With the development of artificial intelligence and communication technology, road-vehicle fusion system has become the trend of future traffic development. Nowadays, most proposed researches mainly focus on risk warning and fixed speed guidance. High-precision trajectory planning is required for the operation of autonomous driving vehicles. In this paper, the space-time trajectory map and Frenet space coordinate system of the road are established. Through self-perception and autonomous driving vehicles perception, the perceptual platform of road compares the expected trajectory of autonomous driving vehicles with the current perceived information, analyzes the potential risks that the automatic driving vehicle may face in the future, and completes the trajectory planning of the autonomous driving vehicle based on the Frenet coordinate system and the space-time trajectory map. Traffic scenarios such as sharp turn scene are simulated using ROS and MATLAB. The experimental results show that the trajectory and speed smoothness of the autonomous driving vehicle are improved and the driving safety of the vehicle is enhanced in the road-vehicle sensing cooperative system.

CICTP