Traversability analysis for UGV (unmanned ground vehicle) navigation based on multimodal information
Efficient and safe navigation of Unmanned Ground Vehicles(UGV) in unstructured off-road environments remains a significant challenge due to diverse terrains and highly dynamic scenarios. Traversability analysis presents tremendous potential in addressing such problem by perceiving surroundings and b...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/173932 |
| _version_ | 1811686319058845696 |
|---|---|
| author | Guo, Jiajie |
| author2 | Wang Dan Wei |
| author_facet | Wang Dan Wei Guo, Jiajie |
| author_sort | Guo, Jiajie |
| collection | NTU |
| description | Efficient and safe navigation of Unmanned Ground Vehicles(UGV) in unstructured off-road environments remains a significant challenge due to diverse terrains and highly dynamic scenarios. Traversability analysis presents tremendous potential in addressing such problem by perceiving surroundings and building traversability maps. In this dissertation, we introduce a novel traversability analysis algorithm based on multi-modal information fusion. This algorithm integrates data from LiDAR and cameras to comprehensively understand the environment. Point clouds are utilized to extract geometric features such as flat surfaces, slopes and depressions, while semantic segmentation of images enables the identification of various terrains as well as dynamic objects. These two types of information will be effectively fused and integrated to generate a real-time traversability map, which is dynamically insensitive. To verify the performance and effectiveness, the algorithm has been deployed on a UGV where MMDeploy Toolbox is used to accelerate the inference speed of the segmentation model and maintain the data fusion frequency at around 10 Hz. Extensive experiments conducted on campus showcased the algorithm's robustness in such environment with diverse terrains and dynamic objects. |
| first_indexed | 2024-10-01T04:58:31Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/173932 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:58:31Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1739322024-03-08T15:43:54Z Traversability analysis for UGV (unmanned ground vehicle) navigation based on multimodal information Guo, Jiajie Wang Dan Wei School of Electrical and Electronic Engineering EDWWANG@ntu.edu.sg Engineering Multi-modal perception Traversability mapping Efficient and safe navigation of Unmanned Ground Vehicles(UGV) in unstructured off-road environments remains a significant challenge due to diverse terrains and highly dynamic scenarios. Traversability analysis presents tremendous potential in addressing such problem by perceiving surroundings and building traversability maps. In this dissertation, we introduce a novel traversability analysis algorithm based on multi-modal information fusion. This algorithm integrates data from LiDAR and cameras to comprehensively understand the environment. Point clouds are utilized to extract geometric features such as flat surfaces, slopes and depressions, while semantic segmentation of images enables the identification of various terrains as well as dynamic objects. These two types of information will be effectively fused and integrated to generate a real-time traversability map, which is dynamically insensitive. To verify the performance and effectiveness, the algorithm has been deployed on a UGV where MMDeploy Toolbox is used to accelerate the inference speed of the segmentation model and maintain the data fusion frequency at around 10 Hz. Extensive experiments conducted on campus showcased the algorithm's robustness in such environment with diverse terrains and dynamic objects. Master's degree 2024-03-07T01:42:15Z 2024-03-07T01:42:15Z 2023 Thesis-Master by Coursework Guo, J. (2023). Traversability analysis for UGV (unmanned ground vehicle) navigation based on multimodal information. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/173932 https://hdl.handle.net/10356/173932 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering Multi-modal perception Traversability mapping Guo, Jiajie Traversability analysis for UGV (unmanned ground vehicle) navigation based on multimodal information |
| title | Traversability analysis for UGV (unmanned ground vehicle) navigation based on multimodal information |
| title_full | Traversability analysis for UGV (unmanned ground vehicle) navigation based on multimodal information |
| title_fullStr | Traversability analysis for UGV (unmanned ground vehicle) navigation based on multimodal information |
| title_full_unstemmed | Traversability analysis for UGV (unmanned ground vehicle) navigation based on multimodal information |
| title_short | Traversability analysis for UGV (unmanned ground vehicle) navigation based on multimodal information |
| title_sort | traversability analysis for ugv unmanned ground vehicle navigation based on multimodal information |
| topic | Engineering Multi-modal perception Traversability mapping |
| url | https://hdl.handle.net/10356/173932 |
| work_keys_str_mv | AT guojiajie traversabilityanalysisforugvunmannedgroundvehiclenavigationbasedonmultimodalinformation |