An Intelligent Navigation Control Approach for Autonomous Unmanned Vehicles via Deep Learning-Enhanced Visual SLAM Framework
For autonomous unmanned vehicles (AUVs), navigation control is an essential concern in academia. Conventionally, existing research works dealt with this issue by resorting to the “Simultaneous Localization and Mapping” (SLAM) technology. Although many SLAM-based approaches had...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10290892/ |
| _version_ | 1797640374246703104 |
|---|---|
| author | Lu Chen Yapeng Liu Panpan Dong Jianwei Liang Aibing Wang |
| author_facet | Lu Chen Yapeng Liu Panpan Dong Jianwei Liang Aibing Wang |
| author_sort | Lu Chen |
| collection | DOAJ |
| description | For autonomous unmanned vehicles (AUVs), navigation control is an essential concern in academia. Conventionally, existing research works dealt with this issue by resorting to the “Simultaneous Localization and Mapping” (SLAM) technology. Although many SLAM-based approaches had been proposed in recent years, they could not mostly perceive semantic characteristics from dynamic visual scenarios. To deal with this challenge, this paper proposes a navigation control approach for AUVs via a deep learning-enhanced visual SLAM framework. Firstly, the commonly used coordinate system in the motion of AUVs is analyzed, and a mathematical description of the circular arc motion of AUVs is formulated. Then, an up-convex curve model is adopted to realize high-accuracy detection of the bilateral lane lines. On the foundation, a yaw angle guidance-based imitation learning framework is utilized to realize navigation control. This well facilitates the analyzing the causal relationship between scenarios and decisions. Some experiments are conducted by simulating real-world urban road scenes, to testify the efficiency of the navigation control for AUVs. The results show that navigation accuracy can be improved by about 5%. |
| first_indexed | 2024-03-11T13:30:56Z |
| format | Article |
| id | doaj.art-df5b20cf1a6c4384a868767bb3fc7c56 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T13:30:56Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-df5b20cf1a6c4384a868767bb3fc7c562023-11-02T23:01:31ZengIEEEIEEE Access2169-35362023-01-011111906711907710.1109/ACCESS.2023.332675410290892An Intelligent Navigation Control Approach for Autonomous Unmanned Vehicles via Deep Learning-Enhanced Visual SLAM FrameworkLu Chen0Yapeng Liu1https://orcid.org/0009-0000-3105-8182Panpan Dong2Jianwei Liang3Aibing Wang4Department of Mechanical and Electrical Engineering, Shijiazhuang College of Applied Technology, Shijiazhuang, ChinaDepartment of Information Science and Engineering, Hebei Vocational College of Labour Relations, Shijiazhuang, ChinaDepartment of Automotive Engineering, Hebei Jiaotong Vocational and Technical College, Shijiazhuang, ChinaDepartment of Mechanical and Electrical Engineering, Shijiazhuang College of Applied Technology, Shijiazhuang, ChinaDepartment of Automotive Engineering, Hebei Jiaotong Vocational and Technical College, Shijiazhuang, ChinaFor autonomous unmanned vehicles (AUVs), navigation control is an essential concern in academia. Conventionally, existing research works dealt with this issue by resorting to the “Simultaneous Localization and Mapping” (SLAM) technology. Although many SLAM-based approaches had been proposed in recent years, they could not mostly perceive semantic characteristics from dynamic visual scenarios. To deal with this challenge, this paper proposes a navigation control approach for AUVs via a deep learning-enhanced visual SLAM framework. Firstly, the commonly used coordinate system in the motion of AUVs is analyzed, and a mathematical description of the circular arc motion of AUVs is formulated. Then, an up-convex curve model is adopted to realize high-accuracy detection of the bilateral lane lines. On the foundation, a yaw angle guidance-based imitation learning framework is utilized to realize navigation control. This well facilitates the analyzing the causal relationship between scenarios and decisions. Some experiments are conducted by simulating real-world urban road scenes, to testify the efficiency of the navigation control for AUVs. The results show that navigation accuracy can be improved by about 5%.https://ieeexplore.ieee.org/document/10290892/Autonomous unmanned vehiclesnavigation controldeep learningvisual SLAM |
| spellingShingle | Lu Chen Yapeng Liu Panpan Dong Jianwei Liang Aibing Wang An Intelligent Navigation Control Approach for Autonomous Unmanned Vehicles via Deep Learning-Enhanced Visual SLAM Framework IEEE Access Autonomous unmanned vehicles navigation control deep learning visual SLAM |
| title | An Intelligent Navigation Control Approach for Autonomous Unmanned Vehicles via Deep Learning-Enhanced Visual SLAM Framework |
| title_full | An Intelligent Navigation Control Approach for Autonomous Unmanned Vehicles via Deep Learning-Enhanced Visual SLAM Framework |
| title_fullStr | An Intelligent Navigation Control Approach for Autonomous Unmanned Vehicles via Deep Learning-Enhanced Visual SLAM Framework |
| title_full_unstemmed | An Intelligent Navigation Control Approach for Autonomous Unmanned Vehicles via Deep Learning-Enhanced Visual SLAM Framework |
| title_short | An Intelligent Navigation Control Approach for Autonomous Unmanned Vehicles via Deep Learning-Enhanced Visual SLAM Framework |
| title_sort | intelligent navigation control approach for autonomous unmanned vehicles via deep learning enhanced visual slam framework |
| topic | Autonomous unmanned vehicles navigation control deep learning visual SLAM |
| url | https://ieeexplore.ieee.org/document/10290892/ |
| work_keys_str_mv | AT luchen anintelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework AT yapengliu anintelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework AT panpandong anintelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework AT jianweiliang anintelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework AT aibingwang anintelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework AT luchen intelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework AT yapengliu intelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework AT panpandong intelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework AT jianweiliang intelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework AT aibingwang intelligentnavigationcontrolapproachforautonomousunmannedvehiclesviadeeplearningenhancedvisualslamframework |