Sample-Based Methods for Factored Task and Motion Planning
© 2017 MIT Press Journals. All rights reserved. There has been a great deal of progress in developing probabilistically complete methods that move beyond motion planning to multi-modal problems including various forms of task planning. This paper presents a general-purpose formulation of a large cla...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Robotics: Science and Systems Foundation
2021
|
| Online Access: | https://hdl.handle.net/1721.1/137701 |
| _version_ | 1826214248325316608 |
|---|---|
| author | Garrett, Caelan Lozano-Perez, Tomas Kaelbling, Leslie |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Garrett, Caelan Lozano-Perez, Tomas Kaelbling, Leslie |
| author_sort | Garrett, Caelan |
| collection | MIT |
| description | © 2017 MIT Press Journals. All rights reserved. There has been a great deal of progress in developing probabilistically complete methods that move beyond motion planning to multi-modal problems including various forms of task planning. This paper presents a general-purpose formulation of a large class of discrete-time planning problems, with hybrid state and action spaces. The formulation characterizes conditions on the submanifolds in which solutions lie, leading to a characterization of robust feasibility that incorporates dimensionality-reducing constraints. It then connects those conditions to corresponding conditional samplers that are provided as part of a domain specification. We present domain-independent sample-based planning algorithms and show that they are both probabilistically complete and computationally efficient on a set of challenging benchmark problems. |
| first_indexed | 2024-09-23T16:02:29Z |
| format | Article |
| id | mit-1721.1/137701 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T16:02:29Z |
| publishDate | 2021 |
| publisher | Robotics: Science and Systems Foundation |
| record_format | dspace |
| spelling | mit-1721.1/1377012023-02-13T20:53:17Z Sample-Based Methods for Factored Task and Motion Planning Garrett, Caelan Lozano-Perez, Tomas Kaelbling, Leslie Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory © 2017 MIT Press Journals. All rights reserved. There has been a great deal of progress in developing probabilistically complete methods that move beyond motion planning to multi-modal problems including various forms of task planning. This paper presents a general-purpose formulation of a large class of discrete-time planning problems, with hybrid state and action spaces. The formulation characterizes conditions on the submanifolds in which solutions lie, leading to a characterization of robust feasibility that incorporates dimensionality-reducing constraints. It then connects those conditions to corresponding conditional samplers that are provided as part of a domain specification. We present domain-independent sample-based planning algorithms and show that they are both probabilistically complete and computationally efficient on a set of challenging benchmark problems. 2021-11-08T16:28:52Z 2021-11-08T16:28:52Z 2017-07-12 2019-06-04T15:05:33Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137701 Garrett, Caelan, Lozano-Perez, Tomas and Kaelbling, Leslie. 2017. "Sample-Based Methods for Factored Task and Motion Planning." en 10.15607/rss.2017.xiii.039 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Robotics: Science and Systems Foundation MIT web domain |
| spellingShingle | Garrett, Caelan Lozano-Perez, Tomas Kaelbling, Leslie Sample-Based Methods for Factored Task and Motion Planning |
| title | Sample-Based Methods for Factored Task and Motion Planning |
| title_full | Sample-Based Methods for Factored Task and Motion Planning |
| title_fullStr | Sample-Based Methods for Factored Task and Motion Planning |
| title_full_unstemmed | Sample-Based Methods for Factored Task and Motion Planning |
| title_short | Sample-Based Methods for Factored Task and Motion Planning |
| title_sort | sample based methods for factored task and motion planning |
| url | https://hdl.handle.net/1721.1/137701 |
| work_keys_str_mv | AT garrettcaelan samplebasedmethodsforfactoredtaskandmotionplanning AT lozanopereztomas samplebasedmethodsforfactoredtaskandmotionplanning AT kaelblingleslie samplebasedmethodsforfactoredtaskandmotionplanning |