlists/hls/6ef2996c-a7ff-480b-88be-e908905b7c97/9e86cf90-f79e-420c-b5c9-c124fa5cebea-master.m3u8https://peertube.laas.fr/videos/embed/eGBLQAbkLDBtNNtUcHjZni5419092025-01-28T20:10:17.655ZYESGTEthiqueNOhttps://peertube.laas.fr/w/wSzETWfPrQZKgo4hC6ZWgNhttps://peertube.laas.fr/lazy-static/thumbnails/a71557b5-df44-416d-97d2-edb63f3ece42.jpgElliot Chane-Sane : Agile Legged Locomotion and Visual ImitationLegged robots, with their potential to navigate complex, unstructured environments, present exciting opportunities for diverse real-world applications. In recent years, training locomotion policies in physics simulators with reinforcement learning (RL), then directly transferring them to real robots, has emerged as a powerful approach for achieving robust and adaptive behaviors. However, key challenges remain, including learning agile yet safe locomotion policies, efficiently training vision-based policies, and achieving natural, animal-like motions. In the first part of this talk, I will present a simple yet effective method for integrating constraints into RL, streamlining reward engineering and enabling safe and efficient sim- to-real transfer. In the second part, I will focus on extending this approach to parkour from depth pixels through a sample-efficient visual RL algorithm. Finally, i! n the third part of the talk, I will present an approach to learn legged locomotion skills by watching thousands of wild animal videos from the internet, such as those featured in nature documentaries.https://peertube.laas.fr/static/streaming-playlists/hls/fa02193a-a2f4-4c91-aea7-df1290c19b64/6b4a804a-98d7-4d72-904b-8357041189ee-master.m3u8https://peertube.laas.fr/videos/embed/wSzETWfPrQZKgo4hC6ZWgN33490372025-02-10T19:37:20.931ZYESGepetto Scientific MeetingsNOhttps://peertube.laas.fr/w/g5CV8ZpCpfa55mYHryEN2Uhttps://peertube.laas.fr/lazy-static/thumbnails/09d29d79-d3b2-4179-8cc6-c527dd77cffe.jpgFirst steps of H1 in LAAS-CNRSFirst steps of H1 in LAAS-CNRShttps://peertube.laas.fr/static/streaming-playlists/hls/7a1ece2d-2cdd-495d-817d-402ecd69fdb6/e904c680-ba48-4c18-a983-1d2b5294d3b3-master.m3u8https://peertube.laas.fr/videos/embed/g5CV8ZpCpfa55mYHryEN2U470282025-02-21T11:27:12.829ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/fJzosSuhV7ehS2XfHySdiehttps://peertube.laas.fr/lazy-static/thumbnails/8ff592b8-780e-45c6-8d1c-6a70f5c80e63.jpgAliengo MinimalAliengo Minimalhttps://peertube.laas.fr/static/streaming-playlists/hls/7751c156-f83b-46c8-8dd3-fc1e3823ac07/0541e750-bec2-407a-9ad0-f1c944eefb1f-master.m3u8https://peertube.laas.fr/videos/embed/fJzosSuhV7ehS2XfHySdie6062025-02-24T08:33:10.197ZYESMain pncrestaz channelNOhttps://peertube.laas.fr/w/8qFTgNWLkJJZi47hKVEKiKhttps://peertube.laas.fr/lazy-static/thumbnails/e277fc19-ab64-465b-a4e9-2fb8ab8fb5d8.jpgOptimal_Motion_Prediction_for_Human_To_Robot_Handovers_1080pOptimal Motion Prediction for Human to Robot Handovers. Submitted to IEEE IROS 2025https://peertube.laas.fr/static/streaming-playlists/hls/3c226686-cc58-4878-9873-4622b0912531/639c41ad-1446-404b-943b-07a7b020266e-master.m3u8https://peertube.laas.fr/videos/embed/8qFTgNWLkJJZi47hKVEKiK1740342025-02-28T09:54:57.523ZYESMain msabbah channelNOhttps://peertube.laas.fr/w/4rN4nm6dmkF7uyWBMkRKCWhttps://peertube.laas.fr/lazy-static/thumbnails/a2c8cb35-3772-4d0b-81c9-32c46cb94a21.jpgOptimal Control of Walker with Parallel ActuationOptimal Control of Walker with Parallel Actuationhttps://peertube.laas.fr/static/streaming-playlists/hls/1be564ff-84e0-43cb-abda-b608da332e22/85a6bcfc-8c2f-4867-a247-9d8f69090e7d-master.m3u8https://peertube.laas.fr/videos/embed/4rN4nm6dmkF7uyWBMkRKCW1350322025-03-04T10:05:12.194ZYESMain ldematteis channelNOhttps://peertube.laas.fr/w/jCivgszL7etScwigms3umVhttps://peertube.laas.fr/lazy-static/thumbnails/90915118-a44c-4e65-a4f0-ebd1a5289df2.jpgControl of Humanoid Robots with Parallel Mechanisms using Kinematic Actuation ModelsInspired by the mechanical design of Cassie, several recently released humanoid robots are using actuator configuration in which the motor is displaced from the joint location to optimize the leg inertia. This in turn induces a non-linearity in the reduction ratio of the transmission which is often neglected when computing the robot motion (e.g. by trajectory optimization or reinforcement learning) and only accounted for at control time. This paper proposes an analytical method to efficiently handle this non-linearity. Using this actuation model, we demonstrate that we can leverage the dynamic abilities of the non-linear transmission while only modeling the inertia of the main serial chain of the leg, without approximating the motor capabilities nor the joint range. Based on analytical inverse kinematics, our method does not need any numerical routines dedicated to the closed-kinematics actuation, hence leading to very efficient computations. Our study focuses on two mechanisms widely used in recent humanoid robots; the four-bar knee linkage as well as a parallel 2 DoF ankle mechanism. We integrate these models inside optimization based (DDP) and learning (PPO) control approaches. A comparison of our model against a simplified model that completely neglects closed-chains is then shown in simulation. https://peertube.laas.fr/static/streaming-playlists/hls/96d60f27-119b-4b0b-a651-ef8a3cbf295d/f39dd8d1-6d61-4299-9341-e3df6f680766-master.m3u8https://peertube.laas.fr/videos/embed/jCivgszL7etScwigms3umV1280182025-03-10T13:51:11.668ZYESMain vlutz channelNOhttps://peertube.laas.fr/w/fR5SgK9gJMC7s7FcdANC9Lhttps://peertube.laas.fr/lazy-static/thumbnails/6ceabc58-ecd3-454b-8046-6a87c7bbc425.jpgPlateforme de caractérisationPrésentation des zones de caractérisation du laboratoirehttps://peertube.laas.fr/static/streaming-playlists/hls/783a629d-27fc-454d-82a1-483570e65e1c/0c6815b5-4522-4b42-a173-ecd782f38116-master.m3u8https://peertube.laas.fr/videos/embed/fR5SgK9gJMC7s7FcdANC9L2400342025-04-03T14:02:40.204ZYESLAAS-CNRS ChannelNOhttps://peertube.laas.fr/w/vDAsaTNgjtBVLykGb58QbVhttps://peertube.laas.fr/lazy-static/thumbnails/b73ff191-807e-4689-9122-70a39e395daa.jpgPerfect run, 2 recharges and found the target.This run illustrates a complete successful mission, with two battery charging episodes. The camera_track finds the target, returns success. As a result this halts the rest of the flying mission and the whole BT return success.https://peertube.laas.fr/static/streaming-playlists/hls/f018c59e-46a7-4db0-82ac-b2de8b42f251/bfcb2dcd-e7ae-4d28-877b-28972f21a0be-master.m3u8https://peertube.laas.fr/videos/embed/vDAsaTNgjtBVLykGb58QbV119082025-04-04T12:39:17.425ZYESBT2FiacreNOhttps://peertube.laas.fr/w/akeQQoMravspqbM94YgwmWhttps://peertube.laas.fr/lazy-static/thumbnails/29ea0cb0-d3f5-4b59-8787-be352c456cd8.jpgMission with a battery charge and then a localization failure while flying on the 3rd levelIn this particular mission, the drone surveys the area, goes once to the charging station in -1,-1 and then encounters a localization failure which leads to an emergency landing, and halting the rest of the mission (hence the purple color of the camera and goto).https://peertube.laas.fr/static/streaming-playlists/hls/4b91e8f4-fa24-4bec-bff6-793a9b96942e/f10275d4-b832-486e-8e3d-4e6df2ce6b23-master.m3u8https://peertube.laas.fr/videos/embed/akeQQoMravspqbM94YgwmW91042025-04-04T12:42:48.970ZYESBT2FiacreNOhttps://peertube.laas.fr/w/mFfzxftRB89Sy69ZNq7soHhttps://peertube.laas.fr/lazy-static/thumbnails/9cd85af1-d854-4e15-b370-a9a6875aef34.jpgwhole mission but nothingwhole mission but nothinghttps://peertube.laas.fr/static/streaming-playlists/hls/a771c3af-a081-4d8b-9c92-16f65176a93d/85c9eebf-7cb8-4d51-aeed-784f74b046a8-master.m3u8https://peertube.laas.fr/videos/embed/mFfzxftRB89Sy69ZNq7soH98002025-04-04T12:46:46.687ZYESBT2FiacreNOhttps://peertube.laas.fr/w/6RhNGprXYrTYg8WH3vcJs5https://peertube.laas.fr/lazy-static/thumbnails/d8c2e258-3f0d-4d58-879a-99cd6d23742c.jpgrecharge loc failurerecharge loc failurehttps://peertube.laas.fr/static/streaming-playlists/hls/2f5f7e9a-ccb6-471f-ba00-b6fe4f303fd8/40922c77-bef8-413c-a99d-b7f34318f772-master.m3u8https://peertube.laas.fr/videos/embed/6RhNGprXYrTYg8WH3vcJs526032025-04-04T12:49:35.162ZYESBT2FiacreNOhttps://peertube.laas.fr/w/8UVwPxUmUzNxNP8kfchhsuhttps://peertube.laas.fr/lazy-static/thumbnails/2c520ef3-2e96-4323-9e2a-4a2f683bab15.jpgFast successful missionThe drone finds the target almost immediately and then returns to the base and loand.https://peertube.laas.fr/static/streaming-playlists/hls/4013a2f4-771c-489a-98b3-0b72a6e37070/45a48811-66c0-41de-a414-6a87f25f0ab1-master.m3u8https://peertube.laas.fr/videos/embed/8UVwPxUmUzNxNP8kfchhsu22062025-04-04T12:51:51.093ZYESBT2FiacreNOhttps://peertube.laas.fr/w/rFifbtNQW3Y6H6pTcS8RJThttps://peertube.laas.fr/lazy-static/thumbnails/e8984da6-fd43-49a7-a373-61ef6ec98569.jpgMIsssion with a battery recharge but ulimately an overall failure.The drone executes the whole mission (with on battery recharge), flying the pattern at the 3 flight levels, but never finds the target, hence, fails the mission.https://peertube.laas.fr/static/streaming-playlists/hls/cff119cf-cd16-4f25-aab4-6cb92ac4f2f3/94b237d3-d4dd-47c3-861c-af8c3caf6cb5-master.m3u8https://peertube.laas.fr/videos/embed/rFifbtNQW3Y6H6pTcS8RJT1110102025-04-04T12:52:31.391ZYESBT2FiacreNOhttps://peertube.laas.fr/w/9ngZXRRom3a339MQRW5iEZhttps://peertube.laas.fr/lazy-static/thumbnails/bbec3d56-1cb7-45d0-8564-5e26a0e391ec.jpgH1 First Policy DeployedFirst deployment of a RL policy. This test is simply the one found here: https://github.com/unitreerobotics/unitree_rl_gym/https://peertube.laas.fr/static/streaming-playlists/hls/43c196a1-ea34-499d-9766-aad32fbb0659/532736ca-74c0-42db-95d2-08ee63a78ee5-master.m3u8https://peertube.laas.fr/videos/embed/9ngZXRRom3a339MQRW5iEZ800412025-04-18T17:07:37.038ZYESC3PONOhttps://peertube.laas.fr/w/9om4Y89qRraSf72yH1seYkhttps://peertube.laas.fr/lazy-static/thumbnails/01e1205f-b86f-4980-a26e-f65b5949f9dc.jpgStagewise Implementations of Sequential Quadratic Programming for Model-Predictive ControlSubmitted to IEEE Transactions on Robotics (T-RO) By Armand Jordana (1), Sébastien Kleff (1), Avadesh Meduri (1), Justin Carpentier (2,3), Nicolas Mansard (4,5), Ludovic Righetti (1,5) The promise of model-predictive control in robotics has led to extensive development of efficient numerical optimal control solvers in line with differential dynamic programming because it exploits the sparsity induced by time. In this work, we argue that this effervescence has hidden the fact that sparsity can be equally exploited by standard nonlinear optimization. In particular, we show how a tailored implementation of sequential quadratic programming achieves state-of-the-art model-predictive control. Then, we clarify the connections between popular algorithms from the robotics community and well-established optimization techniques. Further, the sequential quadratic program formulation naturally encompasses the constrained case, a notoriously difficult problem in the robotics community. Specifically, we show that it only requires a sparsity-exploiting implementation of a state-of-the-art quadratic programming solver. We illustrate the validity of this approach in a comparative study and experiments on a torque-controlled manipulator. To the best of our knowledge, this is the first demonstration of nonlinear model-predictive control with arbitrary constraints on real hardware. Project page: https://gepettoweb.laas.fr/articles/jordana_kleff_meduri__sqp_tro_2025.html Pre-print available at: https://hal.science/hal-04330251/ - ^1^ NYU - New York University [New York] - ^2^ NYU Tandon School of Engineering - ^3^ LAAS-CNRS, Université de Toulouse - ^4^ Inria, École normale supérieure, CNRS, PSL Research University, Paris - ^5^ Artificial and Natural Intelligence Toulouse Institute, Toulouse https://peertube.laas.fr/static/streaming-playlists/hls/43e7d6fe-2680-4c95-a252-d48a6e453ac7/153b55f3-65f9-4667-9dea-af4762199ebb-master.m3u8https://peertube.laas.fr/videos/embed/9om4Y89qRraSf72yH1seYk2130152025-04-29T10:26:08.111ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/vMgVFRe7e7jyfYc6eXFg8Lhttps://peertube.laas.fr/lazy-static/thumbnails/bf0ceefa-def2-4501-b6bc-783b84b60335.jpgForce feedback model-predictive control via online estimationPublished in IEEE International Conference on Robotics and Automation (ICRA) By Armand Jordana (1,2,3), Sébastien Kleff (1,2,4), Justin Carpentier (3), Nicolas Mansard (4,5), Ludovic Righetti (1,2,5) Nonlinear model-predictive control has recently shown its practicability in robotics. However it remains limited in contact interaction tasks due to its inability to leverage sensed efforts. In this work, we propose a novel model-predictive control approach that incorporates direct feedback from force sensors while circumventing explicit modeling of the contact force evolution. Our approach is based on the online estimation of the discrepancy between the force predicted by the dynamics model and force measurements, combined with high-frequency nonlinear model-predictive control. We report an experimental validation on a torque-controlled manipulator in challenging tasks for which accurate force tracking is necessary. We show that a simple reformulation of the optimal control problem combined with standard estimation tools enables to achieve state-of-the-art performance in force control while preserving the benefits of model-predictive control, thereby outperforming traditional force control techniques. This work paves the way toward a more systematic integration of force sensors in model predictive control. Project page: https://gepettoweb.laas.fr/articles/jordana__icra2024.html Pre-print available at: https://hal.science/hal-04564888v1 ^1 NYU - New York University [New York] ^2 NYU Tandon School of Engineering ^3 Inria, École normale supérieure, CNRS, PSL Research University, Paris ^4 LAAS-CNRS, Université de Toulouse ^5 Artificial and Natural Intelligence Toulouse Institute, Toulouse https://peertube.laas.fr/static/streaming-playlists/hls/f12b4e29-02ab-41b4-a6a9-29ac94099146/85a7bcaa-5c5c-4ac3-9a9a-c1d77dff4fbe-master.m3u8https://peertube.laas.fr/videos/embed/vMgVFRe7e7jyfYc6eXFg8L1520112025-04-29T15:43:33.435ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/uq6gBHqAY8KypwdzausieLhttps://peertube.laas.fr/lazy-static/thumbnails/ce39dd80-9885-442b-8061-749d04a973d3.jpgRisk-Sensitive Extended Kalman FilterBy Armand Jordana (1), Avadesh Meduri (2), Etienne Arlaud (3), Justin Carpentier (3), Ludovic Righetti (1,4) Published in IEEE International Conference on Robotics and Automation (ICRA) In robotics, designing robust algorithms in the face of estimation uncertainty is a challenging task. Indeed, controllers often do not consider the estimation uncertainty and only rely on the most likely estimated state. Consequently, sudden changes in the environment or the robot's dynamics can lead to catastrophic behaviors. In this work, we present a risk-sensitive Extended Kalman Filter that allows doing outputfeedback Model Predictive Control (MPC) safely. This filter adapts its estimation to the control objective. By taking a pessimistic estimate concerning the value function resulting from the MPC controller, the filter provides increased robustness to the controller in phases of uncertainty as compared to a standard Extended Kalman Filter (EKF). Moreover, the filter has the same complexity as an EKF, so that it can be used for real-time model-predictive control. The paper evaluates the risk-sensitive behavior of the proposed filter when used in a nonlinear model-predictive control loop on a planar drone and industrial manipulator in simulation, as well as on an external force estimation task on a real quadruped robot. These experiments demonstrate the abilities of the approach to improve performance in the face of uncertainties significantly. Project page: https://gepettoweb.laas.fr/articles/jordana__ekf_icra2025.html Pre-print available at: https://hal.science/hal-04107207v1 ^1 NYU Tandon School of Engineering ^2 NYU - New York University [New York] ^3 WILLOW - Models of visual object recognition and scene understanding ^4 Max Planck Institute for Intelligent Systems [Tübingen] https://peertube.laas.fr/static/streaming-playlists/hls/e61cfaf1-2ceb-4b0b-a769-c2ce105f0332/227bbb79-9cb1-469e-93f0-eff58df62b56-master.m3u8https://peertube.laas.fr/videos/embed/uq6gBHqAY8KypwdzausieL63082025-04-29T15:51:52.906ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/sA9GyRsTnozSNWb1gAezkShttps://peertube.laas.fr/lazy-static/thumbnails/298952b7-0b67-4071-be92-6c28ee68c2ce.jpgDiscovery motion by the robotMotion provided by Aldebaranhttps://peertube.laas.fr/static/streaming-playlists/hls/d752412a-171f-488b-a361-a49df9f285ac/8173629c-91c4-4967-9304-35213713c475-master.m3u8https://peertube.laas.fr/videos/embed/sA9GyRsTnozSNWb1gAezkS120132025-05-06T04:52:57.309ZYESRobot Roméo from Aldebaran RoboticsNOhttps://peertube.laas.fr/w/hc3hVrQnC6jWLCAo9YdzrAhttps://peertube.laas.fr/lazy-static/thumbnails/1a6b1ba4-2148-47cd-baf5-72166d32b472.jpgRoméo walking on the floorThe only walking that Gepetto (Kevin Giraud--Esclasse and Olivier Stasse) succeeded to realize on the robot https://peertube.laas.fr/static/streaming-playlists/hls/831ccff7-85ee-444e-aa99-084e301ffc50/a24d486a-5f78-4760-97cf-bfbe1f2e65a2-master.m3u8https://peertube.laas.fr/videos/embed/hc3hVrQnC6jWLCAo9YdzrA240312025-05-06T04:56:29.768ZRoméo 2BPIwalkingromeoYESRobot Roméo from Aldebaran RoboticsNOhttps://peertube.laas.fr/w/uLd9mDJgL9kxXU7baHxKtphttps://peertube.laas.fr/lazy-static/thumbnails/d2d2ca3b-22af-4b2f-bcc7-18b29efeb966.jpgPosture and oscillations of the legs when controlling the legs in positionThis video illustrates the flexibilities present in the Roméo humanoid robot. The control flexibility