Real-time Dynamic Trajectory Planning for Intelligent Vehicles Based on Quintic Polynomial

Abstract

The trajectory planning of intelligent vehicles is the focus of the research field of intelligent vehicles. In this paper, the vehicle state is analyzed during the lane change process, the trajectory of the intelligent vehicle is planned by using the quintic polynomial, the trajectory optimization function is introduced, the objective function of integrated lane change time and maximum acceleration to improve comfort and passage efficiency is constructed, the lane change trajectory is optimally selected based on particle swarm algorithm, and the lane change trajectory is referenced according to the real-time information provided by the Vehicle to Everything to realize real-time data update in order to the data is updated in real-time to provide timely feedback to the information processing center for re-planning the path when there is an unexpected situation ahead. The simulation results show that the lane change trajectory planning method can solve the problems caused by the change of speed of surrounding vehicles and the sudden intrusion of vehicles in the process of lane change, and can significantly improve the smoothness and safety of the process of lane change.