Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact
Path planning classically focuses on avoiding environmental contact. However, some assembly tasks permit contact through compliance, and such contact may allow for more efficient and reliable solutions under action uncertainty. But, optimal manipulation plans that leverage environmental contact are...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2020
|
| Online Access: | https://hdl.handle.net/1721.1/125865 |
| _version_ | 1826214322378899456 |
|---|---|
| author | Guan, Charlie Vega-Brown, William R Roy, Nicholas |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Guan, Charlie Vega-Brown, William R Roy, Nicholas |
| author_sort | Guan, Charlie |
| collection | MIT |
| description | Path planning classically focuses on avoiding environmental contact. However, some assembly tasks permit contact through compliance, and such contact may allow for more efficient and reliable solutions under action uncertainty. But, optimal manipulation plans that leverage environmental contact are difficult to compute. Environmental contact produces complex kinematics that create difficulties for planning. This complexity is usually addressed by discretization over state and action space, but discretization quickly becomes computationally intractable. To overcome the challenge, we use the insight that only actions on configurations near the contact manifold are likely to involve complex kinematics, while segments of the plan through free space do not. Leveraging this structure can greatly reduce the number of states considered and scales much better with problem complexity. We develop an algorithm based on this idea and show that it performs comparably to full MDP solutions at a fraction of the computational cost. |
| first_indexed | 2024-09-23T16:03:32Z |
| format | Article |
| id | mit-1721.1/125865 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T16:03:32Z |
| publishDate | 2020 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1258652022-10-02T06:02:40Z Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact Guan, Charlie Vega-Brown, William R Roy, Nicholas Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Path planning classically focuses on avoiding environmental contact. However, some assembly tasks permit contact through compliance, and such contact may allow for more efficient and reliable solutions under action uncertainty. But, optimal manipulation plans that leverage environmental contact are difficult to compute. Environmental contact produces complex kinematics that create difficulties for planning. This complexity is usually addressed by discretization over state and action space, but discretization quickly becomes computationally intractable. To overcome the challenge, we use the insight that only actions on configurations near the contact manifold are likely to involve complex kinematics, while segments of the plan through free space do not. Leveraging this structure can greatly reduce the number of states considered and scales much better with problem complexity. We develop an algorithm based on this idea and show that it performs comparably to full MDP solutions at a fraction of the computational cost. 2020-06-18T18:13:47Z 2020-06-18T18:13:47Z 2018-09 2018-05 2019-10-31T13:18:31Z Article http://purl.org/eprint/type/ConferencePaper 9781538630815 https://hdl.handle.net/1721.1/125865 Guan, Charlie et al. "Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact." May 2018, IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, Australia, Institute of Electrical and Electronics Engineers (IEEE), September 2018 © 2018 IEEE en http://dx.doi.org/10.1109/icra.2018.8462696 IEEE International Conference on Robotics and Automation (ICRA) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Guan, Charlie Vega-Brown, William R Roy, Nicholas Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact |
| title | Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact |
| title_full | Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact |
| title_fullStr | Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact |
| title_full_unstemmed | Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact |
| title_short | Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact |
| title_sort | efficient planning for near optimal compliant manipulation leveraging environmental contact |
| url | https://hdl.handle.net/1721.1/125865 |
| work_keys_str_mv | AT guancharlie efficientplanningfornearoptimalcompliantmanipulationleveragingenvironmentalcontact AT vegabrownwilliamr efficientplanningfornearoptimalcompliantmanipulationleveragingenvironmentalcontact AT roynicholas efficientplanningfornearoptimalcompliantmanipulationleveragingenvironmentalcontact |