Multi-model Fuzzy Controller for Vehicle Lane Tracking

A fuzzy-logic-based multi-model lateral controller for vehicle trajectory following is presented. It is designed to control the steering angle based on the lateral deviation and the yaw angle. Firstly, local controllers are designed for four speed regions respectively. Then, by using a weighted integration of the four local outputs through a fusion module, a global control output is obtained so as to ensure the global performance. The multi-model fuzzy controller, which inherits the advantages of both the multi-model control and fuzzy control, can be used for wide range operation of vehicle speed. To verify the robustness and effectiveness of the proposed controller, two simulation tests are carried out using AMESim and Matlab/Simulink. The results from the first simulation show the ability of the proposed controller in different speed operations, and the other test demonstrates that the proposed controller achieves satisfactory results for different curvature of trajectory.