A three-degrees-of-freedom model, including surge, sway and yaw motion, with differential thrusters is proposed to describe unmanned surface vehicle (USV) dynamics in this study. The experiment is carried out in the Qing Huai River and the data obtained from different zigzag trajectories are filtered by a Gaussian filtering method. A physics-informed neural network (PINN) is proposed to identify the dynamic models of the USV. PINNs combine the advantages of data-driven machine learning and physical models. They can also embed the speed and steering models into the loss function, which can significantly retain all types of information. Compared with traditional neural networks, the results show that the PINN has better generalization ability in predicting the surge and sway velocities and rotation speed with only limited training data.

Fixed-point underwater hovering is a key technology for the reliable operation of a remotely operated vehicle in the ocean to inspect the surfaces of a variety of underwater structures, such as ports and offshore wind power facilities. This study proposes an underwater wall absorber that can be used in remotely operated vehicles. First, we explain the working principle of the underwater absorber. Second, we analyze the main factors affecting its adsorption performance by using numerical simulations. Finally, we show the results of a tested prototype of the proposed absorber, whose performance was consistent with the results of numerical calculations. The proposed absorber may have important technical prospects for use in remotely operated underwater vehicles.