Trajectory Tracking Control Of Unmanned Vehicles Based On Neural Network

As a highly intelligent product of many high-tech integration,unmanned vehicles are not only the future development direction of the vehicle industry,but also an important way to solve traffic congestion and improve travel safety.The trajectory tracking control of the unmanned vehicle is related to whether the vehicle can travel according to the desired trajectory,ensuring the accuracy,safety and stability of the vehicle.In this paper,the neural network method is used to study the longitudinal and lateral dynamics control of vehicles.The vertical,horizontal and integrated control systems are designed to compensate for the shortcomings of the single control method in solving complex control problems.Based on the requirements of unmanned vehicle control,after some simplifications,the vehicle longitudinal dynamics model is established,and the longitudinal simulation model is constructed by combining the vehicle transmission system dynamics model.The vehicle two-degree-of-freedom lateral dynamic model is established.The horizontal simulation model is constructed according to the relative positional relationship between the vehicle and the desired trajectory.Considering the longitudinal and lateral coupling of the vehicle,the horizontal and vertical integrated control system model of the driverless vehicle is constructed.A PID controller based on BP neural network is designed.Taking the vehicle speed as the system input and the three parameters of the PID controller as the output,the control parameters of the PID controller are adjusted and optimized in real time through the self-learning of the BP neural network.The simulation results are carried out in MATLAB/Simulink.A fuzzy controller based on BP neural network is designed.Taking the distance error and direction error as the input of the controller and the wheel rotation angle as the output,the vehicle fuzzy control rules are continuously updated by the neural network to improve the control effect.The simulation results are carried out in MATLAB/Simulink.In order to verify the comprehensive control effect of the longitudinal and lateral controllers,the vehicle horizontal and vertical integrated control system was designed with the vehicle speed as the coupling point.The joint simulation was carried out in combination with MATLAB/Simulink and Carsim.