This paper suggests a Q-learning technique for designing guide-path networks for automated guided vehicle systems. This study uses the total travel time as the decision criteria for constructing guide-path layouts. The Q-learning technique is applied to the estimation of the travel time of vehicles on each segment of the guide-path. Computational experiments were performed to evaluate the performance of the proposed algorithm. The simulation results showed that the proposed algorithm is superior to Kim and Tanchoco's (1993) in terms of average travel time, interference time, and number of deliveries.
- Automated guided vehicle system
- Beam search
- Guide-path network design
ASJC Scopus subject areas
- Computer Science(all)