Elastic Tracking Operation Method for High-Speed Railway Using Deep Reinforcement Learning

Abstract

Transportation-related consumer electronics technology has advanced rapidly, particularly for automated train operation on high-speed railways. To maximize transport capacity and meet growing demands, this manuscript proposes a new elastic tracking operation control method, that compresses the tracking interval while maintaining safety. The train operation process is formulated as a Monte Carlo process and the Twin Delayed Deep Deterministic policy gradient (TD3) algorithm is used to generate the basic operation strategy. A three-stage control principle and train tracking operation requirements are taken into account, and an elastic parameter-based train state transition rule is proposed. An improved cuckoo algorithm is then used to determine the elastic parameters for faster and more accurate solution convergence. Our results demonstrate that TD3-TOC is effective in i) improving the stability of the train operation process, ii) reducing the tracking interval, and iii) reducing delay in the case of emergency. In addition, the effectiveness of the elastic interval is demonstrated in experiments.