Author_Institution :
Fac. of Inf. Sci. & Technol., Osaka Inst. of Technol., Osaka, Japan
Abstract :
This paper addresses scheduling problems on the material handling operation at marine container-yard terminals. The layout, removal order and removal destination of containers are simultaneously optimized in order to reduce the waiting time for a vessel. The schedule of container-movements is derived by autonomous learning method based on a new learning model considering container-groups and corresponding Q-Learning algorithm. In the proposed method, the layout and movements of containers are described based on the Markov decision process (MDP), and a state is represented by a container-layout with a selection of a container to be removed or a selection of destination on where the removed container are placed. Then, a state transition arises from a container-movement, a selection of container-destination, or a selection of container to be removed. Only the container-movement takes a cost, and a series of container-movements with selections of destination and order of containers is evaluated by a total amount of costs. As a consequent, the total amount of costs reflects the number of container-movements that is required to achieve desired container-layout.
Keywords :
Markov processes; containerisation; decision theory; learning (artificial intelligence); loading; marine engineering; scheduling; ships; MDP; Markov decision process; Q-learning system; a-priori knowledge; autonomous learning method; container layout; container removal destination; container removal order; group-based container marshalling; marine container-yard terminal; material handling operation; reinforcement learning; scheduling; ship loading; state transition; Containers; Costs; Learning; Loading; Marine technology; Marine vehicles; Materials handling; Materials science and technology; Stacking; Throughput; Block Stacking; Container Transfer Problem; Q-Learning; Reinforcement Learning; Scheduling;
