Auto-Berthing Control of Marine Vessels Under Cyber Attacks

This paper studies the automatic berthing control of an unmanned surface vessel under cyber attacks. An adaptive neural-network-based fault-tolerant control method is developed. Unknown vessel dynamics, external disturbances, measurement noise, and cyber attacks are considered at the same time. First, the signal scaling, bias, and power-type distortion caused by cyber attacks are described by a unified nonlinear measurement model. The model has a known structure and unknown parameters. It converts different attack effects into structured uncertainties. Based on the corrupted position and attitude measurements, the tracking errors are defined. The vessel heading is reconstructed by integrating the unaffected yaw-rate signal. A Nussbaum-type function is introduced to handle the unknown gain in the measurement channel. A first-order filter is used to generate a smooth approximation of the virtual control signal. A neural network is then employed to approximate the unknown vessel dynamics. Adaptive laws are designed to estimate the composite uncertainties and external disturbances. Lyapunov analysis shows that all closed-loop signals remain bounded. The berthing tracking errors ultimately converge to a compact set around the origin. Finally, a berthing simulation with time-varying cyber attacks, measurement noise, and marine disturbances is conducted to evaluate the proposed method.