Improvement of Steering Performance for Autonomous Vehicles Based on Preview Model

This paper presents an approach to traveling along a reference path and evading obstacles with smooth steering angle for autonomous vehicles when trajectory planner and control run asynchronously. Trajectory in this paper is composed of position and time information, which is produced through decision maker, reference line calculator, trajectory smoother and speed planner. In order to restrain possible oscillation of steering angle, a vehicle dynamic model with preview is applied. It is transformed into a standard form of state space and can be directly used in control. Considering the control runs at a higher frequency than planning, a progression method coordinating these two parts is applied, which bases on time points on the trajectory and matches points with vehicle position after preview. The simulation results demonstrate improvement on the smoothness of steering angle. And vehicle's lateral error on tracking trajectory is kept small.