tau = Kp ( q- q_d) + Kd ( dq -dq_d) is added to the mechanical flexibility. From memory the gains are very high, so this illustrate quite well the mechanical flexibility.https://peertube.laas.fr/static/streaming-playlists/hls/e8ec17a8-1661-4476-8852-c38a5b941bc9/217d73fe-9331-427d-a207-d81ab942dde8-master.m3u8https://peertube.laas.fr/videos/embed/uLd9mDJgL9kxXU7baHxKtp250152025-05-06T05:02:31.700ZLegsPosition controlRoméo 2YESRobot Roméo from Aldebaran RoboticsNOhttps://peertube.laas.fr/w/t5VxrEEAbQfD5nEjUTn9bUhttps://peertube.laas.fr/lazy-static/thumbnails/e7617626-3e06-4f39-b847-4110cd68221f.jpgWalking motion on line and in the airThis motion is generated on line in the Roméo robot using the algorithm proposed by Maximilien Naveau and here implemented by Kevin Giraud--Esclasse. It was tested in the here and on the floor.https://peertube.laas.fr/static/streaming-playlists/hls/db56b724-62dd-452c-80a0-54b9706f1010/1f2d1003-d29e-4418-aebb-9a8fabdf75e4-master.m3u8https://peertube.laas.fr/videos/embed/t5VxrEEAbQfD5nEjUTn9bU340422025-05-06T05:06:40.912ZWalking motionin the airRoméoYESRobot Roméo from Aldebaran RoboticsNOhttps://peertube.laas.fr/w/6y4coQKwhTNpX7LcPnZXz5https://peertube.laas.fr/lazy-static/thumbnails/98c42b9a-ecfe-4815-8fc7-964ecdda98ea.jpgOscillation test on the Romeo's actuator benchRewriting of the low level driver used on the Romeo's power electronics. It allowed to reach 1 KHz of control frequency.https://peertube.laas.fr/static/streaming-playlists/hls/2cf776bc-d8df-479a-bcfd-67fe2436a292/f5f12b93-d368-4627-a490-78dfb480e0f6-master.m3u8https://peertube.laas.fr/videos/embed/6y4coQKwhTNpX7LcPnZXz5130172025-05-06T05:09:08.526ZRoméoActuator benchYESRobot Roméo from Aldebaran RoboticsNOhttps://peertube.laas.fr/w/uEaFDFi29toJkePaGLaoQjhttps://peertube.laas.fr/lazy-static/thumbnails/3ffb9c3f-f219-4a0d-8231-bad7e3b99243.jpgVisual servoing on Romeo with ViSP and the SoTOn this video the Romeo robot is tracking a visual feature detected by ViSP. The control law is computed by the SoT. The experiment was realized by Kevin Giraud--Esclasse, Claudio Giovanni, Fabien Spindler and Olivier Stasse.https://peertube.laas.fr/static/streaming-playlists/hls/e8141d0c-f336-4f0c-984a-3f0f7dbfbff2/b7a22fa6-4712-4cb6-a403-c622e2fd1f4a-master.m3u8https://peertube.laas.fr/videos/embed/uEaFDFi29toJkePaGLaoQj450312025-05-06T05:11:33.244ZRoméoViSPSoTYESRobot Roméo from Aldebaran RoboticsNOhttps://peertube.laas.fr/w/hW6JB1EWSV5N9PMtX86nS9https://peertube.laas.fr/lazy-static/thumbnails/10941700-34ac-4923-91e5-90e2138f71f1.jpgInfinite-Horizon Value Function Approximation for Model Predictive ControlBy Armand Jordana (1,2), Sébastien Kleff (2,4,6), Arthur Haffemayer (4,5), Joaquim Ortiz-Haro (1), Justin Carpentier (3), Nicolas Mansard (4,5), Ludovic Righetti (2) Submitted to IEEE Robotics and Automation Letters (RAL) Model Predictive Control has emerged as a popular tool for robots to generate complex motions. However, the real-time requirement has limited the use of hard constraints and large preview horizons, which are necessary to ensure safety and stability. In practice, practitioners have to carefully design cost functions that can imitate an infinite horizon formulation, which is tedious and often results in local minima. In this work, we study how to approximate the infinite horizon value function of constrained optimal control problems with neural networks using value iteration and trajectory optimization. Furthermore, we demonstrate how using this value function approximation as a terminal cost provides global stability to the model predictive controller. The approach is validated on two toy problems and a real-world scenario with online obstacle avoidance on an industrial manipulator where the value function is conditioned to the goal and obstacle. Project page: https://gepettoweb.laas.fr/articles/jordana__value_2025.html Pre-print available at: https://hal.science/hal-04948407 ^1^ NYU - New York University [New York] ^2^ NYU Tandon School of Engineering ^3^ Inria, École normale supérieure, CNRS, PSL Research University, Paris ^4^ LAAS-CNRS, Université de Toulouse ^5^ Artificial and Natural Intelligence Toulouse Institute, Toulouse ^6^ Inria, Bordeaux https://peertube.laas.fr/static/streaming-playlists/hls/891fea8a-b760-4d90-9608-2f2db84ecb28/f59a2500-2bf3-448a-8fbc-3444c210e0cf-master.m3u8https://peertube.laas.fr/videos/embed/hW6JB1EWSV5N9PMtX86nS92100332025-05-15T20:06:52.275ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/synLitWUzZk45UJzhH3Fd7https://peertube.laas.fr/lazy-static/thumbnails/9fa94535-330e-43b2-a793-0f474728b759.jpgagimus-pick-and-place-pandaThis video showcases the [agimus_demo_05_pick_and_place](https://github.com/agimus-project/agimus-demos), the most advanced demonstration developed during the Agimus project. Running on the **Panda robot by Franka Emika** and integrated at **CTU**, the demo performs a **pick-and-place task** using **visual feedback**, **motion planning via HPP**, and **model predictive control (MPC)** in a **ROS2 environment**. The robot identifies objects from a pile, plans motions using HPP (through a CORBA interface), and executes them using MPC for precise control and collision avoidance. A custom sequencer orchestrates the task, sorting objects into boxes based on shape. Vision is reinforced by depth images and processed using HappyPose, now natively available in ROS2 via [happypose_ros](https://github.com/agimus-project/happypose_ros). This demo highlights the full integration of perception, planning, and control in a complex manipulation scenario.https://peertube.laas.fr/static/streaming-playlists/hls/d712d177-709d-4856-80a7-95be6bf0a05a/51a70ec7-4e17-4e09-ada8-aa6744292582-master.m3u8https://peertube.laas.fr/videos/embed/synLitWUzZk45UJzhH3Fd73110582025-05-16T14:40:33.620Zpick-and-placepandaagimusrobotYESAgimus ProjectNOhttps://peertube.laas.fr/w/aGGCWRMvfnPEg8aeTyxx72https://peertube.laas.fr/lazy-static/thumbnails/ada1d93d-496f-438f-b177-62b36a19fd41.jpgagimus-sanding-pandaThis video demonstrates a **Model Predictive Controller (MPC)** with **force feedback** on the **Panda robot** at **LAAS**, applied to a **sanding task** that involves physical interaction with a table surface. The controller integrates **joint torque estimates** and **external forces** measured by an **ATI Mini45 6D force-torque sensor** mounted at the end-effector, borrowed from **CTU**. Inspired by the approach in "*Introducing Force Feedback in Model Predictive Control*" (Kleff et al., IROS 2022), the controller extends classical MPC to adapt to sensed efforts using a robot actuation model. This allows real-time adaptation to contact forces, improving precision and robustness in compliant tasks. The implementation spans several repositories, including Python and ROS2 C++ controllers ([panda_deburring](https://gitlab.laas.fr/kwojciecho/panda_deburring/-/tree/devel?ref_type=heads), [agimus_pytroller](https://gitlab.laas.fr/kwojciecho/agimus_pytroller/-/tree/devel?ref_type=heads)), calibration tools ([panda_ft_sensor_calibration](https://github.com/Kotochleb/panda_ft_sensor_calibration/tree/devel)), updated robot description ([franka_description](https://github.com/agimus-project/franka_description/tree/feature/ft-sensor)), and sensor drivers ([ros2_net_ft_driver](https://github.com/gbartyzel/ros2_net_ft_driver)). This setup enables safe, feedback-driven control for manipulation tasks requiring dynamic contact response.https://peertube.laas.fr/static/streaming-playlists/hls/4e910acc-415b-45d0-ad2e-f18ac3033131/0fa9bb90-c5b2-480a-903c-88c00f864047-master.m3u8https://peertube.laas.fr/videos/embed/aGGCWRMvfnPEg8aeTyxx72470462025-05-16T14:52:56.988ZpandarobotagimusYESAgimus ProjectNOhttps://peertube.laas.fr/w/6DLVRpkvRxBat4aZrWuZzLhttps://peertube.laas.fr/lazy-static/thumbnails/03688e60-591a-43b2-b968-d636e78f3ea1.jpgForce Feedback in Model Predictive Control: A Soft Contact ApproachBy Sébastien Kleff (1,2,3), Armand Jordana (1,2,4), Nicolas Mansard (3,5), Ludovic Righetti (1,2,5) Submitted to IEEE Transactions on Robotics (T-RO) Model-predictive control is an appealing framework to control robots due to its ability to exploit both sensory information and model predictions. But its performance remains fundamentally limited in tasks involving contact with the environment, in part because optimal control policies do not reason over force measurements. In this article, we propose a first complete answer to this issue by introducing a novel approach that systematically includes measured efforts into the optimal control loop. We propose to augment the state-space with a visco-elastic model of the contact force in the task space. We derive a complete predictive controller with an efficient formulation whose implementation is released in open-source. We conduct extensive comparisons with two other methods: the classical model-predictive control