Path following for Autonomous Ground Vehicle Using DDPG Algorithm: A Reinforcement Learning Approach
The potential of autonomous driving technology to revolutionize the transportation industry has attracted significant attention. Path following, a fundamental task in autonomous driving, involves accurately and safely guiding a vehicle along a specified path. Conventional path-following methods ofte...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/11/6847 |
| _version_ | 1797597818952613888 |
|---|---|
| author | Yu Cao Kan Ni Xiongwen Jiang Taiga Kuroiwa Haohao Zhang Takahiro Kawaguchi Seiji Hashimoto Wei Jiang |
| author_facet | Yu Cao Kan Ni Xiongwen Jiang Taiga Kuroiwa Haohao Zhang Takahiro Kawaguchi Seiji Hashimoto Wei Jiang |
| author_sort | Yu Cao |
| collection | DOAJ |
| description | The potential of autonomous driving technology to revolutionize the transportation industry has attracted significant attention. Path following, a fundamental task in autonomous driving, involves accurately and safely guiding a vehicle along a specified path. Conventional path-following methods often rely on rule-based or parameter-tuning aspects, which may not be adaptable to complex and dynamic scenarios. Reinforcement learning (RL) has emerged as a promising approach that can learn effective control policies from experience without prior knowledge of system dynamics. This paper investigates the effectiveness of the Deep Deterministic Policy Gradient (DDPG) algorithm for steering control in ground vehicle path following. The algorithm quickly converges and the trained agent achieves stable and fast path following, outperforming three baseline methods. Additionally, the agent achieves smooth control without excessive actions. These results validate the proposed approach’s effectiveness, which could contribute to the development of autonomous driving technology. |
| first_indexed | 2024-03-11T03:10:50Z |
| format | Article |
| id | doaj.art-b8b074e75bca47cb95a7995f927d349e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T03:10:50Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b8b074e75bca47cb95a7995f927d349e2023-11-18T07:37:31ZengMDPI AGApplied Sciences2076-34172023-06-011311684710.3390/app13116847Path following for Autonomous Ground Vehicle Using DDPG Algorithm: A Reinforcement Learning ApproachYu Cao0Kan Ni1Xiongwen Jiang2Taiga Kuroiwa3Haohao Zhang4Takahiro Kawaguchi5Seiji Hashimoto6Wei Jiang7Program of Intelligence and Control, Cluster of Electronics and Mechanical Engineering, School of Science and Technology, Gunma University, 1-5-1 Tenjin-cho, Kiryu 376-8515, JapanProgram of Intelligence and Control, Cluster of Electronics and Mechanical Engineering, School of Science and Technology, Gunma University, 1-5-1 Tenjin-cho, Kiryu 376-8515, JapanProgram of Intelligence and Control, Cluster of Electronics and Mechanical Engineering, School of Science and Technology, Gunma University, 1-5-1 Tenjin-cho, Kiryu 376-8515, JapanProgram of Intelligence and Control, Cluster of Electronics and Mechanical Engineering, School of Science and Technology, Gunma University, 1-5-1 Tenjin-cho, Kiryu 376-8515, JapanRyomo Systems Co., Ltd., Ota 373-0853, JapanProgram of Intelligence and Control, Cluster of Electronics and Mechanical Engineering, School of Science and Technology, Gunma University, 1-5-1 Tenjin-cho, Kiryu 376-8515, JapanProgram of Intelligence and Control, Cluster of Electronics and Mechanical Engineering, School of Science and Technology, Gunma University, 1-5-1 Tenjin-cho, Kiryu 376-8515, JapanDepartment of Electronic Engineering, Yangzhou University, Yangzhou 225012, ChinaThe potential of autonomous driving technology to revolutionize the transportation industry has attracted significant attention. Path following, a fundamental task in autonomous driving, involves accurately and safely guiding a vehicle along a specified path. Conventional path-following methods often rely on rule-based or parameter-tuning aspects, which may not be adaptable to complex and dynamic scenarios. Reinforcement learning (RL) has emerged as a promising approach that can learn effective control policies from experience without prior knowledge of system dynamics. This paper investigates the effectiveness of the Deep Deterministic Policy Gradient (DDPG) algorithm for steering control in ground vehicle path following. The algorithm quickly converges and the trained agent achieves stable and fast path following, outperforming three baseline methods. Additionally, the agent achieves smooth control without excessive actions. These results validate the proposed approach’s effectiveness, which could contribute to the development of autonomous driving technology.https://www.mdpi.com/2076-3417/13/11/6847autonomous drivingpath followingRLDDPGground vehicle |
| spellingShingle | Yu Cao Kan Ni Xiongwen Jiang Taiga Kuroiwa Haohao Zhang Takahiro Kawaguchi Seiji Hashimoto Wei Jiang Path following for Autonomous Ground Vehicle Using DDPG Algorithm: A Reinforcement Learning Approach Applied Sciences autonomous driving path following RL DDPG ground vehicle |
| title | Path following for Autonomous Ground Vehicle Using DDPG Algorithm: A Reinforcement Learning Approach |
| title_full | Path following for Autonomous Ground Vehicle Using DDPG Algorithm: A Reinforcement Learning Approach |
| title_fullStr | Path following for Autonomous Ground Vehicle Using DDPG Algorithm: A Reinforcement Learning Approach |
| title_full_unstemmed | Path following for Autonomous Ground Vehicle Using DDPG Algorithm: A Reinforcement Learning Approach |
| title_short | Path following for Autonomous Ground Vehicle Using DDPG Algorithm: A Reinforcement Learning Approach |
| title_sort | path following for autonomous ground vehicle using ddpg algorithm a reinforcement learning approach |
| topic | autonomous driving path following RL DDPG ground vehicle |
| url | https://www.mdpi.com/2076-3417/13/11/6847 |
| work_keys_str_mv | AT yucao pathfollowingforautonomousgroundvehicleusingddpgalgorithmareinforcementlearningapproach AT kanni pathfollowingforautonomousgroundvehicleusingddpgalgorithmareinforcementlearningapproach AT xiongwenjiang pathfollowingforautonomousgroundvehicleusingddpgalgorithmareinforcementlearningapproach AT taigakuroiwa pathfollowingforautonomousgroundvehicleusingddpgalgorithmareinforcementlearningapproach AT haohaozhang pathfollowingforautonomousgroundvehicleusingddpgalgorithmareinforcementlearningapproach AT takahirokawaguchi pathfollowingforautonomousgroundvehicleusingddpgalgorithmareinforcementlearningapproach AT seijihashimoto pathfollowingforautonomousgroundvehicleusingddpgalgorithmareinforcementlearningapproach AT weijiang pathfollowingforautonomousgroundvehicleusingddpgalgorithmareinforcementlearningapproach |