Vehicle Safety Planning Control Method Based on Variable Gauss Safety Field
The existing intelligent vehicle trajectory-planning methods have limitations in terms of efficiency and safety. To overcome these limitations, this paper proposes an automatic driving trajectory-planning method based on a variable Gaussian safety field. Firstly, the time series bird’s-eye view is u...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | World Electric Vehicle Journal |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2032-6653/13/11/203 |
| _version_ | 1827645318183780352 |
|---|---|
| author | Zixuan Zhu Chenglong Teng Yingfeng Cai Long Chen Yubo Lian Hai Wang |
| author_facet | Zixuan Zhu Chenglong Teng Yingfeng Cai Long Chen Yubo Lian Hai Wang |
| author_sort | Zixuan Zhu |
| collection | DOAJ |
| description | The existing intelligent vehicle trajectory-planning methods have limitations in terms of efficiency and safety. To overcome these limitations, this paper proposes an automatic driving trajectory-planning method based on a variable Gaussian safety field. Firstly, the time series bird’s-eye view is used as the input state quantity of the network, which improves the effectiveness of the trajectory planning policy network in extracting the features of the surrounding traffic environment. Then, the policy gradient algorithm is used to generate the planned trajectory of the autonomous vehicle, which improves the planning efficiency. The variable Gaussian safety field is used as the reward function of the trajectory planning part and the evaluation index of the control part, which improves the safety of the reinforcement learning vehicle tracking algorithm. The proposed algorithm is verified using the simulator. The obtained results show that the proposed algorithm has excellent trajectory planning ability in the highway scene and can achieve high safety and high precision tracking control. |
| first_indexed | 2024-03-09T18:33:39Z |
| format | Article |
| id | doaj.art-dbf0a41901fb41c1a7ac6c07de89186e |
| institution | Directory Open Access Journal |
| issn | 2032-6653 |
| language | English |
| last_indexed | 2024-03-09T18:33:39Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | World Electric Vehicle Journal |
| spelling | doaj.art-dbf0a41901fb41c1a7ac6c07de89186e2023-11-24T07:22:01ZengMDPI AGWorld Electric Vehicle Journal2032-66532022-10-01131120310.3390/wevj13110203Vehicle Safety Planning Control Method Based on Variable Gauss Safety FieldZixuan Zhu0Chenglong Teng1Yingfeng Cai2Long Chen3Yubo Lian4Hai Wang5Automotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, ChinaBYD Auto Industry Co., Ltd., Shenzhen 518118, ChinaSchool of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, ChinaAutomotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, ChinaBYD Auto Industry Co., Ltd., Shenzhen 518118, ChinaAutomotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, ChinaThe existing intelligent vehicle trajectory-planning methods have limitations in terms of efficiency and safety. To overcome these limitations, this paper proposes an automatic driving trajectory-planning method based on a variable Gaussian safety field. Firstly, the time series bird’s-eye view is used as the input state quantity of the network, which improves the effectiveness of the trajectory planning policy network in extracting the features of the surrounding traffic environment. Then, the policy gradient algorithm is used to generate the planned trajectory of the autonomous vehicle, which improves the planning efficiency. The variable Gaussian safety field is used as the reward function of the trajectory planning part and the evaluation index of the control part, which improves the safety of the reinforcement learning vehicle tracking algorithm. The proposed algorithm is verified using the simulator. The obtained results show that the proposed algorithm has excellent trajectory planning ability in the highway scene and can achieve high safety and high precision tracking control.https://www.mdpi.com/2032-6653/13/11/203autonomous drivingplanning algorithmvariable Gaussian safety fieldreinforcement learningpolicy gradient |
| spellingShingle | Zixuan Zhu Chenglong Teng Yingfeng Cai Long Chen Yubo Lian Hai Wang Vehicle Safety Planning Control Method Based on Variable Gauss Safety Field World Electric Vehicle Journal autonomous driving planning algorithm variable Gaussian safety field reinforcement learning policy gradient |
| title | Vehicle Safety Planning Control Method Based on Variable Gauss Safety Field |
| title_full | Vehicle Safety Planning Control Method Based on Variable Gauss Safety Field |
| title_fullStr | Vehicle Safety Planning Control Method Based on Variable Gauss Safety Field |
| title_full_unstemmed | Vehicle Safety Planning Control Method Based on Variable Gauss Safety Field |
| title_short | Vehicle Safety Planning Control Method Based on Variable Gauss Safety Field |
| title_sort | vehicle safety planning control method based on variable gauss safety field |
| topic | autonomous driving planning algorithm variable Gaussian safety field reinforcement learning policy gradient |
| url | https://www.mdpi.com/2032-6653/13/11/203 |
| work_keys_str_mv | AT zixuanzhu vehiclesafetyplanningcontrolmethodbasedonvariablegausssafetyfield AT chenglongteng vehiclesafetyplanningcontrolmethodbasedonvariablegausssafetyfield AT yingfengcai vehiclesafetyplanningcontrolmethodbasedonvariablegausssafetyfield AT longchen vehiclesafetyplanningcontrolmethodbasedonvariablegausssafetyfield AT yubolian vehiclesafetyplanningcontrolmethodbasedonvariablegausssafetyfield AT haiwang vehiclesafetyplanningcontrolmethodbasedonvariablegausssafetyfield |