強化学習による無人搬送車の分散型スケジューリング

抄録

In this paper, we propose an autonomous vehicle scheduling schema in large physical distribution terminals publicly used as the next generation wide area physical distribution bases. This schema uses Learning Automaton for vehicles scheduling based on Contract Net Protocol, in order to obtain useful emergent behaviors of agents in the system based on the local decision-making of each agent. The state of the automaton is updated at each instant on the basis of new information that includes the arrival estimation time of vehicles. Each agent estimates the arriaval time of vehicles by using Bayesian learning process. Using traffic simulation, we evaluate the schema in various simulated environments. The result shows the advantage of the schema over when each agent provides the same criteria from the top down, and each agent voluntarily generates criteria via interactions with the environment, playing an individual role in the system.