Deep Reinforcement Learning for Overtaking Decision-Making and Planning of Autonomous Vehicles

Aihaiti, Ailipaer; Arvin, Farshad; Hu, Junyan

Abstract

The safe overtaking of autonomous vehicles has become an important focus in recent robotics and AI research. Considering the scenario of overtaking with oncoming vehicles, this paper proposes a hierarchical framework based on deep reinforcement learning to interact with the traffic environment and learn to overtake safely and efficiently. At the high level, an optimized actor-critic network with TRPO deep reinforcement learning algorithm is used to make safe overtaking decisions. At the low level, a reliable lane-changing path planning strategy is employed for motion control. A well-designed reward function is introduced to guide the agent in learning efficient overtaking behaviors. The effectiveness of the proposed framework is demonstrated through simulation experiments.

Citation

Aihaiti, A., Arvin, F., & Hu, J. (2025, March). Deep Reinforcement Learning for Overtaking Decision-Making and Planning of Autonomous Vehicles. Presented at 2025 IEEE International Conference on Industrial Technology, Wuhan, China

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2025 IEEE International Conference on Industrial Technology
• Start Date: Mar 26, 2025
• End Date: Mar 28, 2025
• Acceptance Date: Jan 31, 2025
• Online Publication Date: Apr 22, 2025
• Publication Date: Apr 22, 2025
• Deposit Date: Mar 3, 2025
• Publicly Available Date: Apr 22, 2025
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Series ISSN: 2641-0184
• Book Title: 2025 IEEE International Conference on Industrial Technology (ICIT)
• DOI: https://doi.org/10.1109/ICIT63637.2025.10965305
• Public URL: https://durham-repository.worktribe.com/output/3670739