{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-articulated-motions-from-visual","title":"Learning Articulated Motions From Visual Demonstration","arxiv_id":"1502.01659","date":"2015-02-05","proceeding":null,"authors":["Sudeep Pillai","Matthew R. Walter","Seth Teller"],"abstract":"Many functional elements of human homes and workplaces consist of rigid\ncomponents which are connected through one or more sliding or rotating\nlinkages. Examples include doors and drawers of cabinets and appliances;\nlaptops; and swivel office chairs. A robotic mobile manipulator would benefit\nfrom the ability to acquire kinematic models of such objects from observation.\nThis paper describes a method by which a robot can acquire an object model by\ncapturing depth imagery of the object as a human moves it through its range of\nmotion. We envision that in future, a machine newly introduced to an\nenvironment could be shown by its human user the articulated objects particular\nto that environment, inferring from these \"visual demonstrations\" enough\ninformation to actuate each object independently of the user.\n  Our method employs sparse (markerless) feature tracking, motion segmentation,\ncomponent pose estimation, and articulation learning; it does not require prior\nobject models. Using the method, a robot can observe an object being exercised,\ninfer a kinematic model incorporating rigid, prismatic and revolute joints,\nthen use the model to predict the object's motion from a novel vantage point.\nWe evaluate the method's performance, and compare it to that of a previously\npublished technique, for a variety of household objects.","url_abs":"http://arxiv.org/abs/1502.01659v1","url_pdf":"http://arxiv.org/pdf/1502.01659v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-articulated-motions-from-visual","repo_url":"https://github.com/wecacuee/articulated-slam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"motion-segmentation","task_name":"Motion Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1502.01659","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}