Towards high-speed autonomous navigation of unknown environments
In this paper, we summarize recent research enabling high-speed navigation in unknown environments for dynamic robots that perceive the world through onboard sensors. Many existing solutions to this problem guarantee safety by making the conservative assumption that any unknown portion of the map ma...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
SPIE
2017
|
| Online Access: | http://hdl.handle.net/1721.1/106286 https://orcid.org/0000-0003-3765-2021 https://orcid.org/0000-0002-8293-0492 |
| _version_ | 1811075472483680256 |
|---|---|
| author | Richter, Charles Andrew Roy, Nicholas |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Richter, Charles Andrew Roy, Nicholas |
| author_sort | Richter, Charles Andrew |
| collection | MIT |
| description | In this paper, we summarize recent research enabling high-speed navigation in unknown environments for dynamic robots that perceive the world through onboard sensors. Many existing solutions to this problem guarantee safety by making the conservative assumption that any unknown portion of the map may contain an obstacle, and therefore constrain planned motions to lie entirely within known free space. In this work, we observe that safety constraints may significantly limit performance and that faster navigation is possible if the planner reasons about collision with unobserved obstacles probabilistically. Our overall approach is to use machine learning to approximate the expected costs of collision using the current state of the map and the planned trajectory. Our contribution is to demonstrate fast but safe planning using a learned function to predict future collision probabilities. |
| first_indexed | 2024-09-23T10:06:39Z |
| format | Article |
| id | mit-1721.1/106286 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:06:39Z |
| publishDate | 2017 |
| publisher | SPIE |
| record_format | dspace |
| spelling | mit-1721.1/1062862022-09-30T18:58:27Z Towards high-speed autonomous navigation of unknown environments Richter, Charles Andrew Roy, Nicholas Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Richter, Charles Andrew Roy, Nicholas In this paper, we summarize recent research enabling high-speed navigation in unknown environments for dynamic robots that perceive the world through onboard sensors. Many existing solutions to this problem guarantee safety by making the conservative assumption that any unknown portion of the map may contain an obstacle, and therefore constrain planned motions to lie entirely within known free space. In this work, we observe that safety constraints may significantly limit performance and that faster navigation is possible if the planner reasons about collision with unobserved obstacles probabilistically. Our overall approach is to use machine learning to approximate the expected costs of collision using the current state of the map and the planned trajectory. Our contribution is to demonstrate fast but safe planning using a learned function to predict future collision probabilities. U.S. Army Research Laboratory. Micro Autonomous Systems and Technology Collaborative Technology Alliance 2017-01-09T15:34:19Z 2017-01-09T15:34:19Z 2015-04 Article http://purl.org/eprint/type/ConferencePaper 0277-786X 1996-756x http://hdl.handle.net/1721.1/106286 Richter, Charles, and Nicholas Roy. “Towards High-Speed Autonomous Navigation of Unknown Environments.” Ed. Thomas George, Achyut K. Dutta, and M. Saif Islam. N.p., 2015. 94671P. © 2015 Society of Photo-Optical Instrumentation Engineers (SPIE) https://orcid.org/0000-0003-3765-2021 https://orcid.org/0000-0002-8293-0492 en_US http://dx.doi.org/10.1117/12.2178668 Proceedings of SPIE--the Society of Photo-Optical Instrumentation Engineers, 2015 Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf SPIE SPIE |
| spellingShingle | Richter, Charles Andrew Roy, Nicholas Towards high-speed autonomous navigation of unknown environments |
| title | Towards high-speed autonomous navigation of unknown environments |
| title_full | Towards high-speed autonomous navigation of unknown environments |
| title_fullStr | Towards high-speed autonomous navigation of unknown environments |
| title_full_unstemmed | Towards high-speed autonomous navigation of unknown environments |
| title_short | Towards high-speed autonomous navigation of unknown environments |
| title_sort | towards high speed autonomous navigation of unknown environments |
| url | http://hdl.handle.net/1721.1/106286 https://orcid.org/0000-0003-3765-2021 https://orcid.org/0000-0002-8293-0492 |
| work_keys_str_mv | AT richtercharlesandrew towardshighspeedautonomousnavigationofunknownenvironments AT roynicholas towardshighspeedautonomousnavigationofunknownenvironments |