5A3 A REINFORCEMENT LEARNING FOR MARSHALING OF FREIGHT CARS IN A TRAIN BASED ON THE PROCESSING TIME(Technical session 5A: OS4: Railway scheduling)

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper a new method for generating marshaling plan of freight cars in a train is proposed. In the proposed method, marshaling plans based on the processing time can be obtained by a reinforcement learning system. In order to evaluate the processing time, the total transfer distance of a locomotive and the total movement counts of freight cars are simultaneously considered. The order of movements of freight cars, the position for each removed car, the layout of cars in a train and the number of cars to be moved are simultaneously optimized to achieve minimization of the total processing time for obtaining the desired layout of freight cars for an outbound train. Initially, freight cars are located in a freight yard by the random layout, and they are moved and lined into a main track in a certain desired order in order to assemble an out bound train. Learning algorithm in the proposed method is based on the Q-Learning, and is ap-plied to reflect the processing time that are used to achieve one of the desired layouts in the main track. After adequate autonomous learning, the optimum marshaling plan can be obtained by selecting a series of movements of freight cars that has the best evaluation.

• 一般社団法人日本機械学会の論文
• 2011-07-02

著者

• Hirashima Yoichi

  Faculty of Information Science and Technology, Osaka Institute of Technology

関連論文

• 5A3 A REINFORCEMENT LEARNING FOR MARSHALING OF FREIGHT CARS IN A TRAIN BASED ON THE PROCESSING TIME(Technical session 5A: OS4: Railway scheduling)

スポンサーリンク