Research on optimization of intelligent driving

Trajectory tracking control is one of the most fundamental and important technologies in intelligent vehicles. In response to the problems of low accuracy and poor reliability in current intelligent vehicle path tracking control, the shortest time to complete path tracking of double lane changing was set as the control objective and the optimal control problem for vehicle path tracking is transformed into a nonlinear programming problem using the multi-interval Radau pseudospectral method, and then solved by the sequential quadratic programming method. Through Carsim and MATLAB/Simulink platforms, a joint control simulation of the control algorithm was conducted under double lane changing condition, and finally verified through virtual experiments. The joint simulation and virtual experiment results show that the intelligent vehicle path tracking control algorithm proposed in this paper has good tracking accuracy and driving stability while ensuring the target path tracking performance of the intelligent vehicle. The average values of lateral error and heading error are calculated to be 0.0912 m and 0.0263 rad, indicating that the lateral error and heading error of path tracking are controlled within a small error range during the path tracking process which indicating that the proposed method has high computational accuracy.