Robust Object-based SLAM for High-speed Autonomous Navigation
We present Robust Object-based SLAM for High-speed Autonomous Navigation (ROSHAN), a novel approach to object-level mapping suitable for autonomous navigation. In ROSHAN, we represent objects as ellipsoids and infer their parameters using three sources of information - bounding box detections, image...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/130015 |
| _version_ | 1811071531192680448 |
|---|---|
| author | Ok, Kyel Liu, Katherine Y Frey, Kristoffer M. (Kristoffer Martin) How, Jonathan P 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 Ok, Kyel Liu, Katherine Y Frey, Kristoffer M. (Kristoffer Martin) How, Jonathan P Roy, Nicholas |
| author_sort | Ok, Kyel |
| collection | MIT |
| description | We present Robust Object-based SLAM for High-speed Autonomous Navigation (ROSHAN), a novel approach to object-level mapping suitable for autonomous navigation. In ROSHAN, we represent objects as ellipsoids and infer their parameters using three sources of information - bounding box detections, image texture, and semantic knowledge - to overcome the observability problem in ellipsoid-based SLAM under common forward-translating vehicle motions. Each bounding box provides four planar constraints on an object surface and we add a fifth planar constraint using the texture on the objects along with a semantic prior on the shape of ellipsoids. We demonstrate ROSHAN in simulation where we outperform the baseline, reducing the median shape error by 83% and the median position error by 72% in a forward-moving camera sequence. We demonstrate similar qualitative result on data collected on a fast-moving autonomous quadrotor. |
| first_indexed | 2024-09-23T08:52:39Z |
| format | Article |
| id | mit-1721.1/130015 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:52:39Z |
| publishDate | 2021 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1300152022-09-26T08:55:20Z Robust Object-based SLAM for High-speed Autonomous Navigation Ok, Kyel Liu, Katherine Y Frey, Kristoffer M. (Kristoffer Martin) How, Jonathan P Roy, Nicholas Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Aeronautics and Astronautics We present Robust Object-based SLAM for High-speed Autonomous Navigation (ROSHAN), a novel approach to object-level mapping suitable for autonomous navigation. In ROSHAN, we represent objects as ellipsoids and infer their parameters using three sources of information - bounding box detections, image texture, and semantic knowledge - to overcome the observability problem in ellipsoid-based SLAM under common forward-translating vehicle motions. Each bounding box provides four planar constraints on an object surface and we add a fifth planar constraint using the texture on the objects along with a semantic prior on the shape of ellipsoids. We demonstrate ROSHAN in simulation where we outperform the baseline, reducing the median shape error by 83% and the median position error by 72% in a forward-moving camera sequence. We demonstrate similar qualitative result on data collected on a fast-moving autonomous quadrotor. NASA (Award NNX15AQ50A) DARPA (Contract HR0011-15-C-0110) 2021-03-01T16:34:55Z 2021-03-01T16:34:55Z 2019-08 2019-05 2019-10-28T17:42:59Z Article http://purl.org/eprint/type/ConferencePaper 9781538660270 9781538681763 2577-087X https://hdl.handle.net/1721.1/130015 Ok, Kyel et al. "Robust Object-based SLAM for High-speed Autonomous Navigation." 2019 International Conference on Robotics and Automation, May 2019, Montreal, Canada, Institute of Electrical and Electronics Engineers, August 2019 © 2019 IEEE en http://dx.doi.org/10.1109/icra.2019.8794344 2019 International Conference on Robotics and Automation 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 | Ok, Kyel Liu, Katherine Y Frey, Kristoffer M. (Kristoffer Martin) How, Jonathan P Roy, Nicholas Robust Object-based SLAM for High-speed Autonomous Navigation |
| title | Robust Object-based SLAM for High-speed Autonomous Navigation |
| title_full | Robust Object-based SLAM for High-speed Autonomous Navigation |
| title_fullStr | Robust Object-based SLAM for High-speed Autonomous Navigation |
| title_full_unstemmed | Robust Object-based SLAM for High-speed Autonomous Navigation |
| title_short | Robust Object-based SLAM for High-speed Autonomous Navigation |
| title_sort | robust object based slam for high speed autonomous navigation |
| url | https://hdl.handle.net/1721.1/130015 |
| work_keys_str_mv | AT okkyel robustobjectbasedslamforhighspeedautonomousnavigation AT liukatheriney robustobjectbasedslamforhighspeedautonomousnavigation AT freykristoffermkristoffermartin robustobjectbasedslamforhighspeedautonomousnavigation AT howjonathanp robustobjectbasedslamforhighspeedautonomousnavigation AT roynicholas robustobjectbasedslamforhighspeedautonomousnavigation |