Motion learning in variable environments using probabilistic flow tubes
Commanding an autonomous system through complex motions at a low level can be tedious or impractical for systems with many degrees of freedom. Allowing an operator to demonstrate the desired motions directly can often enable more intuitive and efficient interaction. Two challenges in the field of le...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2013
|
| Online Access: | http://hdl.handle.net/1721.1/81155 https://orcid.org/0000-0002-1057-3940 |
| _version_ | 1811091246157922304 |
|---|---|
| author | Dong, Shuonan Williams, Brian Charles |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Dong, Shuonan Williams, Brian Charles |
| author_sort | Dong, Shuonan |
| collection | MIT |
| description | Commanding an autonomous system through complex motions at a low level can be tedious or impractical for systems with many degrees of freedom. Allowing an operator to demonstrate the desired motions directly can often enable more intuitive and efficient interaction. Two challenges in the field of learning from demonstration include (1) how to best represent learned motions to accurately reflect a human's intentions, and (2) how to enable learned motions to be easily applicable in new situations. This paper introduces a novel representation of continuous actions called probabilistic flow tubes that can provide flexibility during execution while robustly encoding a human's intended motions. Our approach also automatically determines certain qualitative characteristics of a motion so that these characteristics can be preserved when autonomously executing the motion in a new situation. We demonstrate the effectiveness of our motion learning approach both in a simulated two-dimensional environment and on the All Terrain Hex-Limbed Extra-Terrestrial Explorer (ATHLETE) robot performing object manipulation tasks. |
| first_indexed | 2024-09-23T14:59:23Z |
| format | Article |
| id | mit-1721.1/81155 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:59:23Z |
| publishDate | 2013 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/811552022-09-29T11:53:24Z Motion learning in variable environments using probabilistic flow tubes Dong, Shuonan Williams, Brian Charles Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Dong, Shuonan Williams, Brian Charles Commanding an autonomous system through complex motions at a low level can be tedious or impractical for systems with many degrees of freedom. Allowing an operator to demonstrate the desired motions directly can often enable more intuitive and efficient interaction. Two challenges in the field of learning from demonstration include (1) how to best represent learned motions to accurately reflect a human's intentions, and (2) how to enable learned motions to be easily applicable in new situations. This paper introduces a novel representation of continuous actions called probabilistic flow tubes that can provide flexibility during execution while robustly encoding a human's intended motions. Our approach also automatically determines certain qualitative characteristics of a motion so that these characteristics can be preserved when autonomously executing the motion in a new situation. We demonstrate the effectiveness of our motion learning approach both in a simulated two-dimensional environment and on the All Terrain Hex-Limbed Extra-Terrestrial Explorer (ATHLETE) robot performing object manipulation tasks. United States. Dept. of Defense (National Defense Science and Engineering Graduate Fellowship 32 CFR 168a) United States. National Aeronautics and Space Administration (JPL Strategic University Research Partnership) 2013-09-24T20:41:09Z 2013-09-24T20:41:09Z 2011-05 Article http://purl.org/eprint/type/ConferencePaper 978-1-61284-386-5 http://hdl.handle.net/1721.1/81155 Shuonan Dong, and Brian Williams. “Motion learning in variable environments using probabilistic flow tubes.” In 2011 IEEE International Conference on Robotics and Automation, 1976-1981. Institute of Electrical and Electronics Engineers, 2011. https://orcid.org/0000-0002-1057-3940 en_US http://dx.doi.org/10.1109/ICRA.2011.5980530 2011 IEEE International Conference on Robotics and Automation Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Dong, Shuonan Williams, Brian Charles Motion learning in variable environments using probabilistic flow tubes |
| title | Motion learning in variable environments using probabilistic flow tubes |
| title_full | Motion learning in variable environments using probabilistic flow tubes |
| title_fullStr | Motion learning in variable environments using probabilistic flow tubes |
| title_full_unstemmed | Motion learning in variable environments using probabilistic flow tubes |
| title_short | Motion learning in variable environments using probabilistic flow tubes |
| title_sort | motion learning in variable environments using probabilistic flow tubes |
| url | http://hdl.handle.net/1721.1/81155 https://orcid.org/0000-0002-1057-3940 |
| work_keys_str_mv | AT dongshuonan motionlearninginvariableenvironmentsusingprobabilisticflowtubes AT williamsbriancharles motionlearninginvariableenvironmentsusingprobabilisticflowtubes |