formulation, which inherently restricts the feedback to position and velocity information, and our previous approach that enabled torque feedback in the joint space. We demonstrate through simulation studies and hardware experiments, the benefit of exploiting Cartesian force measurements in the model-predictive control framework to achieve challenging contact tasks. Project page: https://gepettoweb.laas.fr/articles/kleff_tro_2025.html Pre-print available at: https://hal.science/hal-04572399 ^1^ NYU - New York University [New York] ^2^ NYU Tandon School of Engineering ^3^ LAAS-CNRS, Université de Toulouse ^4^ Inria, École normale supérieure, CNRS, PSL Research University, Paris ^5^ Artificial and Natural Intelligence Toulouse Institute, Toulouse https://peertube.laas.fr/static/streaming-playlists/hls/2dc3e6a4-933e-448d-ad16-13fd6a57deca/49c6725c-4170-4d98-9d6b-851b4e80a198-master.m3u8https://peertube.laas.fr/videos/embed/6DLVRpkvRxBat4aZrWuZzL1120262025-05-19T09:56:34.755ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/jW2CELK7R6NndzdydGaFULhttps://peertube.laas.fr/lazy-static/thumbnails/4d164b0e-1ed1-47d9-80a4-27f013f03fd8.jpgIST - Karim Ramdani - Faut-il payer pour publier ?Conférence organisée entre le service IST édition et le groupe de travail éthique du LAAS Karim Ramdani - Inria Nancy Faut-il payer pour publier ? Un rapide survol des évolutions en cours dans l’édition scientifique. Durant cet exposé, je présenterai les différents modèles économiques en vigueur dans l’édition scientifique et dresserai un panorama des évolutions en cours. Je m’intéresserai plus particulièrement au modèle auteur-payeur (parfois appelé Gold Open Access) et je tenterai de montrer les risques qu’il présente. Enfin, je conclurai en évoquant quelques pistes d’actions possibles à l’échelle individuelle et institutionnelle.https://peertube.laas.fr/static/streaming-playlists/hls/994faa54-4027-4a1d-9478-795baa9d38d8/1dd33c4e-a4ec-4e4b-a1c4-df09419e48ec-master.m3u8https://peertube.laas.fr/videos/embed/jW2CELK7R6NndzdydGaFUL23530342025-05-22T15:24:33.340ZYESGTEthiqueNOhttps://peertube.laas.fr/w/iaRvVDEuvGLXUPtMzQiP8thttps://peertube.laas.fr/lazy-static/thumbnails/822ca13f-5508-4349-925a-30fd007f2a9a.jpgagimus-sanding-panda v2agimus-sanding-panda v2https://peertube.laas.fr/static/streaming-playlists/hls/8b0b9102-04cc-4103-9ed4-c2e324f82c55/d2bd0520-becb-4205-8440-268319bfae33-master.m3u8https://peertube.laas.fr/videos/embed/iaRvVDEuvGLXUPtMzQiP8t2380652025-05-23T15:20:17.487ZYESAgimus ProjectNOhttps://peertube.laas.fr/w/5txLFLLz7SbBP8C98roh26https://peertube.laas.fr/lazy-static/thumbnails/2636e9fa-c5da-49a5-aec0-6e1e580bde52.jpgpyrene-manipulate-boxManipulation of a box with a humanoid robot. The path is computed by the manipulation planning platform HPP.https://peertube.laas.fr/static/streaming-playlists/hls/243d3735-960f-4516-babe-64ddeeafc4df/cecbb657-7174-4a55-8b8e-bbabea5396b2-master.m3u8https://peertube.laas.fr/videos/embed/5txLFLLz7SbBP8C98roh26180202025-06-18T11:00:29.863ZYESMain florent channelNOhttps://peertube.laas.fr/w/pZnosMjJYMyud5no2Sbarghttps://peertube.laas.fr/lazy-static/thumbnails/ee379d3d-6f45-4e8a-92bb-94c3657c47b2.jpgVisual-RRT*: Generating Asymptotically Optimal Trajectories with Vision-based Controllers by Rafa...Visual-RRT*: Generating Asymptotically Optimal Trajectories with Vision-based Controllers by Rafael MURRIETA-CID Research director / Investigador Titular D (CIMAT - Centro de Investigación en Matemáticas) Email: murrieta@cimat.mx Site: https://www.cimat.mx/~murrieta Date: Monday, 16th of june, 2025 - 16:00 Place : LAAS-CNRS - Salle de Conférences 7 avenue du Colonel Roche 31077 TOULOUSE Cedex 4 Résumé : In this talk, we will present a planning method for robotic systems that, by construction, guarantees the planned trajectories to be executable in closed-loop with a visual servoing controller, in addition to assuring their asymptotically optimality in the state space. The design of this method requires one to obtain a locally optimal steering method, locally stable closed-loop controllers used to track the optimal trajectories, and a mapping between the motion of the robot in the state space and the corresponding motion of the visual features in the image space. As a result, the proposed approach allows the system to navigate in a closed-loop manner among non-convex obstacles, following asymptotically optimal trajectories. The method is validated using two systems: a nonholonomic robot and a robotic arm. Real-world experiments are carried out for the first system. Biographie : In November 1998 he received the PhD. from the INP of Toulouse. His PhD. research was done in the group of "Robotique et Intelligence Artificielle" (RIA) of the "Laboratoire d'Analyse et d'Architecture des Systemes du Centre National de la Recherche Scientifique Francaise" (LAAS/CNRS) in Toulouse, under the supervision of Maurice Briot and Michel Devy. His PhD. research was about artificial vision for outdoor autonomous robots. From September 2002 to July 2004 he was a postdoctoral researcher in the Beckman Institute and the Department of Electrical and Computer Engineering (ECE) of the University of Illinois at Urbana-Champaign (UIUC). He worked with Seth Hutchinson. He ...https://peertube.laas.fr/static/streaming-playlists/hls/c244c3b2-9c4b-4eb1-aa99-4b216ce9064d/22e66835-9101-4682-8e84-29c4bd80c1fc-master.m3u8https://peertube.laas.fr/videos/embed/pZnosMjJYMyud5no2Sbarg26820162025-06-18T12:29:04.497ZYESSeminars in GepettoNOhttps://peertube.laas.fr/w/n7XgjbrfZii5QQ6sUf8c9mhttps://peertube.laas.fr/lazy-static/thumbnails/764cada3-c710-4738-a5f4-ba1140a6ea5c.jpgBEYOND RIGID: Exploring Soft Robotics par Charbel D. TAWK Assistant Professor (Lebanese American ...Website: https://soe.lau.edu.lb/about/people/charbel-dalely-tawk.php Date: Mercredi, 18 juin, 2025 - 14:00 Lieu : LAAS-CNRS - Salle de Conférences 7 avenue du Colonel Roche 31077 TOULOUSE Cedex 4 Résumé : Soft robotics is an emerging field that combines compliant materials, bioinspired design, and advanced manufacturing to create adaptive robotic systems capable of safe and flexible interaction with complex environments. This seminar explores recent developments in the design and fabrication of soft actuators, sensors, and robotic interfaces using 3D printing and multi-material additive manufacturing. Key themes include the development of soft grippers, computational tools, including finite element modeling and machine learning, wearable soft robotics, including tactile sensors and haptic interfaces that support human–machine interaction in applications like rehabilitation, prosthetics, and teleoperation, and other forms of soft robotics systems. Biographie : Charbel Dalely Tawk is an Assistant Professor at the Lebanese American University (LAU), specializing in soft robotics, additive manufacturing, and human-machine interfaces. He earned his Ph.D. in Soft Robotics from the University of Wollongong, Australia, in 2019, under the ARC Centre of Excellence for Electromaterials Science (ACES), and his B.E. in Mechanical Engineering from the Lebanese American University in 2016. His research focuses on integrating 3D printing technologies with soft actuators and sensors to create adaptable, human-compatible robotic devices. Key areas of his work include the design and fabrication of 3D-printed soft grippers with embedded sensing capabilities, enabling precise and responsive interactions in various applications. Additionally, he explores soft human-machine interfaces, aiming to enhance the integration of robotic systems with human operators through intuitive control mechanisms. His contributions to additive manufacturing techniques further support the creati...https://peertube.laas.fr/static/streaming-playlists/hls/ab086ea1-11fe-4848-8812-4488c8caf3e8/db0d94e9-a8c4-4d9b-be20-d1ece08e2578-master.m3u8https://peertube.laas.fr/videos/embed/n7XgjbrfZii5QQ6sUf8c9m27920472025-06-19T11:27:36.144ZYESSeminars in GepettoNOhttps://peertube.laas.fr/w/1jpJmhozRqxf6nupuUkDDehttps://peertube.laas.fr/lazy-static/thumbnails/4cb3d7d5-2528-4645-af3d-57aa892af587.jpgPrésentation de l'Automatique par des Secondes (2025)Cette vidéo a été conçue et réalisée par des élèves de seconde lors de leur stage en juin 2025. L'objectif était de comprendre et restituer les principes de l'Automatique, en particulier autour de la maquette du pendule inversé.https://peertube.laas.fr/static/streaming-playlists/hls/02920318-ab2b-4485-8541-f8a2c07c611b/9a03ad1b-9be7-4521-a81f-13b2ecb99fd4-master.m3u8https://peertube.laas.fr/videos/embed/1jpJmhozRqxf6nupuUkDDe2220432025-07-05T11:24:26.707ZYESMain yariba channelNOhttps://peertube.laas.fr/w/6hnN96zyP7ADvGvyop3hfwhttps://peertube.laas.fr/lazy-static/thumbnails/e5787382-4161-41c8-bc03-a4df65826d97.jpgpanda MPC visual servoing + collision avoidancepanda MPC visual servoing + collision