Lateral Control Method of Tracked Vehicle Based on Backstepping Method and Adaptive Neural Network

To address the problem that traditional control methods usually ignore the fine-grained control of the degree of steering with non-prescribed steering radius, which results in large tracking errors in the control of the tracked vehicle at medium and high speeds, this paper proposes a lateral control method for tracked vehicles based on the backstepping method and adaptive neural networks. Firstly, a transient dynamics model is established for the steering with Non-prescribed steering radius of the tracked vehicle; then a tracking error model is introduced and the backstepping method is used to calculate the target angular velocity at which the position error and heading error converge to zero at the same time; finally, the adaptive neural network is used to track the angular velocity to achieve the control purpose. Simulation results show that the backstepping adaptive neural network control method proposed in this paper has higher control accuracy and lower joystick pull frequency under the path of variable curvature curve type. The overall control effect is significantly better than the PID control method.