A Hybrid Approach for Visual Servo Control of Underwater Vehicles

This paper presents a hybrid visual servo controller for underwater vehicles by exploiting a combination of measured Euclidean information and image information of a single feature. A dynamic inversion-based neural network control scheme is proposed for tracking of the reference trajectory generated from a constant target pose. A single-hidden- layer (SHL) feedforward neural network, in conjunction with a sliding mode controller, is employed to compensate for dynamic uncertainties. The adaptation laws for neural network weight matrices are designed to ensure the asymptotical stability of the tracking errors and the ultimate uniform boundedness of the weight matrices. Simulation results are provided to demonstrate the effectiveness of the developed controller.