Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM
Multi-robot SLAM systems in GPS-denied environments require loop closures to maintain a drift-free centralized map. With an increasing number of robots and size of the environment, checking and computing the transformation for all the loop closure candidates becomes computationally infeasible. In...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2022
|
| Online Access: | https://hdl.handle.net/1721.1/145304 |
| _version_ | 1826190612399915008 |
|---|---|
| author | Denniston, Christopher E Chang, Yun Reinke, Andrzej Ebadi, Kamak Sukhatme, Gaurav S Carlone, Luca Morrell, Benjamin Agha-mohammadi, Ali-akbar |
| author2 | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems |
| author_facet | Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Denniston, Christopher E Chang, Yun Reinke, Andrzej Ebadi, Kamak Sukhatme, Gaurav S Carlone, Luca Morrell, Benjamin Agha-mohammadi, Ali-akbar |
| author_sort | Denniston, Christopher E |
| collection | MIT |
| description | Multi-robot SLAM systems in GPS-denied environments require loop closures to
maintain a drift-free centralized map. With an increasing number of robots and
size of the environment, checking and computing the transformation for all the
loop closure candidates becomes computationally infeasible. In this work, we
describe a loop closure module that is able to prioritize which loop closures
to compute based on the underlying pose graph, the proximity to known beacons,
and the characteristics of the point clouds. We validate this system in the
context of the DARPA Subterranean Challenge and on numerous challenging
underground datasets and demonstrate the ability of this system to generate and
maintain a map with low error. We find that our proposed techniques are able to
select effective loop closures which results in 51% mean reduction in median
error when compared to an odometric solution and 75% mean reduction in median
error when compared to a baseline version of this system with no
prioritization. We also find our proposed system is able to find a lower error
in the mission time of one hour when compared to a system that processes every
possible loop closure in four and a half hours. The code and dataset for this
work can be found https://github.com/NeBula-Autonomy/LAMP |
| first_indexed | 2024-09-23T08:43:02Z |
| format | Article |
| id | mit-1721.1/145304 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:43:02Z |
| publishDate | 2022 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1453042023-01-30T21:20:15Z Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM Denniston, Christopher E Chang, Yun Reinke, Andrzej Ebadi, Kamak Sukhatme, Gaurav S Carlone, Luca Morrell, Benjamin Agha-mohammadi, Ali-akbar Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Multi-robot SLAM systems in GPS-denied environments require loop closures to maintain a drift-free centralized map. With an increasing number of robots and size of the environment, checking and computing the transformation for all the loop closure candidates becomes computationally infeasible. In this work, we describe a loop closure module that is able to prioritize which loop closures to compute based on the underlying pose graph, the proximity to known beacons, and the characteristics of the point clouds. We validate this system in the context of the DARPA Subterranean Challenge and on numerous challenging underground datasets and demonstrate the ability of this system to generate and maintain a map with low error. We find that our proposed techniques are able to select effective loop closures which results in 51% mean reduction in median error when compared to an odometric solution and 75% mean reduction in median error when compared to a baseline version of this system with no prioritization. We also find our proposed system is able to find a lower error in the mission time of one hour when compared to a system that processes every possible loop closure in four and a half hours. The code and dataset for this work can be found https://github.com/NeBula-Autonomy/LAMP 2022-09-07T18:16:41Z 2022-09-07T18:16:41Z 2022-10 2022-09-07T18:10:30Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/145304 Denniston, Christopher E, Chang, Yun, Reinke, Andrzej, Ebadi, Kamak, Sukhatme, Gaurav S et al. 2022. "Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM." IEEE Robotics and Automation Letters, 7 (4). en 10.1109/lra.2022.3191156 IEEE Robotics and Automation Letters Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) arXiv |
| spellingShingle | Denniston, Christopher E Chang, Yun Reinke, Andrzej Ebadi, Kamak Sukhatme, Gaurav S Carlone, Luca Morrell, Benjamin Agha-mohammadi, Ali-akbar Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM |
| title | Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM |
| title_full | Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM |
| title_fullStr | Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM |
| title_full_unstemmed | Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM |
| title_short | Loop Closure Prioritization for Efficient and Scalable Multi-Robot SLAM |
| title_sort | loop closure prioritization for efficient and scalable multi robot slam |
| url | https://hdl.handle.net/1721.1/145304 |
| work_keys_str_mv | AT dennistonchristophere loopclosureprioritizationforefficientandscalablemultirobotslam AT changyun loopclosureprioritizationforefficientandscalablemultirobotslam AT reinkeandrzej loopclosureprioritizationforefficientandscalablemultirobotslam AT ebadikamak loopclosureprioritizationforefficientandscalablemultirobotslam AT sukhatmegauravs loopclosureprioritizationforefficientandscalablemultirobotslam AT carloneluca loopclosureprioritizationforefficientandscalablemultirobotslam AT morrellbenjamin loopclosureprioritizationforefficientandscalablemultirobotslam AT aghamohammadialiakbar loopclosureprioritizationforefficientandscalablemultirobotslam |