{"id":831304,"date":"2022-03-03T09:30:48","date_gmt":"2022-03-03T17:30:48","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=831304"},"modified":"2023-01-11T12:34:36","modified_gmt":"2023-01-11T20:34:36","slug":"microsoft-research-iisc-ai-seminar-series-learning-to-walk","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/microsoft-research-iisc-ai-seminar-series-learning-to-walk\/","title":{"rendered":"Learning to Walk"},"content":{"rendered":"<p>Legged locomotion is commonly studied and programmed as a discrete set of structured gait patterns, like walk, trot, gallop. However, studies of children learning to walk (Adolph et al) show that real-world locomotion is often quite unstructured and more like \u201cbouts of intermittent steps\u201d. We have developed a general approach to walking which is built on learning on varied terrains in simulation and then fast online adaptation (fractions of a second) in the real world. This is made possible by our Rapid Motor Adaptation (RMA) algorithm. RMA consists of two components: a base policy and an adaptation module, both of which can be trained in simulation. We thus learn walking policies that are much more flexible and adaptable. In our set-up gaits emerge as a consequence of minimizing energy consumption at different target speeds, consistent with various animal motor studies. We then incrementally add a navigation layer to the robot from onboard cameras and tightly couple it with locomotion via proprioception without retraining the walking policy. This is enabled by the use of additional safety monitors which are trained in simulation to predict the safe walking speed for the robot under varying conditions and also detect collisions which might get missed by the onboard cameras. The planner then uses these to plan a path for the robot in a locomotion aware way. You can see our robot walking at <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/www.youtube.com\/watch?v=nBy1piJrq1A\" target=\"_blank\" rel=\"noopener\">https:\/\/www.youtube.com\/watch?v=nBy1piJrq1A<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>.<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Legged locomotion is commonly studied and programmed as a discrete set of structured gait patterns, like walk, trot, gallop. However, studies of children learning to walk (Adolph et al) show that real-world locomotion is often quite unstructured and more like \u201cbouts of intermittent steps\u201d. We have developed a general approach to walking which is built [&hellip;]<\/p>\n","protected":false},"featured_media":831307,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13561,13556,13562,13552,13554,13553],"msr-video-type":[267237],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-831304","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-algorithms","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-research-area-hardware-devices","msr-research-area-human-computer-interaction","msr-research-area-medical-health-genomics","msr-video-type-microsoft-research-iisc-ai-seminar-series","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/gPJRx2c75NU","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/831304"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":6,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/831304\/revisions"}],"predecessor-version":[{"id":912285,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/831304\/revisions\/912285"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/831307"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=831304"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=831304"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=831304"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=831304"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=831304"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=831304"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}