Abstract
The authors proposed the application of fuzzy reasoning to the steering control of automated guided vehicles (AGVs) and achieved the stable control results. Furthermore, we proposed the steering control of AGVs by neural network using the teaching signal of the fuzzy control results. Since it is necessary in this control method to obtain the stable control results by other control methods in advance, it is not practical.
In this paper, a steering control strategy of AGVs is proposed with the successive learning neural network using the auto-tuning function (AT function). The coefficients of the proposed AT function and the initial values of the teaching signal are discussed by the computer simulation. The right and left turning experiments using the AGV built as a trial are implemented and the validity of the AT function is discussed. The excellent traveling control of the AGV is obtained in some trials. Then, the learning of the neural network is almost terminated and after then the excellent traveling lasts. Thus, the proposed AT function is proved to be very available for the successive learning of neural network.
