Ship berthing motion control based on improved Simulation Localization and Mapping algorithm

Abstract

With the development of autonomous vehicles and unmanned aerial vehicles, unmanned ships have also become a hot topic. In order to solve the problem of real-time motion attitude estimation of the ship itself when berthing and sailing relying on data driven. Based on the monocular camera, the improved ORB (Oriented FAST and Rotated Brief) enhanced SLAM (Simulation Localization and Mapping) algorithm image feature extraction method is used to solve the monocular camera motion pose, and finally build the ship motion control model. Solve the problem of ship berthing process control. This article uses the monocular camera video data when berthing to verify. The results show that compared with the traditional SLAM algorithm, the algorithm requires less calculation time and higher perception accuracy during the berthing process of the ship.