Autonomous vision-based landing of UAV’s on unstructured terrains

Unmanned Aerial Vehicles (UAVs) technology has enabled the design of many diverse applications in recent years. The development of autonomous landing methods has become a core task, as UAV’s navigate in remote and usually unknown environments. In this study we present a vision-based autonomous landing system for UAVs equipped with a stereo camera and an inertial measurement unit (IMU). We utilize stereo processing to acquire the 3D reconstruction of the scene. Next, we evaluate and quantity into map-metrics the factors of the terrain that are crucial for a safe landing. The optimal landing site in terms of flatness, steepness and inclination across the scene is chosen. The pose estimation is obtained by the fusion of stereo ORB-SLAM2 measurements with data from the inertial sensors, assuming no GPS signal. We evaluate the utility of our system using a multifaceted dataset and trials in real-world environments.