Single neural network-based asymptotic adaptive control for an autonomous underwater vehicle with uncertain dynamics

Abstract

This paper focuses on the adaptive asymptotic tracking control problem for an autonomous underwater vehicle (AUV) with un-modeled dynamics and unknown input saturation by combining the backstepping control strategy and the neural network (NN) method. In our controller, a novel single neural network-based backstepping control method is proposed to address the uncertain problem, and the input saturation issue is overcome in virtue of a hyperbolic tangent function. The approximation error of the neural network is also compensated by a new adaptive mechanism in order to achieve the zero-error regulation. Furthermore, the nonlinear transformation is incorporated into the backstepping-based framework to improve the AUV performance. And then, the performance analysis illustrates that the designed controller can realize the asymptotic stability of the AUV system. Finally, the effectiveness of our control strategy is validated through simulation results.