online read us now
Paper details
Number 3 - September 2021
Volume 31 - 2021
An automated driving strategy generating method based on WGAIL–DDPG
Mingheng Zhang, Xing Wan, Longhui Gang, Xinfei Lv, Zengwen Wu, Zhaoyang Liu
Abstract
Reliability, efficiency and generalization are basic evaluation criteria for a vehicle automated driving system. This paper
proposes an automated driving decision-making method based on the Wasserstein generative adversarial imitation
learning–deep deterministic policy gradient (WGAIL–DDPG(λ)). Here the exact reward function is designed based on the requirements of a vehicle’s driving performance, i.e., safety, dynamic and ride comfort performance. The model’s training efficiency is improved through the proposed imitation learning strategy, and a gain regulator is designed to smooth the transition from imitation to reinforcement phases. Test results show that the proposed decision-making model can generate actions quickly and accurately according to the surrounding environment. Meanwhile, the imitation learning strategy based on expert experience and the gain regulator can effectively improve the training efficiency for the reinforcement learning model. Additionally, an extended test also proves its good adaptability for different driving conditions.
Keywords
automated driving system, deep learning, deep reinforcement learning, imitation learning, deep deterministic policy gradient