Autonomous Landing Perception System for UAVs in Maritime Contexts - A Modular Sensor Fusion and AI Vision System for Real-Time Estimation of Landing Platform Position and Orientation on Maritime Vessels

Sammanfattning

Precision landing on a dynamically moving platform presents significant challengesfor autonomous unmanned aerial vehicles (UAVs), particularly when the targetmoves in all six degrees of freedom. This thesis proposes a sensor fusion approach toautonomous landing in maritime contexts by integrating data from multiple onboardsensors including light detection and ranging (LiDAR), cameras, inertial measurementunits (IMUs), and depth sensors. The system combines AI-driven algorithmswith an extended Kalman filter (EKF) to continuously estimate the position andorientation of the landing platform in real time. Analysis of results obtained in asimulated environment show the potential of the proposed method under challengingenvironmental conditions. These findings indicate the ability of sensor fusion toassist in autonomous landing in a maritime context.