Path-tracking of autonomous vehicles using a novel adaptive robust exponential-like-sliding-mode fuzzy type-2 neural network controller

Structured and unstructured uncertainties together with external disturbances may pose considerable challenges in realizing desired path-tacking and lane keeping of autonomous vehicles. This paper presents a novel robust adaptive indirect control method based on an exponential-like-sliding-mode fuzzy type-2 neural network approach for enhanced path-tracking performance of road autonomous vehicles subject to parametric uncertainties related to vehicle nominal cornering stiffness, road-tire adhesion coefficient, inertial parameters, and forward speed. A hierarchical controller is designed and the stability of the closed-loop system is ensured along with deriving the adaptation laws by employing the Lyapunov stability theorem. The conventional reaching law related to the sliding mode degrades from the system stability and introduces an inherent chattering of the controller input. The convergence law for the sliding surface is adjusted based on a variable exponential sliding manifold to eliminate possible chattering in the buffeting switch zone near the origin. The proposed exponential-like sliding surface guarantees the swift and smooth global asymptotic convergence of the tracking error toward zero. Furthermore, an adaptive look-ahead path-tracking error term is introduced as an auxiliary error criterion to improve the vehicle path-tracking performance. The effectiveness of the proposed controller is verified through Matlab/Simulink–CarSim co-simulations and comparisons with selected reported control methods for two different road maneuvers. The results suggested substantially improved tracking performance by the proposed controller with robustness to withstand against the perturbed parameters and external disturbances.