Intelligent Land-Vehicle Model Transfer Trajectory Planning Method Based on Deep Reinforcement Learning

• Published in: Sensors (Basel, Switzerland) Vol. 18; no. 9; p. 2905
• Main Authors: Yu, Lingli, Shao, Xuanya, Wei, Yadong, Zhou, Kaijun
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.09.2018; MDPI
• Subjects: Algorithms; Automation; Autonomous vehicles; deep reinforcement learning; Dependence; Dynamic models; Efficiency; end-to-end; Image coding; intelligent driving vehicle; International conferences; Kalman filters; Kinematics; Laboratories; Lateral control; Markov analysis; model transfer; Motion planning; Neural networks; Noise; Robotics; Stability; Teaching methods; Traffic control; Traffic flow; Trajectory control; Trajectory planning; Virtual reality; United States > US; China; end-to-end; model transfer; deep reinforcement learning; intelligent driving vehicle; trajectory planning
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s18092905

To address the problem of model error and tracking dependence in the process of intelligent vehicle motion planning, an intelligent vehicle model transfer trajectory planning method based on deep reinforcement learning is proposed, which is able to obtain an effective control action sequence directly. Firstly, an abstract model of the real environment is extracted. On this basis, a deep deterministic policy gradient (DDPG) and a vehicle dynamic model are adopted to jointly train a reinforcement learning model, and to decide the optimal intelligent driving maneuver. Secondly, the actual scene is transferred to an equivalent virtual abstract scene using a transfer model. Furthermore, the control action and trajectory sequences are calculated according to the trained deep reinforcement learning model. Thirdly, the optimal trajectory sequence is selected according to an evaluation function in the real environment. Finally, the results demonstrate that the proposed method can deal with the problem of intelligent vehicle trajectory planning for continuous input and continuous output. The model transfer method improves the model's generalization performance. Compared with traditional trajectory planning, the proposed method outputs continuous rotation-angle control sequences. Moreover, the lateral control errors are also reduced.