Dynamic Environments and Robust SLAM: Optimizing Sensor Fusion and Semantics for Wheeled Robots
This paper proposes an approach to enhance the robustness and accuracy of visual simultaneous localization and mapping (SLAM) for ground wheeled mobile robots in dynamic environments. The proposed method incorporates encoder measurements to establish optimization constraints in bundle adjustment. To...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
FRUCT
2023-05-01
|
| Series: | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| Subjects: | |
| Online Access: | https://www.fruct.org/publications/volume-33/fruct33/files/Mah.pdf |
| _version_ | 1797807549256302592 |
|---|---|
| author | Andrey Penkovskiy Jaafar Mahmoud |
| author_facet | Andrey Penkovskiy Jaafar Mahmoud |
| author_sort | Andrey Penkovskiy |
| collection | DOAJ |
| description | This paper proposes an approach to enhance the robustness and accuracy of visual simultaneous localization and mapping (SLAM) for ground wheeled mobile robots in dynamic environments. The proposed method incorporates encoder measurements to establish optimization constraints in bundle adjustment. To further improve robustness, a geometric technique utilizing KMeans clustering with epipolar constraints and the SegNet for semantic segmentation is employed to filter out features detected on moving objects. These modifications are integrated into the state-of-the-art SLAM system ORB-SLAM3 and demonstrate superior accuracy and real-time performance compared to the baseline approach. The effectiveness of the proposed method is demonstrated through multiple OpenLoris and IROS Lifelong SLAM competition scenarios. |
| first_indexed | 2024-03-13T06:24:15Z |
| format | Article |
| id | doaj.art-e6518c4e76534358b4489e3ea3000e7f |
| institution | Directory Open Access Journal |
| issn | 2305-7254 2343-0737 |
| language | English |
| last_indexed | 2024-03-13T06:24:15Z |
| publishDate | 2023-05-01 |
| publisher | FRUCT |
| record_format | Article |
| series | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| spelling | doaj.art-e6518c4e76534358b4489e3ea3000e7f2023-06-09T11:41:51ZengFRUCTProceedings of the XXth Conference of Open Innovations Association FRUCT2305-72542343-07372023-05-0133118519110.23919/FRUCT58615.2023.10143050Dynamic Environments and Robust SLAM: Optimizing Sensor Fusion and Semantics for Wheeled RobotsAndrey Penkovskiy0Jaafar Mahmoud1ITMO UniversityITMO UniversityThis paper proposes an approach to enhance the robustness and accuracy of visual simultaneous localization and mapping (SLAM) for ground wheeled mobile robots in dynamic environments. The proposed method incorporates encoder measurements to establish optimization constraints in bundle adjustment. To further improve robustness, a geometric technique utilizing KMeans clustering with epipolar constraints and the SegNet for semantic segmentation is employed to filter out features detected on moving objects. These modifications are integrated into the state-of-the-art SLAM system ORB-SLAM3 and demonstrate superior accuracy and real-time performance compared to the baseline approach. The effectiveness of the proposed method is demonstrated through multiple OpenLoris and IROS Lifelong SLAM competition scenarios.https://www.fruct.org/publications/volume-33/fruct33/files/Mah.pdfslammobile robotsdynamic environmentsoptimization |
| spellingShingle | Andrey Penkovskiy Jaafar Mahmoud Dynamic Environments and Robust SLAM: Optimizing Sensor Fusion and Semantics for Wheeled Robots Proceedings of the XXth Conference of Open Innovations Association FRUCT slam mobile robots dynamic environments optimization |
| title | Dynamic Environments and Robust SLAM: Optimizing Sensor Fusion and Semantics for Wheeled Robots |
| title_full | Dynamic Environments and Robust SLAM: Optimizing Sensor Fusion and Semantics for Wheeled Robots |
| title_fullStr | Dynamic Environments and Robust SLAM: Optimizing Sensor Fusion and Semantics for Wheeled Robots |
| title_full_unstemmed | Dynamic Environments and Robust SLAM: Optimizing Sensor Fusion and Semantics for Wheeled Robots |
| title_short | Dynamic Environments and Robust SLAM: Optimizing Sensor Fusion and Semantics for Wheeled Robots |
| title_sort | dynamic environments and robust slam optimizing sensor fusion and semantics for wheeled robots |
| topic | slam mobile robots dynamic environments optimization |
| url | https://www.fruct.org/publications/volume-33/fruct33/files/Mah.pdf |
| work_keys_str_mv | AT andreypenkovskiy dynamicenvironmentsandrobustslamoptimizingsensorfusionandsemanticsforwheeledrobots AT jaafarmahmoud dynamicenvironmentsandrobustslamoptimizingsensorfusionandsemanticsforwheeledrobots |