UAVS safe landing using range images

In this paper a mixed vision-range based approach, based on Kinect technology, for safe landing of an Unmanned Aerial Vehicle (UAV) is proposed. The guidance system allows a remote user to define target areas from an high resolution aerial or satellite image to determine the waypoints of the navigation trajectory or the landing area. The system is based on our previous work on UAV navigation and landing: a feature-based image matching algorithms finds the natural landmarks and gives feedbacks to the control system for autonomous navigation and landing. An algorithm for safe landing areas detection is proposed, based on the use of 4D RGBD (Red, Green, Blue, Distance) image analysis. The helicopter is required to navigate from an initial to a final position in a partially known environment, to locate a landing area and to land on it. Results show the appropriateness of the vision-based approach that does not require any artificial landmark (e.g., helipad) and is quite robust to occlusions, light variations and high vibrations. © 2011 by ASME.