Vision aided automatic landing system for fixed wing UAV

In this paper, we present a multi-sensor system for automatic landing of fixed wing UAVs. The system is composed of a high precision aircraft controller and a vision module which is currently used for detection and tracking of runways. Designing the system we paid special attention to its robustness. The runway detection algorithm uses a maximum amount of information in images and works with high level geometrical models. It allows detecting a runway under different weather conditions even if only a small part is visible in the image. In order to increase landing reliability under sub-optimal wind conditions, an additional loop was introduced into the altitude controller. All control and image processing is performed onboard. The system has been successfully tested in flight experiments with two different fixed wing platforms at various weather conditions, in summer, fall and winter.