Vision-Guided UAV Landing on a Swaying Ocean Platform in Simulation.

This paper presents a new method for the autonomous landing of an unmanned aerial vehicle (UAV) on a moving ocean platform in simulation. The method uses GNSS data and a lightweight boat detection algorithm to guide the UAV toward the unmanned surface vehicle (USV). Once the USV is within the view of the down-looking camera, the UAV estimates its relative position by detecting a set of ArUco markers on the USV landing pad. During the descent process, to compensate for the heave motion of the USV caused by waves, the system utilizes data from a buoy equipped with a wave sensor. Simulation experiments demonstrate the reliability and effectiveness of the proposed approach.