Neural Network Based Adaptive Controller for a Remotely Operated Vehicle

This paper analyzes the tracking control problem for an underwater vehicle subjected to different load configurations, that result in considerable variations of its mass and inertial parameters. For this class of rapidly varying processes, traditional control techniques are not adequate to guarantee the required performance when a change of the configuration occurs. To cope with this problem, a neural network based nonlinear adaptive control is proposed. The stability of this control system is analyzed using the Lyapunov theory and its performance is evaluated by numerical simulations.