On the neuro-adaptive feedback linearising control of underactuated autonomous underwater vehicles in three-dimensional space

This study addresses the input-output feedback linearisation and the internal dynamics stability of an underactuated autonomous underwater vehicle (AUV) in three-dimensional space. By taking the coordinates of a virtual reference point in front of AUV system as the output equation, the input-output feedback linearisability of AUV kinematics and dynamics is guaranteed. A non-linear controller is designed to make the reference point track a desired trajectory which is generated by an open-loop path planner. Then, it is shown that the resulting internal dynamics of the system is stable. Neural network approximation capabilities and adaptive techniques are also adopted to compensate for unknown vehicle parameters, and constant or time-varying disturbances induced by waves and ocean currents. A Lyapunov-based stability analysis is used to show uniform ultimate boundedness of tracking errors. Finally, simulation results are provided to illustrate the effectiveness of the proposed control system as a qualified candidate for real implementations in offshore applications.