avoidancehttps://peertube.laas.fr/static/streaming-playlists/hls/2ac7068c-6eab-47f0-9108-43a1d534488a/6aa73f2b-bd08-4dad-8993-02de017f9a29-master.m3u8https://peertube.laas.fr/videos/embed/6hnN96zyP7ADvGvyop3hfw190422025-07-09T09:26:05.296ZYESMain tmartinezf channelNOhttps://peertube.laas.fr/w/5Yq4NvZPb8XLPNNW9F6apWhttps://peertube.laas.fr/lazy-static/thumbnails/6e8ac413-e262-4daf-9827-61bb49ad5519.jpgpanda MPC visual servoingpanda MPC visual servoinghttps://peertube.laas.fr/static/streaming-playlists/hls/28450964-14c2-413f-82a9-222966422968/00d36ebe-760e-439d-abc5-1eefebce7f19-master.m3u8https://peertube.laas.fr/videos/embed/5Yq4NvZPb8XLPNNW9F6apW230662025-07-09T09:32:21.324ZYESMain tmartinezf channelNOhttps://peertube.laas.fr/w/hVYEnX3Sya5qu2GWavFxnqhttps://peertube.laas.fr/lazy-static/thumbnails/88476a9a-42a9-4aad-8cf0-d371a0fc0bbe.jpgMultimodal AGent for robotique MAnipulation : V0Some videos from work from early 2025. No training needed. Adaptation to unseen task and unseen object (as long as the camera is able to detect them). Adaptation to all robots hardware and interface. Currently running on a distant machine using a 7 Billions parameter Transformers. I am working to compress it to 2B and to run directly on the robot in real time.https://peertube.laas.fr/static/streaming-playlists/hls/891b8eb0-8b95-45ee-a46c-52d30a5ef43e/059a2592-951e-4596-b068-848589e38574-master.m3u8https://peertube.laas.fr/videos/embed/hVYEnX3Sya5qu2GWavFxnq3400462025-08-02T20:16:34.312ZvisionrobotichumanoidlanguageLLMYESLoan BERNAT ChannelNOhttps://peertube.laas.fr/w/nGG1DtPuJicQtfJuuUX94ehttps://peertube.laas.fr/lazy-static/thumbnails/2c3e4029-c950-4769-a902-c38dfd48e55d.jpgcomparison_lifting_cutcomparison_lifting_cuthttps://peertube.laas.fr/static/streaming-playlists/hls/afbe5205-d96d-46a4-af4a-f62293b24933/cf0ec0aa-91c1-48ff-a33f-566e0e1c5e4e-master.m3u8https://peertube.laas.fr/videos/embed/nGG1DtPuJicQtfJuuUX94e30282025-09-28T01:35:42.178ZYESMain msabbah channelNOhttps://peertube.laas.fr/w/5cW4no88QqrVD5WFwaS8kzhttps://peertube.laas.fr/lazy-static/thumbnails/cac6260a-82dc-4430-9d96-700145ff9e25.jpgre-graspIn this video we used the AGIMUS architecture to plan a pick and place motion that needs two hands to perform. In this experiment though we only have access to a table and a unique robot arm. Hence we need to grasp the object once, reconfigure it on the table and re-grasp it in order to achieve the desired end configuration of the object. We use the intelligence of the Humanoid Path Planner (HPP) software to solve such a problem automatically. HPP is using randomized algorithm to explore the space and we did not yet use the functionality to shorten the paths. Hence sometimes the robot will perform unoptimized path in terms of length but always in a collision free space as requested.https://peertube.laas.fr/static/streaming-playlists/hls/220f0cf3-2bd0-4398-bccb-08ccd05c274b/6d515527-791a-4d4d-9e10-027e3122096c-master.m3u8https://peertube.laas.fr/videos/embed/5cW4no88QqrVD5WFwaS8kz1560592025-09-25T16:37:14.805ZYESMain mnaveau channelNOhttps://peertube.laas.fr/w/hoAinLX5c7QXVkYvW52x4jhttps://peertube.laas.fr/lazy-static/thumbnails/c5bb6612-5122-4ba9-b1e6-44cc3477b4e7.jpgFirst experiment with a home-trained policy on H1v2 at LAAS-CNRSAuthors: Ale, Côme, Constant et alhttps://peertube.laas.fr/static/streaming-playlists/hls/84b9b828-4af3-4379-84ab-66354f07e884/1432abdd-546c-4c88-9dbc-9f6b18c2b129-master.m3u8https://peertube.laas.fr/videos/embed/hoAinLX5c7QXVkYvW52x4j220412025-10-15T06:10:21.573ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/oY2KeZcjdsmfywg5aH3y34https://peertube.laas.fr/lazy-static/thumbnails/95077ebb-c364-4d59-a4fc-b61c833c9afa.jpgLearning Force-Feedback MPC with Obstacles for Robotic DeburringLearning Force-Feedback MPC with Obstacles for Robotic Deburringhttps://peertube.laas.fr/static/streaming-playlists/hls/b9fbc701-65f7-490a-b301-543af5d51ff7/6652ad71-3c56-4f33-8302-d2b654d1e202-master.m3u8https://peertube.laas.fr/videos/embed/oY2KeZcjdsmfywg5aH3y341510182025-10-15T18:37:27.933ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/npBenPa27YHZo6pMXF2q8Qhttps://peertube.laas.fr/lazy-static/thumbnails/4a071456-f7da-4142-acd7-217152a100b4.jpgbipetto_run_forwardbipetto_run_forwardhttps://peertube.laas.fr/static/streaming-playlists/hls/ad5bbaef-2e72-4368-83f2-237bd586b1de/8570802b-8998-4015-854d-1ba67577756e-master.m3u8https://peertube.laas.fr/videos/embed/npBenPa27YHZo6pMXF2q8Q140312025-10-22T15:47:27.818ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/xaXGNKjRsLrpDKcKgd7oyThttps://peertube.laas.fr/lazy-static/thumbnails/079c96a5-888f-430c-abaa-7f4ceaec35cc.jpgbipetto_pushbipetto_pushhttps://peertube.laas.fr/static/streaming-playlists/hls/fc6f5228-018a-45d5-abcc-8e986b9f97db/b6630eea-d5a8-40cd-a366-9840f2ff103c-master.m3u8https://peertube.laas.fr/videos/embed/xaXGNKjRsLrpDKcKgd7oyT90222025-10-22T15:47:12.747ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/mqwTmPbMsHzKGbvJYiHY1zhttps://peertube.laas.fr/lazy-static/thumbnails/6d7a7797-1c72-4a44-bf06-832528441602.jpgbipetto_walkbipetto_walkhttps://peertube.laas.fr/static/streaming-playlists/hls/a563a854-cbeb-4197-8584-7fb79b7cde79/b4a6f9fb-4402-49bf-8b73-c24d7fae4673-master.m3u8https://peertube.laas.fr/videos/embed/mqwTmPbMsHzKGbvJYiHY1z290142025-10-22T15:46:59.021ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/wnMr6j2snXXCCj1MaxwrWxhttps://peertube.laas.fr/lazy-static/thumbnails/fb1e910c-2683-4ea4-a345-800bc0753276.jpgBipetto, 20 octobre 2025Bipetto, 20 octobre 2025https://peertube.laas.fr/static/streaming-playlists/hls/f5fcc71e-b621-4ff9-90d9-877c6921e85f/923d4614-f505-407f-aeb5-06e0d4bae9d4-master.m3u8https://peertube.laas.fr/videos/embed/wnMr6j2snXXCCj1MaxwrWx620712025-10-24T07:06:40.744ZYESMain vbatto channelNOhttps://peertube.laas.fr/w/4wwgZrNJ7kzuYFg6oNyB5shttps://peertube.laas.fr/lazy-static/thumbnails/84f67b16-395a-451d-a8cf-6231d3316c20.jpgFirst metal deburingFirst metal deburinghttps://peertube.laas.fr/static/streaming-playlists/hls/1c8e631b-afb9-4396-b0f0-744d2e8b424e/67e65b44-12e1-4a35-a863-636f2bb2bd2e-master.m3u8https://peertube.laas.fr/videos/embed/4wwgZrNJ7kzuYFg6oNyB5s200292025-11-18T13:02:07.318ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/6gdZMjVF14yZ47bEcUM4kVhttps://peertube.laas.fr/lazy-static/thumbnails/9907f3eb-417c-42e0-84c6-036fe8e9e62f.jpgTEAM_course_characterization-2024-Dimensional characterizationThis course in english present the different dimensionnal technics of characterization available in clean roomhttps://peertube.laas.fr/static/streaming-playlists/hls/2a9ddbeb-8a93-415f-96c5-43aaca5c1897/8c75bc39-5020-46e1-bb50-4ec07d54ee30-master.m3u8https://peertube.laas.fr/videos/embed/6gdZMjVF14yZ47bEcUM4kV770092025-11-20T11:55:32.959ZYESMain breig channelNOhttps://peertube.laas.fr/w/x5ifycrMCaRK83qiXTCfNqhttps://peertube.laas.fr/lazy-static/thumbnails/37d7122b-0102-42fd-867f-1cc1073cb21d.jpgTEAM_course_characterization-2024-ConclusionsThis video in english present the conclusions of the TEAM course of characterization in cleanroomhttps://peertube.laas.fr/static/streaming-playlists/hls/fba4e7a1-ff0d-40a0-b39e-d6c733a811ec/184e44c9-31c8-43c0-bef8-2a6aec22a1b2-master.m3u8https://peertube.laas.fr/videos/embed/x5ifycrMCaRK83qiXTCfNq171042025-11-20T11:58:24.347ZYESMain breig channelNOhttps://peertube.laas.fr/w/pixh98LgT3LtVLxG4SrkaZhttps://peertube.laas.fr/lazy-static/thumbnails/b7bd7874-c8fe-4b75-b6dd-f68642b66833.jpgInspireHandsTest Inspire Hands on 2025/11/26https://peertube.laas.fr/static/streaming-playlists/hls/bcb51bf4-2e9b-4cd1-8327-e981c53f5157/47b2043a-7c4c-4ba5-a9f6-00373c9cd6f0-master.m3u8https://peertube.laas.fr/videos/embed/pixh98LgT3LtVLxG4SrkaZ200582025-11-26T16:01:57.071ZYESH1v2 @GEPETTONOhttps://peertube.laas.fr/w/rANCKUNGFsdgggyUdqpRKBhttps://peertube.laas.fr/lazy-static/thumbnails/b6c77aa2-3d19-469e-93a0-b9e5a94e3d57.jpgBT2Fiacre Drone experiment in a dockerThis video presents a screencast of five successive launches of the Drone demo: - the first demo is setup (following the commands described and explained in the installation documentation) and after setting up the gazebo/rviz windows, the drone simulation is started. At 02:40, the BT execution is started, and the mission starts. - yet, it quickly fails with a battery critical and an emergency landing. 03:06 - we move back the drone in 0,0,1 and restart the missions. 