{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/159141"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/159141","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Learning Diffusion Models to Enable Efficient Sampling for Task and Motion Planning on a Panda Robot","abstract":"A search then sample approach to bilevel planning in the context of task and motion planning is one method of effectively solving multi-step robotics problems. In this planning framework, high-level plans of abstract actions are refined into low-level continuous transitions by sampling controller parameters associated with each action. Efficiently sampling these parameters remains a significant challenge, as exhaustive searches often become computational bottlenecks, especially for tasks requiring complex or multimodal parameter distributions. Moreover, relying on samplers hand-designed by humans is both impractical and limiting. To address these challenges, we propose using diffusion models to learn efficient sampling distributions from demonstrations. By avoiding the limitations of hand-specified and naïve sampling methods, our approach enhances planning efficiency and achieves superior performance across diverse tasks that require learning multimodal parameter distributions to solve successfully.","abstract_html":"A search then sample approach to bilevel planning in the context of task and motion planning is one method of effectively solving multi-step robotics problems. In this planning framework, high-level plans of abstract actions are refined into low-level continuous transitions by sampling controller parameters associated with each action. Efficiently sampling these parameters remains a significant challenge, as exhaustive searches often become computational bottlenecks, especially for tasks requiring complex or multimodal parameter distributions. Moreover, relying on samplers hand-designed by humans is both impractical and limiting. To address these challenges, we propose using diffusion models to learn efficient sampling distributions from demonstrations. By avoiding the limitations of hand-specified and naïve sampling methods, our approach enhances planning efficiency and achieves superior performance across diverse tasks that require learning multimodal parameter distributions to solve successfully.","abstract_has_math":false,"creators":["Johnson, Quincy"],"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":["Kaelbling, Leslie","Mendez-Mendez, Jorge"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02","date_published":"2025-02","updated_at":"2026-07-22T22:20:59Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/159141","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kaelbling, Leslie","Mendez-Mendez, Jorge"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Johnson, Quincy"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-04-14T14:08:27Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-04-14T14:08:27Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-02"]},{"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","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/159141"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["A search then sample approach to bilevel planning in the context of task and motion planning is one method of effectively solving multi-step robotics problems. In this planning framework, high-level plans of abstract actions are refined into low-level continuous transitions by sampling controller parameters associated with each action. Efficiently sampling these parameters remains a significant challenge, as exhaustive searches often become computational bottlenecks, especially for tasks requiring complex or multimodal parameter distributions. Moreover, relying on samplers hand-designed by humans is both impractical and limiting. To address these challenges, we propose using diffusion models to learn efficient sampling distributions from demonstrations. By avoiding the limitations of hand-specified and naïve sampling methods, our approach enhances planning efficiency and achieves superior performance across diverse tasks that require learning multimodal parameter distributions to solve successfully."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Learning Diffusion Models to Enable Efficient Sampling for Task and Motion Planning on a Panda Robot"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kaelbling, Leslie","Mendez-Mendez, Jorge"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Johnson, Quincy"],"dc:date.accessioned":["2025-04-14T14:08:27Z"],"dc:date.available":["2025-04-14T14:08:27Z"],"dc:date.issued":["2025-02"],"dc:description.abstract":["A search then sample approach to bilevel planning in the context of task and motion planning is one method of effectively solving multi-step robotics problems. In this planning framework, high-level plans of abstract actions are refined into low-level continuous transitions by sampling controller parameters associated with each action. Efficiently sampling these parameters remains a significant challenge, as exhaustive searches often become computational bottlenecks, especially for tasks requiring complex or multimodal parameter distributions. Moreover, relying on samplers hand-designed by humans is both impractical and limiting. To address these challenges, we propose using diffusion models to learn efficient sampling distributions from demonstrations. By avoiding the limitations of hand-specified and naïve sampling methods, our approach enhances planning efficiency and achieves superior performance across diverse tasks that require learning multimodal parameter distributions to solve successfully."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/159141"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Learning Diffusion Models to Enable Efficient Sampling for Task and Motion Planning on a Panda Robot"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:20:59Z"}