G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments
In this paper, we propose a generalized grouping and pruning method for RGB-D SLAM in low-dynamic environments. The conventional grouping and pruning methods successfully reject the effect of dynamic objects in pose graph optimization (PGO). However, these methods sometimes fail when high-dynamic ob...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9712275/ |
| _version_ | 1830342529277493248 |
|---|---|
| author | Seungwon Song Hyungtae Lim Sungwook Jung Hyun Myung |
| author_facet | Seungwon Song Hyungtae Lim Sungwook Jung Hyun Myung |
| author_sort | Seungwon Song |
| collection | DOAJ |
| description | In this paper, we propose a generalized grouping and pruning method for RGB-D SLAM in low-dynamic environments. The conventional grouping and pruning methods successfully reject the effect of dynamic objects in pose graph optimization (PGO). However, these methods sometimes fail when high-dynamic objects are dominant in the images captured by RGB-D sensors. Furthermore, once it is determined whether the features from dynamic objects are included in some nodes, the corresponding nodes are entirely removed even though these nodes partially include true constraints, which leads to an inaccurate PGO. To tackle these problems, we propose a novel method with intra-grouping, inter-grouping, and selective pruning, called G2P-SLAM. Accordingly, our method successfully rejects false constraints from dynamic objects selectively, thus preserving true constraints from static objects as many as possible. As experimentally verified on both our own datasets and public datasets, our proposed method shows promising performance compared with the state-of-the-art methods. Furthermore, experimental results corroborate that our G2P-SLAM enables robust PGO in both dynamic and low-dynamic environments. |
| first_indexed | 2024-12-19T21:52:28Z |
| format | Article |
| id | doaj.art-a4ebfbcf2cb6450c9b3824b82fb6a697 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T21:52:28Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a4ebfbcf2cb6450c9b3824b82fb6a6972022-12-21T20:04:22ZengIEEEIEEE Access2169-35362022-01-0110213702138310.1109/ACCESS.2022.31511339712275G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic EnvironmentsSeungwon Song0https://orcid.org/0000-0002-3394-8936Hyungtae Lim1https://orcid.org/0000-0002-7185-4666Sungwook Jung2https://orcid.org/0000-0002-1313-1347Hyun Myung3https://orcid.org/0000-0002-5799-2026School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South KoreaSchool of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South KoreaKorea Electronics Technology Institute (KETI), Seongnam, South KoreaSchool of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South KoreaIn this paper, we propose a generalized grouping and pruning method for RGB-D SLAM in low-dynamic environments. The conventional grouping and pruning methods successfully reject the effect of dynamic objects in pose graph optimization (PGO). However, these methods sometimes fail when high-dynamic objects are dominant in the images captured by RGB-D sensors. Furthermore, once it is determined whether the features from dynamic objects are included in some nodes, the corresponding nodes are entirely removed even though these nodes partially include true constraints, which leads to an inaccurate PGO. To tackle these problems, we propose a novel method with intra-grouping, inter-grouping, and selective pruning, called G2P-SLAM. Accordingly, our method successfully rejects false constraints from dynamic objects selectively, thus preserving true constraints from static objects as many as possible. As experimentally verified on both our own datasets and public datasets, our proposed method shows promising performance compared with the state-of-the-art methods. Furthermore, experimental results corroborate that our G2P-SLAM enables robust PGO in both dynamic and low-dynamic environments.https://ieeexplore.ieee.org/document/9712275/Computer visionmobile robotsrobot vision systemssimultaneous localization and mapping |
| spellingShingle | Seungwon Song Hyungtae Lim Sungwook Jung Hyun Myung G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments IEEE Access Computer vision mobile robots robot vision systems simultaneous localization and mapping |
| title | G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments |
| title_full | G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments |
| title_fullStr | G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments |
| title_full_unstemmed | G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments |
| title_short | G2P-SLAM: Generalized RGB-D SLAM Framework for Mobile Robots in Low-Dynamic Environments |
| title_sort | g2p slam generalized rgb d slam framework for mobile robots in low dynamic environments |
| topic | Computer vision mobile robots robot vision systems simultaneous localization and mapping |
| url | https://ieeexplore.ieee.org/document/9712275/ |
| work_keys_str_mv | AT seungwonsong g2pslamgeneralizedrgbdslamframeworkformobilerobotsinlowdynamicenvironments AT hyungtaelim g2pslamgeneralizedrgbdslamframeworkformobilerobotsinlowdynamicenvironments AT sungwookjung g2pslamgeneralizedrgbdslamframeworkformobilerobotsinlowdynamicenvironments AT hyunmyung g2pslamgeneralizedrgbdslamframeworkformobilerobotsinlowdynamicenvironments |