Intelligent vehicle trajectory tracking based on neural networks sliding mode control

The problem of lateral control in intelligent vehicle trajectory tracking for automated highway system is studied. The article deduced the vehicle's desired yaw rate through real time planning virtual path between the vehicle mass center and prediction aiming point which is planned according to the vehicle's kinematic model and pose error model. Based on the lateral dynamic model of vehicle, radical basis function (RBF) neural networks based sliding mode variable structure trajectory tracking controller is designed. A multi-body dynamics model of vehicle is built in ADAMS/Car. The interactive combination control dynamic simulation between Matlab/Simulink and ADAMS is realized through designing the data interface between Matlab and ADAMS. Simulations were conducted and the results show that the proposed algorithm improves the control precision of the system and improves the tracking performance of the system.