Adaptive neural network control for visual docking of an autonomous underwater vehicle using command filtered backstepping

This article proposes an unscented Kalman filter-based visual docking controller for underactuated underwater vehicles using a position-based visual servoing (PBVS) approach. The relative pose of an underwater vehicle with respect to a moving docking station is estimated by an unscented Kalman filter with the visual measurements of multiple point features installed on the station. Based on the estimated pose, the Euler angles commands are designed via an integral cross-tracking docking method to drive the underwater vehicle to move along the desired docking path. Then, an adaptive neural network (NN) controller is designed to track the desired yaw and pitch angles using command filtered backstepping, in which a single-hidden-layer (SHL) neural network is employed to compensate for dynamic uncertainties and external disturbances. A barrier Lyapunov function is defined to improve the stability of tracking errors under attitude constraints to ensure the features are in the field of view, and hyperbolic tangent functions are utilized to deal with input saturation. Simulation studies and pool experiments are provided to demonstrate the performances of the proposed visual docking controller.