A Genetic Fuzzy Controller for Vehicle Automatic Steering Control

This paper presents the design and experimental implementation of a genetic fuzzy controller for automatic steering of a small-scaled vehicle. We first derive a dynamic model of the vehicle via system identification and show that the model exhibits similar characteristics to full-sized vehicles. Subsequently, a stable fuzzy proportional-derivative controller is designed and optimized by genetic algorithms. The control system is transformed into a Lureacute system, and Lyapunov's direct method is used to guarantee the stability of the control system. Experimental studies suggest that the control system is insensitive to parametric uncertainty, load, and disturbances. The performance of the proposed controller is also compared against a conventional proportional derivative (PD) controller. Experimental results confirm that it outperforms the conventional PD controller, particularly in terms of robustness