Adaptive sliding mode fractional‐order control of autonomous underwater vehicles

Abstract This article proposes the design of an adaptive fractional‐order neural network controller based on the backstepping sliding mode control approach for fully actuated 3 degree‐of‐freedom (DOF) autonomous underwater vehicles (AUVs) in the presence of uncertainties and external disturbances. Compared to existing results, the design of an adaptive fractional‐order controller for tracking the desired trajectory of AUV is represented for the first time in this paper. Due to the presence of parametric structural uncertainties, a radial basis function neural network (RBFNN) approximation is employed in combination with adaptive control systems. Furthermore, the robustness of the control law is enhanced against unstructured uncertainties (external disturbances and modeling errors) by employing the ‐modification approach and proving their boundedness. Moreover, the control system stability is analyzed using the fractional Lyapunov approach, demonstrating that all closed‐loop control signals are uniformly bounded. Additionally, the convergence of the Lyapunov variables (tracking error) to a very small neighborhood of zero is proven by adjusting the design parameters of the controller.