{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/127345"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/127345","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Integrated perception, planning and feedback control for generalizable robotic manipulation","abstract":"Humans can easily adapt their manipulation skills to unseen objects, new environment and different tasks. However, existing robot manipulators are typically limited to known object instance and skill transferring is challenging. In this thesis, we take a step further by formulating a manipulation framework that can achieve precise, reliable and dexterous manipulation while being generalizable to potentially unknown object instances. To achieve it, we propose key-point affordances, an object representation consists of 3D semantic key-points. This object representation captures task-related geometric information while ignoring irrelevant details, which enables our method to handle unknown objects with potentially large shape variations. We implement perception, planning and feedback control modules on top of key-point affordances and integrate them into a fully functionally perception-to-action manipulation pipeline. Extensive experiments demonstrate our method can reliably accomplish a variety of challenging tasks with never-before seen objects.","abstract_html":"Humans can easily adapt their manipulation skills to unseen objects, new environment and different tasks. However, existing robot manipulators are typically limited to known object instance and skill transferring is challenging. In this thesis, we take a step further by formulating a manipulation framework that can achieve precise, reliable and dexterous manipulation while being generalizable to potentially unknown object instances. To achieve it, we propose key-point affordances, an object representation consists of 3D semantic key-points. This object representation captures task-related geometric information while ignoring irrelevant details, which enables our method to handle unknown objects with potentially large shape variations. We implement perception, planning and feedback control modules on top of key-point affordances and integrate them into a fully functionally perception-to-action manipulation pipeline. Extensive experiments demonstrate our method can reliably accomplish a variety of challenging tasks with never-before seen objects.","abstract_has_math":false,"creators":["Gao, Wei,(Scientist in electrical engineering and computer science)Massachusetts Institute of Technology."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Russ Tedrake."],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020","date_published":"2020","updated_at":"2026-07-22T22:21:01Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/127345","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Russ Tedrake."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Gao, Wei,(Scientist in electrical engineering and computer science)Massachusetts Institute of Technology."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-09-15T21:53:17Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-09-15T21:53:17Z"]},{"key":"dc:date.issued","label":"Date","values":["2020"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/127345"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020","Cataloged from the official PDF of thesis.","Includes bibliographical references (pages 69-75)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Humans can easily adapt their manipulation skills to unseen objects, new environment and different tasks. However, existing robot manipulators are typically limited to known object instance and skill transferring is challenging. In this thesis, we take a step further by formulating a manipulation framework that can achieve precise, reliable and dexterous manipulation while being generalizable to potentially unknown object instances. To achieve it, we propose key-point affordances, an object representation consists of 3D semantic key-points. This object representation captures task-related geometric information while ignoring irrelevant details, which enables our method to handle unknown objects with potentially large shape variations. We implement perception, planning and feedback control modules on top of key-point affordances and integrate them into a fully functionally perception-to-action manipulation pipeline. Extensive experiments demonstrate our method can reliably accomplish a variety of challenging tasks with never-before seen objects."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Integrated perception, planning and feedback control for generalizable robotic manipulation"]}]}],"canonical_facts":{"dc:contributor.advisor":["Russ Tedrake."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Gao, Wei,(Scientist in electrical engineering and computer science)Massachusetts Institute of Technology."],"dc:date.accessioned":["2020-09-15T21:53:17Z"],"dc:date.available":["2020-09-15T21:53:17Z"],"dc:date.issued":["2020"],"dc:description":["Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020","Cataloged from the official PDF of thesis.","Includes bibliographical references (pages 69-75)."],"dc:description.abstract":["Humans can easily adapt their manipulation skills to unseen objects, new environment and different tasks. However, existing robot manipulators are typically limited to known object instance and skill transferring is challenging. In this thesis, we take a step further by formulating a manipulation framework that can achieve precise, reliable and dexterous manipulation while being generalizable to potentially unknown object instances. To achieve it, we propose key-point affordances, an object representation consists of 3D semantic key-points. This object representation captures task-related geometric information while ignoring irrelevant details, which enables our method to handle unknown objects with potentially large shape variations. We implement perception, planning and feedback control modules on top of key-point affordances and integrate them into a fully functionally perception-to-action manipulation pipeline. Extensive experiments demonstrate our method can reliably accomplish a variety of challenging tasks with never-before seen objects."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/127345"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Integrated perception, planning and feedback control for generalizable robotic manipulation"],"dc:type":["Thesis"],"thesis:degree_name":["Master"]},"updated_at":"2026-07-22T22:21:01Z"}