Research on human-like lane-changing control of intelligent vehicles based on extension goodness evaluation

Abstract

In order to improve the trajectory tracking accuracy and passenger comfort for intelligent vehicle lane-changing at medium and high speed, this paper proposes a new control algorithm based on extension evaluation system for intelligent vehicle lane-changing. In this research, firstly, a vehicle-road dynamics model has been developed. In addition, the actual driving trajectory data of skilled drivers are collected by driving simulator, and the lane-changing path planning model is established based on generalized regression neural network (GRNN). Last, in order to improve the tracking ability to the planning path, the trajectory tracking controller is established. A two-layer structure of lateral trajectory tracking control system is designed, in which the upper layer includes two algorithms: (1) PID feedback control based on preview deviation; (2) PID feedforward-feedback control based on the curvature of the path planning by skilled drivers. While the extension goodness evaluation is introduced in the lower layer which is used to evaluate two controllers in upper layer. According to the real-time state of vehicle-road system, the controller output with higher goodness is selected. Finally, the simulation results verify that comparing with the conventional single PID feedback control, the extension goodness evaluation control can effectively improve the passenger comfort while ensuring tracking accuracy.