Lane-keeping System of Intelligent Vehicles Based on Extension Switching Control Method

In this paper, to solve the problem of intelligent vehicles having low control precision on a roadway with a large curvature, an intelligent vehicle lane-keeping control system based on the theory of extension switching control is proposed. The lane-keeping system comprises two parts-an upper extension controller and a bottom controller. In the upper extension controller, vehicle position information and road curvature information is obtained through the lane line detection method. The lateral position deviation at the preview point and the curvature of the road ahead are selected as feature quantities, and the correlation function is solved. According to the correlation function values, the vehicle-road system states are classified into classical domain, extension domain, or non-domain. In the lower-level controller, a proportion-integral-derivative (PID) feedback controller based on lateral position deviation and heading deviation is used in the classical domain, and a PID feedforward-feedback controller based on the curvature of the road ahead is used in the extension domain. When the vehicle in the non-domain, vehicle-road system is in an unstable state and it has difficulty to control the system and takes emergency braking. The two simulation results demonstrate that compared with the single PID feedback control, the lane-keeping control system proposed in this paper effectively suppresses the tracking deviation in the large curvature road condition and improves the precision and reliability of the lane-keeping system for intelligent driving vehicles. © 2019, Editorial Department of China Journal of Highway and Transport. All right reserved.