03:40 - the second mission fails right away 03:50 with a start_drone failure. - the third mission starts 04:18 and run pretty well (flying up to the third level and detecting but fails with a localization problem at 05:35, which leads to an emergency landing. - 05:50 we show that 3 plates out of 4 were localized. - 05:57 we show the BT with the green "emergency" landing, but also the purple BT which have all been halted (because they were running in a reactive sequence which has now failed). - 06:40 we kill the whole demo to restart it with a fresh rviz/gazebo 07:03 - 07:36 we restart the fourth simulation and the BT at 08:20 - 09:06 again a localization error (those are random). - 09:25 back to 0, 0 , 1 - 09:46 restart the fifth BT (be patient, this one complete) - 11:00 2 plates found, 2 to to find... - 11:30 the 4 plates have been camera_track succeed, hence the parallel succeed, the navigation of the pattern is halted, and the drone return to land in 0, 0 and the whole BT succeed at 11:35 - the end of the video is just to show the environment, the rviz window (with the drone trajectory and the localized plates). https://peertube.laas.fr/static/streaming-playlists/hls/cf507e66-0ed0-4726-be14-ac164327ea5d/4492bf2d-a235-4768-b357-b4373ad55bbd-master.m3u8https://peertube.laas.fr/videos/embed/rANCKUNGFsdgggyUdqpRKB7830352025-12-09T16:47:53.428ZYESBT2FiacreNOhttps://peertube.laas.fr/w/qKwaSrNjasy3nSqT9DJTWghttps://peertube.laas.fr/lazy-static/thumbnails/52e4c01c-3d8f-4268-b949-aeb2a6d10a12.jpgIST - Ophélie Fraisier-Vannier - (Més)usages des LLM pour la production d’articles scientifiquesConférence organisée entre le service IST édition et le groupe de travail éthique du LAAS **Ophélie** **Fraisier-Vannier** **-** **IRIT** (Més)usages des LLM pour la production d’articles scientifiques ------------------------------------------------------------------------------------ L’explosion de l’IA générative ces dernières années a impacté l’ensemble de la société, notamment via les nouvelles possibilités présentées par les outils de génération de texte dont ChatGPT est le représentant le plus connu. Le monde de la recherche n’est pas épargné par ce phénomène. Dans cette présentation, je parlerai de la façon dont ces outils ont été mobilisés dans la publication scientifique en me concentrant plus particulièrement sur leur usages dans les pratiques de recherche discutables.https://peertube.laas.fr/static/streaming-playlists/hls/c86ee729-74ca-4b49-a9f2-f18696007c17/9e742e95-7ed8-4aa3-8b28-a710acc80bb6-master.m3u8https://peertube.laas.fr/videos/embed/qKwaSrNjasy3nSqT9DJTWg20580172025-12-18T13:51:47.730ZYESGTEthiqueNOhttps://peertube.laas.fr/w/tY9UPJqLgEFPPNNFjrKRQ3https://peertube.laas.fr/lazy-static/thumbnails/3c0c2253-3e91-4554-95d3-b358ca1e24dc.jpgVidéo_Générée_à_Partir_de_TexteDemo Fabrice Prigent pour Capitoulhttps://peertube.laas.fr/static/streaming-playlists/hls/e27de2e9-b768-4559-9b2c-1c3d524cfe0e/f74cd198-661e-4830-a869-860393cb1840-master.m3u8https://peertube.laas.fr/videos/embed/tY9UPJqLgEFPPNNFjrKRQ380442025-12-18T08:30:05.711ZYESMain matthieu channelNOhttps://peertube.laas.fr/w/nn8LuK29eNZ2RjBwKrvjX4https://peertube.laas.fr/lazy-static/thumbnails/31b2e497-becd-4d8c-ae15-21c31d671a39.jpgIST - Guillaume Cabanac - Pro bono decontamination of the scientific literatureConférence organisée entre le service IST édition et le groupe de travail éthique du LAAS **Guillaume** **Cabanac** **-** **IRIT** Pro bono decontamination of the scientific literature: How sleuths track errors and fraud with the Problematic Paper Screener Imagine reading invulnerable framework, glucose bigotry, and nucleic corrosive* in a scientific paper published in an established journal with Impact Factor from an haute couture publisher such as Elsevier, Wiley, Springer... Well, we identified more than 18k such problematic papers featuring ‘tortured phrases’ produced by paraphrasing tools to deceive plagiarism detection. In 2021, this issue affected 3 every 10k papers. Scammers produce such unreliable papers in bulk to appear hyper productive; they organise citation rings to increase their h-index. This talk presents how sleuths strive to decontaminate the literature from this digital pollution. A handful of professional scientists and hobbyists re-assess the suspect papers flagged by the ‘Problematic Paper Screener,’ contribute pro bono post-publication peer reviews on PubPeer, and eventually manage to get publishers retract 3000+ papers, mostly in engineering and biomedicine. We also discuss the domino effect of retractions and the necessity to issue chain retractions to stop errors from propagating in the literature. *instead of immune system, glucose intolerance, and nucleic acid.https://peertube.laas.fr/static/streaming-playlists/hls/ad035155-c5ac-46b8-af14-44394c95baf9/114b5ed0-2ab3-430a-ad64-4a5f62bc5bc8-master.m3u8https://peertube.laas.fr/videos/embed/nn8LuK29eNZ2RjBwKrvjX420910162025-12-18T14:57:55.697ZYESGTEthiqueNOhttps://peertube.laas.fr/w/wVbFndRNFt4BLDdYyVHu3ehttps://peertube.laas.fr/lazy-static/thumbnails/6efbed6d-5f1d-48f1-ac32-2f92bde9748f.jpgEcoLAAS conférences : Roland Séférian - CNRMEcoLAAS conférences : Roland Séférian - CNRMhttps://peertube.laas.fr/static/streaming-playlists/hls/fa5f291d-7b10-40c9-81c0-6a5ad0879629/a9e5efa7-5b89-46ea-82b0-7f49358f3da2-master.m3u8https://peertube.laas.fr/videos/embed/wVbFndRNFt4BLDdYyVHu3e52660132026-01-05T13:28:10.158ZClimat, CNRM, GIECYESEcoLAASNOhttps://peertube.laas.fr/w/hotgPp1KP6iEcegCMAZHFyhttps://peertube.laas.fr/lazy-static/thumbnails/71a51ec9-c8bf-4532-9e27-0e3f4244f834.jpgC3PO: Evaluation of the Cocobots settingsC3PO: Evaluation of the Cocobots settingshttps://peertube.laas.fr/static/streaming-playlists/hls/84b5638f-407d-41bc-9c46-4d9853637962/162183ca-d332-4052-a2cf-fb779507718d-master.m3u8https://peertube.laas.fr/videos/embed/hotgPp1KP6iEcegCMAZHFy58092026-01-19T16:52:54.031ZYESC3PONOhttps://peertube.laas.fr/w/7Va7oteLDiT3sv9zu3Xu4Dhttps://peertube.laas.fr/lazy-static/thumbnails/b1ac7044-1343-4566-87c5-d213838a2731.jpgCompliant Collision Avoidance with Diffusion of a Panda Arm in a Cluttered EnvironmentFrom the paper: https://arxiv.org/abs/2601.02873https://peertube.laas.fr/static/streaming-playlists/hls/3802ddb7-c949-4c2d-9c71-84f615d03a3b/abd78844-2156-49b1-8e14-552fb6472ec7-master.m3u8https://peertube.laas.fr/videos/embed/7Va7oteLDiT3sv9zu3Xu4D31052026-01-21T15:53:36.203ZYESMain ahaffemaye channelNOhttps://peertube.laas.fr/w/ff7J5ugPpHj7dDH2goVRNohttps://peertube.laas.fr/lazy-static/thumbnails/4e7300d4-ad93-41ce-b0ff-7cd15c8a70db.jpgWarm-Starting Collision-Free Model Predictive Control With Object-Centric DiffusionThis video illustrates the paper "Warm-Starting Collision-Free Model Predictive Control With Object-Centric Diffusion" published in the Robotics and Automation Letters. Its shows how an optimal control program warm-started by a trajectory generated by a diffusion neural network can produce a collision-free motion for a robotic arm in the presence of movable obstacles.https://peertube.laas.fr/static/streaming-playlists/hls/73587fad-5ebd-4003-b1ed-41f89aeca62e/cdbac5a8-088a-44f2-b922-33d65caf7068-master.m3u8https://peertube.laas.fr/videos/embed/ff7J5ugPpHj7dDH2goVRNo197022026-01-22T15:57:04.606ZYESMain florent channelNOhttps://peertube.laas.fr/w/7XDq6Lw8CYsJvoR59KjoTVhttps://peertube.laas.fr/lazy-static/thumbnails/61d3a066-8091-4d7d-88e4-a074ab680cc9.jpgKey Recovery from Side-Channel Power Analysis Attacks on Non-SIMD HQC DecryptionTalk recorded for CRYPTO 2025. More information, including links to papers and slides, is available at https://crypto.iacr.org/2025/program.phphttps://peertube.laas.fr/static/streaming-playlists/hls/385bcc24-bfed-45e2-bf8d-dc2c297c1ddb/ebbece36-c3ce-468e-9d71-96c372e52b76-master.m3u8https://peertube.laas.fr/videos/embed/7XDq6Lw8CYsJvoR59KjoTV996032026-01-23T10:03:36.220ZPost-Quantum Cryptographycryptographyside-channel attacksPQCHQCYESMain nmaillet channelNOhttps://peertube.laas.fr/w/nj39MnSH6Tg5XCYviXjkFChttps://peertube.laas.fr/lazy-static/thumbnails/b056e6c5-4ad9-446d-a13b-a8489e052b00.jpgVideo_20260123175321Video_20260123175321https://peertube.laas.fr/static/streaming-playlists/hls/ac94a025-fa6e-478e-8846-1fe31b514ac6/667ef770-93ca-47e5-babe-e1935767de17-master.m3u8https://peertube.laas.fr/videos/embed/nj39MnSH6Tg5XCYviXjkFC42072026-01-23T17:55:34.193ZYESMain mkulcsar channelNOhttps://peertube.laas.fr/w/cNFtoYMqn86jzYti4fToWMhttps://peertube.laas.fr/lazy-static/thumbnails/11ba222f-0a7e-4bf2-b859-0605228279b8.jpgMetal deburring sequenceMetal deburring sequencehttps://peertube.laas.fr/static/streaming-playlists/hls/5f99107b-1f59-4d5e-bf95-c2832448f2f9/8326c4b2-05a1-4dba-96ed-b5ef3304ef04-master.m3u8https://peertube.laas.fr/videos/embed/cNFtoYMqn86jzYti4fToWM1340192026-01-26T15:37:39.846ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/f7Va7JQ1UmTZhRXGERZHifhttps://peertube.laas.fr/lazy-static/thumbnails/ef0dc299-2cde-45c2-99d1-15cd7f39e1a8.jpgPlastic deburring sequence 2Plastic deburring sequence 2https://peertube.laas.fr/static/streaming-playlists/hls/725729c3-192a-49de-a2ad-fab490f22fe4/fbc50d28-4a8e-4836-af9d-6bb233409786-master.m3u8https://peertube.laas.fr/videos/embed/f7Va7JQ1UmTZhRXGERZHif2630222026-01-26T15:49:43.020ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/j7jziJF9PSpHtCuLxsdCdwhttps://peertube.laas.fr/lazy-static/thumbnails/1216379b-58ba-49c2-bb3e-0758d8172492.jpgPanda first car