Research on Autonomous Driving Path Planning Technology Based on Reinforcement Learning
DOI:
https://doi.org/10.71222/a9atbq49Keywords:
reinforcement learning, autonomous driving, path planning, Deep Q-Network, A3C algorithmAbstract
Path planning is one of the key technical challenges in the field of autonomous driving. Thanks to the rapid advancement of reinforcement learning (RL) technology in the field of artificial intelligence, research on autonomous driving path planning based on RL is increasingly receiving attention. This study explores the use of reinforcement learning to implement autonomous driving path planning technology, analyzing the needs of multiple aspects such as environmental perception, model construction, obstacle avoidance, and path length optimization. A practical application scheme of reinforcement learning for path planning in different autonomous driving scenarios has been proposed. By comparing reinforcement learning algorithms such as DQN, A3C, PPO, etc., the adaptability and optimization ability of these algorithms in handling complex environments were explained, and the strategy of using multi-agent reinforcement learning for path planning was discussed.
References
1. R. Zhang, J. Yang, Y. Liang, S. Lu, Y. Dong, B. Yang, and L. Zhang, "Navigation for autonomous vehicles via fast-stable and smooth reinforcement learning," Sci. China Technol. Sci., vol. 67, no. 2, pp. 423–434, 2024, doi: 10.1007/s11431-023-2483-x.
2. J. J. Wu, D. F. Song, X. M. Zhang, C. S. Duan, and D. P. Yang, "Multi-objective reinforcement learning-based energy management for fuel cell vehicles considering lifecycle costs," Int. J. Hydrogen Energy, vol. 48, no. 95, pp. 37385–37401, 2023, doi: 10.1016/j.ijhydene.2023.06.145.
3. P. Yan, K. Yu, X. Chao, and Z. Chen, "An online reinforcement learning approach to charging and order-dispatching optimi-zation for an e-hailing electric vehicle fleet," Eur. J. Oper. Res., vol. 310, no. 3, pp. 1218–1233, 2023, doi: 10.1016/j.ejor.2023.03.039.
4. H. Guo, Y. Zhang, L. Chen, and A. A. Khan, “Research on vehicle detection based on improved YOLOv8 network,” arXiv pre-print arXiv:2501.00300, 2024, doi: 10.48550/arXiv.2501.00300.
5. C. Wang, R. Liu, A. Tang, Z. Zhang, and P. Liu, "A reinforcement learning‐based energy management strategy for a battery–ultracapacitor electric vehicle considering temperature effects," Int. J. Circ. Theory Appl., vol. 51, no. 10, pp. 4690–4710, 2023, doi: 10.1002/cta.3656.
6. V. K. T. Mantripragada and R. K. Kumar, "Deep reinforcement learning-based antilock braking algorithm," Vehicle Syst. Dyn., vol. 61, no. 5, pp. 1410–1431, 2023, doi: 10.1080/00423114.2022.2084119.
7. S. Ergün, "A study on multi-agent reinforcement learning for autonomous distribution vehicles," Iran J. Comput. Sci., vol. 6, no. 4, pp. 297–305, 2023, doi: 10.1007/s42044-023-00140-1.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Linfeng Hao (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
