Research on Motion Modeling and Control of Tracking Car Based on Neural Network

Abstract

In order to solve the problem of path recognition, speed management and tracking control, BP neural network was used to build the motion model of the tracking car. BP neural network has strong nonlinear fitting ability and learning ability. It obtained different connection weight parameters according to different training sets and made the model more simple, accurate and universal. Based on the BP neural network model of the tracking car, the tracking strategy with the fuzzy control algorithm was proposed. Experiment results showed that this method improved the stability and robustness of the intelligent tracking car. Moreover, the BP neural network we used has strong generalization ability and can be applied to different modeling environments.