polishingPanda first car polishinghttps://peertube.laas.fr/static/streaming-playlists/hls/92a667c0-76f2-4d45-9fda-a70fd8423ec6/0dd417be-b387-45e1-b013-fd08023e3e1f-master.m3u8https://peertube.laas.fr/videos/embed/j7jziJF9PSpHtCuLxsdCdw610252026-02-04T17:38:09.478ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/5gaNga5mUez4AqDmwVzzv3https://peertube.laas.fr/lazy-static/thumbnails/f5a62224-60b9-466a-8442-e830a14128c1.jpgAutonomous Long-Horizon Manipulation with MAGMA on Real Robots [V1]Videos showcasing two real-robot use cases of the **MAGMA** framework. The system relies on a decoder-only Transformer model with **1.7 billion parameters**, trained using **MAGMA-GEN**, a fully autonomous data-generation framework for learning language-conditioned robotic control policies over long horizons. The training process does not rely on any human-annotated data. For execution, the system integrates *M2T2* for grasp detection and *HPP* for motion planning. The full software stack is implemented in *ROS 2* and runs entirely on a standard laptop computer. The framework is generic and can be adapted to other robotic platforms and task settings. For further information or reuse in your projects, please contact me.https://peertube.laas.fr/static/streaming-playlists/hls/2282bfca-5365-42b5-b8b6-1aa00c8c65f0/392374ff-fda9-4efc-82dc-a5474fc5289e-master.m3u8https://peertube.laas.fr/videos/embed/5gaNga5mUez4AqDmwVzzv33430292026-02-07T15:13:39.622ZINTERACTIONLLMLONG-HORIZONIARoboticsYESLoan BERNAT ChannelNOhttps://peertube.laas.fr/w/db59zo1jzeFAKGQiAEbv9shttps://peertube.laas.fr/lazy-static/thumbnails/b8ad07dd-ca2b-4e2f-aea1-ea1bacbdfedf.jpgPolishing Panda CrayonPolishing Panda Crayonhttps://peertube.laas.fr/static/streaming-playlists/hls/6295a867-3fbc-4ba8-a5e1-66ec55390c6e/b9f22a76-e058-4936-be82-a1c2e8ab1f2a-master.m3u8https://peertube.laas.fr/videos/embed/db59zo1jzeFAKGQiAEbv9s750152026-02-13T02:04:31.161ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/wPijEurxJL77QWD8g7xgvKhttps://peertube.laas.fr/lazy-static/thumbnails/533e662b-9b85-4713-86ee-a7f50a7fc341.jpgPolishing Panda IcePolishing Panda Icehttps://peertube.laas.fr/static/streaming-playlists/hls/f98ccabb-44b8-4ab8-bf41-5407c699d7b1/b28554ea-cd44-473c-967f-bf0c83f81abc-master.m3u8https://peertube.laas.fr/videos/embed/wPijEurxJL77QWD8g7xgvK700172026-02-13T02:17:48.090ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/hvX4CNps8TRKU87WSDX5XGhttps://peertube.laas.fr/lazy-static/thumbnails/bbc8374b-bd1d-491b-91eb-ab10ad52c184.jpgMPPI panda rvizMPPI panda rvizhttps://peertube.laas.fr/static/streaming-playlists/hls/85c0b8b1-ba16-47ab-9c6e-f3d288897fd6/123103ec-b33f-403f-a9a1-50f2a5ed9049-master.m3u8https://peertube.laas.fr/videos/embed/hvX4CNps8TRKU87WSDX5XG940132026-02-15T18:18:47.543ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/5rTSjNmcVbxVddxUhPJyPmhttps://peertube.laas.fr/lazy-static/thumbnails/923408d0-1351-4b4b-9ffd-2eb324c81d5c.jpgPanda Real MPPI pick and placePanda Real MPPI pick and placehttps://peertube.laas.fr/static/streaming-playlists/hls/24021d0c-55ee-44c6-93a0-cea2cbd3d43a/73184f3b-9f51-4c93-8992-db3d199cde21-master.m3u8https://peertube.laas.fr/videos/embed/5rTSjNmcVbxVddxUhPJyPm520122026-02-17T13:07:25.523ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/sCa5mJ7YyU4KPdjxG8fhbDhttps://peertube.laas.fr/lazy-static/thumbnails/12ab3f77-f75d-469f-b481-6955e8d2785d.jpgPanda pick and place mppi disturbPanda pick and place mppi disturbhttps://peertube.laas.fr/static/streaming-playlists/hls/d799f93f-8132-48ee-a90b-8fb35a287409/68a3dc4c-54b2-47b5-830e-30ae69cc6462-master.m3u8https://peertube.laas.fr/videos/embed/sCa5mJ7YyU4KPdjxG8fhbD820172026-02-17T14:12:07.206ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/9WDFjms8GGCbSPYTRs32omhttps://peertube.laas.fr/lazy-static/thumbnails/af44b107-f98b-4252-b6f5-e922cf5afcae.jpgCosmik mppi collision avoidanceCosmik mppi collision avoidancehttps://peertube.laas.fr/static/streaming-playlists/hls/486a7e1f-bf4c-4c06-8223-e7531da57384/635692d1-9657-4716-96a1-ce9328dd2da4-master.m3u8https://peertube.laas.fr/videos/embed/9WDFjms8GGCbSPYTRs32om2210262026-02-18T16:10:00.747ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/s4qQZm1ZCx7zzXvQRHtMfkhttps://peertube.laas.fr/lazy-static/thumbnails/80c531e2-9f62-4a8c-955b-13aaa63d8a8b.jpgCoupled Local and Global World Models for Efficient First Order RLBy Joseph Amigo, Rooholla Khorrambakht, Nicolas Mansard, Ludovic Righetti Artificial and Natural Intelligence Toulouse Institute, Toulouse, France Machines in Motion Laboratory, New York University, USA LAAS-CNRS, Univ. Toulouse, CNRS, Toulouse, France World models offer a promising avenue for more faithfully capturing complex dynamics, including contacts and non-rigidity, as well as complex sensory information, such as visual perception, in situations where standard simulators struggle. However, these models are computationally complex to evaluate, posing a challenge for popular RL approaches that have been successfully used with simulators to solve complex locomotion tasks but yet struggle with manipulation. This paper introduces a method that bypasses simulators entirely, training RL policies inside world models learned from robots' interactions with real environments. At its core, our approach enables policy training with large-scale diffusion models via a novel decoupled first-order gradient (FoG) method: a full-scale world model generates accurate forward trajectories, while a lightweight latent-space surrogate approximates its local dynamics for efficient gradient computation. This coupling of a local and global world model ensures high-fidelity unrolling alongside computationally tractable differentiation. We demonstrate the efficacy of our method on the Push-T manipulation task, where it significantly outperforms PPO in sample efficiency. We further evaluate our approach through an ego-centric object manipulation task with a quadruped. Together, these results demonstrate that learning inside data-driven world models is a promising pathway for solving hard-to-model RL tasks in image space without reliance on hand-crafted physics simulators. https://peertube.laas.fr/static/streaming-playlists/hls/d30825c3-ca2b-4950-b29a-48242371417b/bedb7df2-e03e-48e4-8ff9-922921bff022-master.m3u8https://peertube.laas.fr/videos/embed/s4qQZm1ZCx7zzXvQRHtMfk176092026-02-19T12:27:31.033ZYESMain nmansard channelNOhttps://peertube.laas.fr/w/bEYtSYCHnf8s7rk4SuGqNuhttps://peertube.laas.fr/lazy-static/thumbnails/3e36ea84-7b81-4a54-9be9-18c4f2e0484c.jpgPanda mpc collision not avoidancePanda mpc collision not avoidancehttps://peertube.laas.fr/static/streaming-playlists/hls/566c7512-442c-47d6-98f4-710c60a77268/bf55a564-65bc-4111-bf80-52a628b724a9-master.m3u8https://peertube.laas.fr/videos/embed/bEYtSYCHnf8s7rk4SuGqNu450242026-02-19T19:33:31.013ZYESMain egursoy channelNOhttps://peertube.laas.fr/w/nG3EayYFx8MZFMU9MBbQJYhttps://peertube.laas.fr/lazy-static/thumbnails/ec510136-e236-4276-bc0e-469c4b1c7362.jpgSALLE BLANCHE touraperçu des différentes zones de la salle blanche du LAAShttps://peertube.laas.fr/static/streaming-playlists/hls/afa74cfc-0a57-444e-8dfe-7217037c2f5c/f5bb0321-a5c6-4563-b0f5-c71d39748d83-master.m3u8https://peertube.laas.fr/videos/embed/nG3EayYFx8MZFMU9MBbQJY4020212026-02-20T15:01:14.145ZYESSalle BlancheNOhttps://peertube.laas.fr/w/gzvzY58eq8FJzg2wbrMaXYhttps://peertube.laas.fr/lazy-static/thumbnails/5d52ef29-7504-45b9-90c7-ca254acedc88.jpgfrom articulate-trunk-quadruped (trunk joint fixed) to Go2from articulate-trunk-quadruped (trunk joint fixed) to Go2https://peertube.laas.fr/static/streaming-playlists/hls/7e26db6b-3009-4ec7-a135-1dc93a52f9ca/88148aaf-956e-427c-a4da-31adb7abc265-master.m3u8https://peertube.laas.fr/videos/embed/gzvzY58eq8FJzg2wbrMaXY170132026-03-03T13:11:22.385ZYESMain gpark channelNOhttps://peertube.laas.fr/w/7fmjP9xqmPT3eV8AJ82Fuohttps://peertube.laas.fr/lazy-static/thumbnails/b2c61553-9311-4618-bd0e-877c69ab28ad.jpgH1V2 walk demoH1V2 walk demohttps://peertube.laas.fr/static/streaming-playlists/hls/3297c523-6de7-431f-ba97-4e43a3d1fdc2/5df54846-4d2f-42ab-b259-ffe83605bbde-master.m3u8https://peertube.laas.fr/videos/embed/7fmjP9xqmPT3eV8AJ82Fuo1520212026-03-09T17:02:23.709ZYESMain ldematteis channelNOhttps://peertube.laas.fr/w/1grnJJedad4F5DVBFYLypKhttps://peertube.laas.fr/lazy-static/thumbnails/69c1a43a-d51d-45ad-b5c3-e3eda8245069.jpgCOSMIK-MPPIVideo associated with the IROS Submission for COSMIK-MPPI Title : COSMIK-MPPI: Scaling Constrained Model Predictive Control to Collision Avoidance in Close-Proximity Dynamic Human Environments Authors: Ege Gursoy*, Maxime Sabbah*, Arthur Haffemayer, Joao Cavalcanti Santos, Pietro Noah Crestaz, Vladimir Petrik, Nicolas Mansard, Vincent Bonnet Abstract: Ensuring safe physical interaction between torque-controlled manipulators and humans is essential for deploying robots in everyday environments. Model Predictive