Learning to guide task and motion planning using score-space representation
In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to predict, how to represent a planning problem instance, and how...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publications
2021
|
| Online Access: | https://hdl.handle.net/1721.1/129975 |
| _version_ | 1811074858972348416 |
|---|---|
| author | Kim, Beomjoon Wang, Zi Kaelbling, Leslie P Lozano-Pérez, Tomás |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Kim, Beomjoon Wang, Zi Kaelbling, Leslie P Lozano-Pérez, Tomás |
| author_sort | Kim, Beomjoon |
| collection | MIT |
| description | In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to predict, how to represent a planning problem instance, and how to transfer knowledge from one problem instance to another. We propose a method that predicts constraints on the search space based on a generic representation of a planning problem instance, called score-space, where we represent a problem instance in terms of the performance of a set of solutions attempted so far. Using this representation, we transfer knowledge, in the form of constraints, from previous problems based on the similarity in score-space. We design a sequential algorithm that efficiently predicts these constraints, and evaluate it in three different challenging task and motion planning problems. Results indicate that our approach performs orders of magnitudes faster than an unguided planner. |
| first_indexed | 2024-09-23T09:56:31Z |
| format | Article |
| id | mit-1721.1/129975 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T09:56:31Z |
| publishDate | 2021 |
| publisher | SAGE Publications |
| record_format | dspace |
| spelling | mit-1721.1/1299752022-09-30T17:53:35Z Learning to guide task and motion planning using score-space representation Kim, Beomjoon Wang, Zi Kaelbling, Leslie P Lozano-Pérez, Tomás Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to predict, how to represent a planning problem instance, and how to transfer knowledge from one problem instance to another. We propose a method that predicts constraints on the search space based on a generic representation of a planning problem instance, called score-space, where we represent a problem instance in terms of the performance of a set of solutions attempted so far. Using this representation, we transfer knowledge, in the form of constraints, from previous problems based on the similarity in score-space. We design a sequential algorithm that efficiently predicts these constraints, and evaluate it in three different challenging task and motion planning problems. Results indicate that our approach performs orders of magnitudes faster than an unguided planner. 2021-02-23T16:28:16Z 2021-02-23T16:28:16Z 2019-05 2020-12-22T16:33:45Z Article http://purl.org/eprint/type/JournalArticle 0278-3649 1741-3176 https://hdl.handle.net/1721.1/129975 Kim, Beomjoon et al. "Learning to guide task and motion planning using score-space representation." International Journal of Robotics Research 38, 7 (June 2019): 793-812 © 2019 The Author(s) en http://dx.doi.org/10.1177/0278364919848837 International Journal of Robotics Research Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf SAGE Publications arXiv |
| spellingShingle | Kim, Beomjoon Wang, Zi Kaelbling, Leslie P Lozano-Pérez, Tomás Learning to guide task and motion planning using score-space representation |
| title | Learning to guide task and motion planning using score-space representation |
| title_full | Learning to guide task and motion planning using score-space representation |
| title_fullStr | Learning to guide task and motion planning using score-space representation |
| title_full_unstemmed | Learning to guide task and motion planning using score-space representation |
| title_short | Learning to guide task and motion planning using score-space representation |
| title_sort | learning to guide task and motion planning using score space representation |
| url | https://hdl.handle.net/1721.1/129975 |
| work_keys_str_mv | AT kimbeomjoon learningtoguidetaskandmotionplanningusingscorespacerepresentation AT wangzi learningtoguidetaskandmotionplanningusingscorespacerepresentation AT kaelblinglesliep learningtoguidetaskandmotionplanningusingscorespacerepresentation AT lozanopereztomas learningtoguidetaskandmotionplanningusingscorespacerepresentation |