Lane change trajectory planning method for intelligent vehicles considering surrounding risk

Intelligent vehicle trajectory planning is a multi-objective coupling optimization problem with multiple constraints. Rapid generation of collision-free smooth trajectories that meet kinematic and dynamic constraints can improve the safety and comfort of intelligent vehicle lane-changing process. In order to improve the efficiency of trajectory planning, this paper uses the path and speed decoupling method to generate a feasible lane-changing trajectory set. First, the B-spline curve is used to generate a feasible lane-changing path, and then the speed planning is completed based on Dynamic programming (DP) and Quadratic programming (QP). Considering safety, comfort and efficiency, a comprehensive cost function is established, and the trajectory with the smallest cost function is selected as the output target. The safety cost function is based on the theory of driving risk field, and the safety potential energy index is used to evaluate the safety of the trajectory, which can quantify the risk level of the surrounding traffic factors on the whole process of lane-changing. The simulation results show that the proposed method can quickly plan a reasonable trajectory in the lane-changing scene, and can effectively avoid collision with dynamic obstacles while maintaining safety and efficiency.