Adaptive Neural Disturbance Observer Based Nonsingular Fast Terminal Sliding Mode Control for Underwater Robot Manipulators

This paper presents an adaptive neural disturbance observer based nonsingular fast terminal sliding mode (NFTSM) control method for underwater robot manipulators in the presence of external disturbances. Radial basis function (RBF) neural networks are used in the disturbance observer to approximate the unknown external disturbances, which can improve the robustness of the control system. Moreover, an improved reaching law is applied in the NFTSM strategy to quicken the response of input signals in the different control period. Afterward, it can be demonstrated that all the state signals are ultimately bounded via the Lyapunov stability theory. Finally, numerical simulation results are carried out to verify the effectiveness of the proposed method.