Trajectory Tracking of Intelligent Vehicle Using Model Predictive Control Based on Neural-dynamics Optimization

This paper proposes a model predictive control (MPC) scheme based on neural network optimization for trajectory tracking of intelligent vehicles. Firstly, the vehicle kinematics model is linearized to obtain the vehicle kinematic linear tracking error model, which can be used to predict the future movement of the vehicle. The control scheme combining a feedforward controller and a feedback controller is raised. In the objective function, the control increment constraint and relaxation factor are considered, thereby ensuring the smoothness of the trajectory. The MPC optimization can be iteratively transformed into a quadratic programming problem with inequality constraints, then it can be solved online using primal dual neural network. Finally, the effectiveness and stability of the control strategy are proved through experiments.