Search and rescue under the forest canopy using multiple UAVs
© The Author(s) 2020. We present a multi-robot system for GPS-denied search and rescue under the forest canopy. Forests are particularly challenging environments for collaborative exploration and mapping, in large part due to the existence of severe perceptual aliasing which hinders reliable loop cl...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publications
2021
|
| Online Access: | https://hdl.handle.net/1721.1/136167 |
| _version_ | 1811079101963829248 |
|---|---|
| author | Tian, Yulun Liu, Katherine Ok, Kyel Tran, Loc Allen, Danette Roy, Nicholas How, Jonathan P |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Tian, Yulun Liu, Katherine Ok, Kyel Tran, Loc Allen, Danette Roy, Nicholas How, Jonathan P |
| author_sort | Tian, Yulun |
| collection | MIT |
| description | © The Author(s) 2020. We present a multi-robot system for GPS-denied search and rescue under the forest canopy. Forests are particularly challenging environments for collaborative exploration and mapping, in large part due to the existence of severe perceptual aliasing which hinders reliable loop closure detection for mutual localization and map fusion. Our proposed system features unmanned aerial vehicles (UAVs) that perform onboard sensing, estimation, and planning. When communication is available, each UAV transmits compressed tree-based submaps to a central ground station for collaborative simultaneous localization and mapping (CSLAM). To overcome high measurement noise and perceptual aliasing, we use the local configuration of a group of trees as a distinctive feature for robust loop closure detection. Furthermore, we propose a novel procedure based on cycle consistent multiway matching to recover from incorrect pairwise data associations. The returned global data association is guaranteed to be cycle consistent, and is shown to improve both precision and recall compared with the input pairwise associations. The proposed multi-UAV system is validated both in simulation and during real-world collaborative exploration missions at NASA Langley Research Center. |
| first_indexed | 2024-09-23T11:10:04Z |
| format | Article |
| id | mit-1721.1/136167 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:10:04Z |
| publishDate | 2021 |
| publisher | SAGE Publications |
| record_format | dspace |
| spelling | mit-1721.1/1361672023-09-27T17:31:24Z Search and rescue under the forest canopy using multiple UAVs Tian, Yulun Liu, Katherine Ok, Kyel Tran, Loc Allen, Danette Roy, Nicholas How, Jonathan P Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Massachusetts Institute of Technology. Aerospace Controls Laboratory Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science © The Author(s) 2020. We present a multi-robot system for GPS-denied search and rescue under the forest canopy. Forests are particularly challenging environments for collaborative exploration and mapping, in large part due to the existence of severe perceptual aliasing which hinders reliable loop closure detection for mutual localization and map fusion. Our proposed system features unmanned aerial vehicles (UAVs) that perform onboard sensing, estimation, and planning. When communication is available, each UAV transmits compressed tree-based submaps to a central ground station for collaborative simultaneous localization and mapping (CSLAM). To overcome high measurement noise and perceptual aliasing, we use the local configuration of a group of trees as a distinctive feature for robust loop closure detection. Furthermore, we propose a novel procedure based on cycle consistent multiway matching to recover from incorrect pairwise data associations. The returned global data association is guaranteed to be cycle consistent, and is shown to improve both precision and recall compared with the input pairwise associations. The proposed multi-UAV system is validated both in simulation and during real-world collaborative exploration missions at NASA Langley Research Center. 2021-10-27T20:31:12Z 2021-10-27T20:31:12Z 2020 2021-04-30T15:12:37Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/136167 en 10.1177/0278364920929398 International Journal of Robotics Research Creative Commons Attribution 4.0 International license http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf SAGE Publications arXiv |
| spellingShingle | Tian, Yulun Liu, Katherine Ok, Kyel Tran, Loc Allen, Danette Roy, Nicholas How, Jonathan P Search and rescue under the forest canopy using multiple UAVs |
| title | Search and rescue under the forest canopy using multiple UAVs |
| title_full | Search and rescue under the forest canopy using multiple UAVs |
| title_fullStr | Search and rescue under the forest canopy using multiple UAVs |
| title_full_unstemmed | Search and rescue under the forest canopy using multiple UAVs |
| title_short | Search and rescue under the forest canopy using multiple UAVs |
| title_sort | search and rescue under the forest canopy using multiple uavs |
| url | https://hdl.handle.net/1721.1/136167 |
| work_keys_str_mv | AT tianyulun searchandrescueundertheforestcanopyusingmultipleuavs AT liukatherine searchandrescueundertheforestcanopyusingmultipleuavs AT okkyel searchandrescueundertheforestcanopyusingmultipleuavs AT tranloc searchandrescueundertheforestcanopyusingmultipleuavs AT allendanette searchandrescueundertheforestcanopyusingmultipleuavs AT roynicholas searchandrescueundertheforestcanopyusingmultipleuavs AT howjonathanp searchandrescueundertheforestcanopyusingmultipleuavs |