Guided neural network and its application to longitudinal dynamics identification of a vehicle

Abstract

In this paper, a modified neural network approach called the Guided Neural Network is proposed for the longitudinal dynamics identification of a vehicle using the well-known gradient descent algorithm. The main contribution of this paper is to take account of the known information about tho system in identification and to enhance the convergence of the identification errors. In this approach, the identification is performed in two stages. First, the Guiding Network is utilized to obtain an approximate dynamic characteristics from the known information such as nonlinear models or expert's experiences. Then the errors between the plant and Guiding Network are compensated using the Compensating Network with thy gradient descent algorithm. With this approach, the convergence speed of the identification error can be enhanced and noire accurate dynamic model can be obtained. The proposed approach is applied to the longitudinal dynamics identification uf ii vehicle and the resultant performance enhancement is given.