Vehicle lane keeping system based on TSK fuzzy extension control

In the traditional lane keeping system, a single control algorithm is used for global-region control, which often results in poor control effect in some control areas. In view of this problem, a control method combining the extension control and Takagi-Sugeno-Kang fuzzy control is proposed for lane keeping system control. The extension control strategy based on the idea of control with area division divides different control regions according to the states of the system, and adopts different control algorithms in different control areas to address the limitation of a single control algorithm. For the randomness and inaccuracy of artificial experience in control domain division, a method for control domain division based on the density distribution of characteristic plane is proposed in this article. In order to further improve and explore the performance of extension control, Takagi-Sugeno-Kang extension controller is designed with Takagi-Sugeno-Kang fuzzy control theory, and the extension control performance is improved when switching among different control algorithms. The proposed control strategy is simulated and tested on the CarSim/Simulink joint simulation platform and the CarSim/LabVIEW hardware-in-loop test bench, respectively. The results show that the proposed control strategy can effectively keep the vehicle near the center line of the lane, and both the lane keeping control accuracy and vehicle stability are improved, which guarantees driving safety and comfort.