Identification and control of four-wheel-steering vehicles based on neural network

Vehicle dynamics are influenced by various nonlinear factors, such as tire characteristics, road conditions, etc. Hence, it is difficult to represent the vehicle dynamics by means of a two-degrees-of-freedom linear model perfectly. This paper presents a new four-wheel-steering (4WS) control system with a neural network that has the abilities of nonlinear modeling and control. A vehicle model of the RBF network is identified from the vehicle dynamics firstly. Next, the authors design a radial basis function (RBF) network controller with this vehicle model of the RBF network. The effectiveness of the proposed method is demonstrated with computer simulations.