Safe Motion Strategy for High-speed USV Based on State Information Modeling Forecasting and ROS

Abstract Due to the complexity and variability of the ocean environment, it is difficult for high-speed Unmanned Surface Vehicles (USV) to move safely on hydrographic surveying missions. First, the USV’s heading and speed vectors are modeled and forecasted based on the reservoir computing algorithm and the hybrid kernel function Gaussian process regression algorithm, respectively. Second, a USV safe motion strategy is developed using modeling forecast prior information and motion analysis. Finally, the ROS (Robot Operation System) -based simulation environment for USV is built to verify the effectiveness of the modeling forecasting algorithm and the safe motion strategy. The simulation of outbound, inbound and bridge crossing scenario are performed which ensures the safe motion of the USV when it performs hydrographic surveying tasks.