Preparation of Papers for IFAC Conferences & Symposia: Research on model predictive control of lane keeping based on particle swarm optimization

Aiming at the problems of large deviation and long calculation time in the process of lane departure, a lane keeping model predictive control (MPC) method based on particle swarm optimization (PSO) is proposed, which uses MPC to effectively controls the vehicle, and uses particle swarm optimization algorithm to optimize the control time domain NP and prediction time domain Nc of MPC, which can reduce the number of iterations of model predictive control. Firstly, the particle swarm optimization algorithm is used to optimize the model predictive control. When the objective function reaches the minimum value, stop the iteration to reduce the amount of calculation; Then, the optimized lane keeping controller is Co-simulated by CarSim and Simulink for testing the control effect. The simulation results show that compared with the other three control methods proposed in this paper, this control method can control the vehicle driving on the lane more accurately, and the control accuracy can be improved by about 16%. In addition, the model predictive control based on particle swarm optimization improves the control accuracy and takes into account the stability of vehicle driving and the smoothness of control.