Approach to Semantic Visual SLAM for Bionic Robots Based on Loop Closure Detection with Combinatorial Graph Entropy in Complex Dynamic Scenes
In complex dynamic environments, the performance of SLAM systems on bionic robots is susceptible to interference from dynamic objects or structural changes in the environment. To address this problem, we propose a semantic visual SLAM (vSLAM) algorithm based on loop closure detection with combinator...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/10/7/446 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849734044849274880 |
|---|---|
| author | Dazheng Wang Jingwen Luo |
| author_facet | Dazheng Wang Jingwen Luo |
| author_sort | Dazheng Wang |
| collection | DOAJ |
| description | In complex dynamic environments, the performance of SLAM systems on bionic robots is susceptible to interference from dynamic objects or structural changes in the environment. To address this problem, we propose a semantic visual SLAM (vSLAM) algorithm based on loop closure detection with combinatorial graph entropy. First, in terms of the dynamic feature detection results of YOLOv8-seg, the feature points at the edges of the dynamic object are finely judged by calculating the mean absolute deviation (MAD) of the depth of the pixel points. Then, a high-quality keyframe selection strategy is constructed by combining the semantic information, the average coordinates of the semantic objects, and the degree of variation in the dense region of feature points. Subsequently, the unweighted and weighted graphs of keyframes are constructed according to the distribution of feature points, characterization points, and semantic information, and then a high-performance loop closure detection method based on combinatorial graph entropy is developed. The experimental results show that our loop closure detection approach exhibits higher precision and recall in real scenes compared to the bag-of-words (BoW) model. Compared with ORB-SLAM2, the absolute trajectory accuracy in high-dynamic sequences improved by an average of 97.01%, while the number of extracted keyframes decreased by an average of 61.20%. |
| format | Article |
| id | doaj-art-6a64212097cd4c3ab69853e94592c4b3 |
| institution | DOAJ |
| issn | 2313-7673 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-6a64212097cd4c3ab69853e94592c4b32025-08-20T03:07:54ZengMDPI AGBiomimetics2313-76732025-07-0110744610.3390/biomimetics10070446Approach to Semantic Visual SLAM for Bionic Robots Based on Loop Closure Detection with Combinatorial Graph Entropy in Complex Dynamic ScenesDazheng Wang0Jingwen Luo1School of Information Science and Technology, Yunnan Normal University, Kunming 650500, ChinaSchool of Information Science and Technology, Yunnan Normal University, Kunming 650500, ChinaIn complex dynamic environments, the performance of SLAM systems on bionic robots is susceptible to interference from dynamic objects or structural changes in the environment. To address this problem, we propose a semantic visual SLAM (vSLAM) algorithm based on loop closure detection with combinatorial graph entropy. First, in terms of the dynamic feature detection results of YOLOv8-seg, the feature points at the edges of the dynamic object are finely judged by calculating the mean absolute deviation (MAD) of the depth of the pixel points. Then, a high-quality keyframe selection strategy is constructed by combining the semantic information, the average coordinates of the semantic objects, and the degree of variation in the dense region of feature points. Subsequently, the unweighted and weighted graphs of keyframes are constructed according to the distribution of feature points, characterization points, and semantic information, and then a high-performance loop closure detection method based on combinatorial graph entropy is developed. The experimental results show that our loop closure detection approach exhibits higher precision and recall in real scenes compared to the bag-of-words (BoW) model. Compared with ORB-SLAM2, the absolute trajectory accuracy in high-dynamic sequences improved by an average of 97.01%, while the number of extracted keyframes decreased by an average of 61.20%.https://www.mdpi.com/2313-7673/10/7/446complex dynamic scenesbionic robotsvisual SLAMcombinatorial graph entropyloop closure detection |
| spellingShingle | Dazheng Wang Jingwen Luo Approach to Semantic Visual SLAM for Bionic Robots Based on Loop Closure Detection with Combinatorial Graph Entropy in Complex Dynamic Scenes Biomimetics complex dynamic scenes bionic robots visual SLAM combinatorial graph entropy loop closure detection |
| title | Approach to Semantic Visual SLAM for Bionic Robots Based on Loop Closure Detection with Combinatorial Graph Entropy in Complex Dynamic Scenes |
| title_full | Approach to Semantic Visual SLAM for Bionic Robots Based on Loop Closure Detection with Combinatorial Graph Entropy in Complex Dynamic Scenes |
| title_fullStr | Approach to Semantic Visual SLAM for Bionic Robots Based on Loop Closure Detection with Combinatorial Graph Entropy in Complex Dynamic Scenes |
| title_full_unstemmed | Approach to Semantic Visual SLAM for Bionic Robots Based on Loop Closure Detection with Combinatorial Graph Entropy in Complex Dynamic Scenes |
| title_short | Approach to Semantic Visual SLAM for Bionic Robots Based on Loop Closure Detection with Combinatorial Graph Entropy in Complex Dynamic Scenes |
| title_sort | approach to semantic visual slam for bionic robots based on loop closure detection with combinatorial graph entropy in complex dynamic scenes |
| topic | complex dynamic scenes bionic robots visual SLAM combinatorial graph entropy loop closure detection |
| url | https://www.mdpi.com/2313-7673/10/7/446 |
| work_keys_str_mv | AT dazhengwang approachtosemanticvisualslamforbionicrobotsbasedonloopclosuredetectionwithcombinatorialgraphentropyincomplexdynamicscenes AT jingwenluo approachtosemanticvisualslamforbionicrobotsbasedonloopclosuredetectionwithcombinatorialgraphentropyincomplexdynamicscenes |