关键词: 智能汽车；高速公路；轨迹规划；人工势场算法

Abstract: Improving the stability and safety of intelligent vehicles during lane changes on freeways is one of the core research directions in the field of intelligent transportation systems. This paper takes the lane-changing condition of intelligent vehicles on freeways as the research object, adopts the artificial potential field (APF) algorithm as the basic algorithm for lane-changing trajectory planning, and focuses on improving the repulsive force range of the traditional artificial potential field algorithm. Based on the minimum safe lane-changing distance model integrated with the elliptical vehicle safety contour, a semi-elliptical repulsive force range of the artificial potential field is constructed, and the functional relationship between this repulsive force range and the relative vehicle speed is determined. To verify the effectiveness of the improved method, simulation experiments are carried out in a joint simulation environment of Simulink/CarSim with a model predictive trajectory tracking controller (MPC). The results show that the improved artificial potential field algorithm can safely and effectively plan the lane-changing trajectory of intelligent vehicles on freeways. During the tracking process of the controller, the vehicle state parameters remain stable, which further verifies the effectiveness of the proposed algorithm.

Key words: intelligent vehicle; highway scene; trajectory planning; artificial potential field algorithm