Control (MPC) has emerged as a suitable framework thanks to its capacity to handle hard constraints, provide strong guarantees and zero-shot adaptability through predictive reasoning. However, Gradient-Based MPC (GB-MPC) solvers have demonstrated limited performance for collision avoidance in complex environments. Sampling-based approaches such as Model Predictive Path Integral (MPPI) control offer an alternative via stochastic rollouts, but enforcing safety via additive penalties is inherently fragile, as it provides no formal constraint satisfaction guarantees. We propose a collision avoidance framework called COSMIK-MPPI combining MPPI with the the toolbox for human motion estimation RT-COSMIK and the Constraints-as-Terminations transcription, which enforces safety by treating constraint violations as terminal events, without relying on large penalty terms or explicit human motion prediction. The proposed approach is evaluated against state-of-the-art GB-MPC and vanilla MPPI in simulation and on a real manipulator arm. Results show that COSMIK-MPPI achieves a 100\% task success rate with a constant computation time (22 ms) largely outperforming GB-MPC. In simulated infeasible scenarios, COSMIK-MPPI consistently generates collision-free trajectories, contrary to vanilla MPPI. These properties enabled safe execution of complex real-world human–robot interaction tasks in shared workspaces using an affordable markerless human motion estimator, demonstr...https://peertube.laas.fr/static/streaming-playlists/hls/0227cb57-c428-4dec-8579-14cd265db7e1/128ffa1f-6d52-491e-975f-d5bc76739e97-master.m3u8https://peertube.laas.fr/videos/embed/1grnJJedad4F5DVBFYLypK2740162026-03-17T16:34:41.687ZYESMain msabbah channelNOhttps://peertube.laas.fr/w/cWX5ZsdnhNdU55Dei5FZ6Khttps://peertube.laas.fr/lazy-static/thumbnails/87a90d2b-67c1-40f5-8479-e9b931e93464.jpgPhotolithography process step by stepPhotolithography process step by stephttps://peertube.laas.fr/static/streaming-playlists/hls/60c0a306-adea-447f-98a9-f2acf2a0a009/0b4f1c24-6550-43af-b086-c0e277b70e42-master.m3u8https://peertube.laas.fr/videos/embed/cWX5ZsdnhNdU55Dei5FZ6K3070202026-03-24T16:24:48.953ZYESSalle BlancheNOhttps://peertube.laas.fr/w/vbeQ2woUsKeS4RSAKrSqafhttps://peertube.laas.fr/lazy-static/thumbnails/53773cc1-8631-4509-ae6d-0446c21b57b3.jpgPractical SEM Introduction - Introduction à la microscopie électronique à balayage (MEB)A regarder avant de suivre le cours pratique en présentiel - To see before the SEM traininghttps://peertube.laas.fr/static/streaming-playlists/hls/ec46fb0d-4c4c-4114-8987-87f9ca36a238/d4a82eed-0b14-41f0-93a5-c66cd170fa65-master.m3u8https://peertube.laas.fr/videos/embed/vbeQ2woUsKeS4RSAKrSqaf534002026-04-03T09:21:38.023ZYESMain breig channelNOhttps://peertube.laas.fr/c/matthieu_channel/videoshttps://peertube.laas.fr/c/mhtest/videoshttps://peertube.laas.fr/c/gsaurel_channel/videoshttps://peertube.laas.fr/c/yriou_channel/videoshttps://peertube.laas.fr/c/skleff_channel/videoshttps://peertube.laas.fr/c/mfourmy_channel/videoshttps://peertube.laas.fr/c/tcorberes_channel/videoshttps://peertube.laas.fr/c/tnoel_channel/videoshttps://peertube.laas.fr/c/edantec_channel/videoshttps://peertube.laas.fr/c/nramuzat_channel/videoshttps://peertube.laas.fr/c/jchemin_channel/videoshttps://peertube.laas.fr/c/nmansard_channel/videoshttps://peertube.laas.fr/c/paleziart_channel/videoshttps://peertube.laas.fr/c/tflayols_channel/videoshttps://peertube.laas.fr/c/anicolin_channel/videoshttps://peertube.laas.fr/c/florent_channel/videoshttps://peertube.laas.fr/c/terrinet/videoshttps://peertube.laas.fr/c/gepetto_phd/videoshttps://peertube.laas.fr/c/ostasse_channel/videoshttps://peertube.laas.fr/c/mlpieruc_channel/videoshttps://peertube.laas.fr/c/prouanet_channel/videoshttps://peertube.laas.fr/c/rosconfr2021/videoshttps://peertube.laas.fr/c/nvilla_channel/videoshttps://peertube.laas.fr/c/aparag_channel/videoshttps://peertube.laas.fr/c/societe_de_biomecanique/videoshttps://peertube.laas.fr/c/wjallet_channel/videoshttps://peertube.laas.fr/c/dbury_channel/videoshttps://peertube.laas.fr/c/frisbourg_channel/videoshttps://peertube.laas.fr/c/marido_channel/videoshttps://peertube.laas.fr/c/mjacquet_channel/videoshttps://peertube.laas.fr/c/gsm/videoshttps://peertube.laas.fr/c/rosconfr2022/videoshttps://peertube.laas.fr/c/missions_os_robots/videoshttps://peertube.laas.fr/c/abonnefoy_channel/videoshttps://peertube.laas.fr/c/seminars/videoshttps://peertube.laas.fr/c/archives.robotique/videoshttps://peertube.laas.fr/c/vbatto_channel/videoshttps://peertube.laas.fr/c/ldematteis_channel/videoshttps://peertube.laas.fr/c/msabbah_channel/videoshttps://peertube.laas.fr/c/robotics_lecture/videoshttps://peertube.laas.fr/c/gtethique/videoshttps://peertube.laas.fr/c/lbaudoui_channel/videoshttps://peertube.laas.fr/c/fblanc_channel/videoshttps://peertube.laas.fr/c/ros_2_tutoriels_en_francais/videoshttps://peertube.laas.fr/c/dbaudu_channel/videoshttps://peertube.laas.fr/c/agimus/videoshttps://peertube.laas.fr/c/laas_cnrs_channel/videoshttps://peertube.laas.fr/c/tmartinezf_channel/videoshttps://peertube.laas.fr/c/aws/videoshttps://peertube.laas.fr/c/ahaffemaye_channel/videoshttps://peertube.laas.fr/c/workshop_panache/videoshttps://peertube.laas.fr/c/techday2024/videoshttps://peertube.laas.fr/c/bary_channel/videoshttps://peertube.laas.fr/c/kwojciecho_channel/videoshttps://peertube.laas.fr/c/felix_channel/videoshttps://peertube.laas.fr/c/2rm/videoshttps://peertube.laas.fr/c/c3po/videoshttps://peertube.laas.fr/c/vbonnet_channel/videoshttps://peertube.laas.fr/c/pncrestaz_channel/videoshttps://peertube.laas.fr/c/vlutz_channel/videoshttps://peertube.laas.fr/c/bt2fiacre/videoshttps://peertube.laas.fr/c/romeo/videoshttps://peertube.laas.fr/c/h1_v2_at_gepetto/videoshttps://peertube.laas.fr/c/mnaveau_channel/videoshttps://peertube.laas.fr/c/yariba_channel/videoshttps://peertube.laas.fr/c/lbernat_channel/videoshttps://peertube.laas.fr/c/gpark_channel/videoshttps://peertube.laas.fr/c/egursoy_channel/videoshttps://peertube.laas.fr/c/breig_channel/videoshttps://peertube.laas.fr/c/ecolaas/videoshttps://peertube.laas.fr/c/nmaillet_channel/videoshttps://peertube.laas.fr/c/mkulcsar_channel/videoshttps://peertube.laas.fr/c/salleblanche/videoshttps://peertube.laas.fr/a/matthieu/video-channelshttps://peertube.laas.fr/a/gsaurel/video-channelshttps://peertube.laas.fr/a/yriou/video-channelshttps://peertube.laas.fr/a/skleff/video-channelshttps://peertube.laas.fr/a/mfourmy/video-channelshttps://peertube.laas.fr/a/tcorberes/video-channelshttps://peertube.laas.fr/a/tnoel/video-channelshttps://peertube.laas.fr/a/edantec/video-channelshttps://peertube.laas.fr/a/nramuzat/video-channelshttps://peertube.laas.fr/a/jchemin/video-channelshttps://peertube.laas.fr/a/nmansard/video-channelshttps://peertube.laas.fr/a/paleziart/video-channelshttps://peertube.laas.fr/a/tflayols/video-channelshttps://peertube.laas.fr/a/anicolin/video-channelshttps://peertube.laas.fr/a/florent/video-channelshttps://peertube.laas.fr/a/ostasse/video-channelshttps://peertube.laas.fr/a/mlpieruc/video-channelshttps://peertube.laas.fr/a/prouanet/video-channelshttps://peertube.laas.fr/a/nvilla/video-channelshttps://peertube.laas.fr/a/aparag/video-channelshttps://peertube.laas.fr/a/bwatier/video-channelshttps://peertube.laas.fr/a/wjallet/video-channelshttps://peertube.laas.fr/a/dbury/video-channelshttps://peertube.laas.fr/a/frisbourg/video-channelshttps://peertube.laas.fr/a/marido/video-channelshttps://peertube.laas.fr/a/mjacquet/video-channelshttps://peertube.laas.fr/a/abonnefoy/video-channelshttps://peertube.laas.fr/a/alaborde/video-channelshttps://peertube.laas.fr/a/vbatto/video-channelshttps://peertube.laas.fr/a/ldematteis/video-channelshttps://peertube.laas.fr/a/msabbah/video-channelshttps://peertube.laas.fr/a/fmesnilg/video-channelshttps://peertube.laas.fr/a/lbaudoui/video-channelshttps://peertube.laas.fr/a/fblanc/video-channelshttps://peertube.laas.fr/a/dbaudu/video-channelshttps://peertube.laas.fr/a/laasmedia/video-channelshttps://peertube.laas.fr/a/tmartinezf/video-channelshttps://peertube.laas.fr/a/ahaffemaye/video-channelshttps://peertube.laas.fr/a/simon/video-channelshttps://peertube.laas.fr/a/bary/video-channelshttps://peertube.laas.fr/a/kwojciecho/video-channelshttps://peertube.laas.fr/a/felix/video-channelshttps://peertube.laas.fr/a/vbonnet/video-channelshttps://peertube.laas.fr/a/pncrestaz/video-channelshttps://peertube.laas.fr/a/vlutz/video-channelshttps://peertube.laas.fr/a/mnaveau/video-channelshttps://peertube.laas.fr/a/yariba/video-channelshttps://peertube.laas.fr/a/lbernat/video-channelshttps://peertube.laas.fr/a/gpark/video-channelshttps://peertube.laas.fr/a/egursoy/video-channelshttps://peertube.laas.fr/a/breig/video-channelshttps://peertube.laas.fr/a/isilvain/video-channelshttps://peertube.laas.fr/a/nmaillet/video-channelshttps://peertube.laas.fr/a/mkulcsar/video-channels