Trajectory Tracking Control of Underactuated AUV Based on Ocean Current Observer

This paper addresses the planar trajectory tracking control problem for an Autonomous Underwater Vehicle (AUV) subject to ocean current. The AUV's motion includes longitudinal, lateral, and yaw movements, with underactuation due to the absence of lateral control input. A new Radial Basis Function Neural Network (RBFNN) based disturbance observer is designed, which is used to estimate the ocean. Then the dynamic controller of the AUV is designed by the backstepping method. An example is given to show the effectiveness of the proposed method.