Neural‐network steering control of an automated guided vehicle

With the progress in factory automation in industry has come the demand for higher speed drive and performance for an AGV (automated guided vehicle). A new steering control of the AGV by fuzzy control has been proposed to replace the PI control. However, much time is required to investigate the regulations and to adjust the scaling factors for excellent performance in the fuzzy control. In this paper, a new steering control for an AGV based on the neural network using the backpropagation method is proposed. The good steering control results by the fuzzy control are adopted for the teaching signal of the neural network. First, the effect of the number of learning and the learning errors on the steering control results are discussed by computer simulation using the AGV model. Further, the ability of generalization in the turning radius and the traveling speed also are investigated. It becomes clear that the AGV can travel along a designated route provided the neural network learns both the right and left turning at the maximum traveling speed and the minimum turning radius. Then it is proved by an experiment using the AGV constructed for the test that the proposed steering control method is very affective.