Academic Journal of Computing & Information Science, 2023, 6(1); doi: 10.25236/AJCIS.2023.060104.
Yu Chen, Juntao Li
School of Information, Beijing Wuzi University, Beijing, 101149, China
Intelligent driving is an important feature of electric vehicles, and automatic lane-changing is an important auxiliary operation in the driving process. It involves complex data such as the external environment, vehicle status, and relationship characteristics of other vehicles. This paper proposes research on automatic lane-changing methods for electric vehicles based on a deep deterministic policy gradient algorithm aiming at the complexity of automatic lane-changing for electric vehicles. First, use the actor-critic model of deep reinforcement learning to realize the design of an automatic lane-changing algorithm. On this basis, the actor-critic model is further improved, and a deep deterministic policy gradient algorithm is proposed and applied to the automatic lane-changing strategy of electric vehicles, which improves the accuracy of automatic lane-changing and thus ensures the safety of vehicle driving.
Intelligent driving; Automatic lane-changing; Deep learning; Actor-critic model; DDPG (Deep Deterministic Policy Gradient)
Yu Chen, Juntao Li. Research on Automatic Lane Changing Method for Electric Vehicles Based on Deep Deterministic Policy Gradient Algorithm. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 1: 19-25. https://doi.org/10.25236/AJCIS.2023.060104.
[1] Xia Q, Duan J, Gao F, et al. Test scenario design for intelligent driving system ensuring coverage and effectiveness[J]. International Journal of Automotive Technology, 2018, 19(4): 751-758.
[2] Duan J, Gao F, He Y. Test scenario generation and optimization technology for intelligent driving systems [J]. IEEE Intelligent Transportation Systems Magazine, 2022, 14(1).
[3] Alhariqi A, Gu Z, Saberi M. Calibration of the intelligent driver model (IDM) with adaptive parameters for mixed autonomy traffic using experimental trajectory data[J]. Transportmetrica B: transport dynamics, 2022, 10(1): 421-440.
[4] Li Y, Li L, Ni D, et al. Automatic Lane-Changing Trajectory Planning: From Self-Optimum to Local-Optimum [J]. IEEE Transactions on Intelligent Transportation Systems, 2022.
[5] Wang Lichao, et al. "A model of lane-changing intention induced by deceleration frequency in an automatic driving environment." Physica A: Statistical Mechanics and its Applications 604 (2022): 127905.
[6] Li, Ning, et al. "Reinforcement learning control method for real‐time hybrid simulation based on deep deterministic policy gradient algorithm." Structural Control and Health Monitoring 29.10 (2022): e3035.