Chapter 7 - Adaptive sliding mode control based on local recurrent neural networks for an underwater robot

Abstract

The trajectory tracking control problem of an underwater robot is addressed in this chapter. In general, an accurate thrust modeling is very difficult to establish for an underwater robot in practice. Hence, the control voltage of the thruster is designed directly as the input of the system by the controller in this article. First, Taylor's polynomial is used to transform the form of the trajectory tracking error system of an underwater robot to the form of affine nonlinear systems, whose input is the control voltage of the thruster. Then, according to the principle of sliding mode control, and using the local recurrent neural network to estimate the unknown term of an affine system online, an adaptive sliding mode control is proposed. Aiming at the chattering problem which is caused by the sliding mode control term, we propose a switch gain adjustment method based on an exponential function. It is proved that the trajectory tracking error of the underwater robot control system is uniformly ultimately bounded through Lyapunov theory. The feasibility and effectiveness of the proposed approach is demonstrated with trajectory tracking experiments of the experimental prototype of an underwater robot.