NEURAL-NETWORK CONTROL FOR AUTOMATIC BRAKING CONTROL-SYSTEM

We have developed an automatic braking control system for automobiles applying a three-layer neural network model. This system enables the v ehicle to decelerate smoothly and to stop at the specified position be hind the vehicle ahead. This paper focuses on the use of the three-lay er neural network model in the automatic braking control system. Becau se vehicle dynamics is varied by the variations in road conditions or vehicle characteristics, it cannot be represented accurately by mathem atical models. According to this reason, the conventional control meth ods, such as proportional integrative derivative (PID) control, cannot achieve satisfactory control performance. Therefore, we have construc ted the neural network adaptive control system based on the feedback e rror learning method. This learning method enables the system to adapt to the changes in road grade and vehicle weight without using any spe cific sensors. Experimental results show satisfactory control performa nce and reveal that the neural network adaptive control system based o n the feedback error learning method is available for the automatic br aking control system.