A vision-based navigation system for Unmanned Aerial Vehicles (UAVs)

Abstract

The advances in microelectronics foster the Unmanned Aerial Vehicles (UAVs) to be used in many civil and academic applications that require higher levels of autonomy and flight stabilization. The main objective in this paper is to provide UAVs with a robust navigation system; in order to allow the UAVs to perform complex tasks autonomously and in real-time. The proposed algorithms deal with solving the navigation problem for outdoor and indoor environments, mainly based on visual information that is captured by monocular cameras. This paper covers the topics of Pose Estimation, Navigation Guidance, and Visual Servoing. All the proposed algorithms have been verified with real flights in both indoor and outdoor environments, taking into consideration the visual conditions; such as illumination and textures. The obtained results have been validated against other systems; such as VICON motion capture system, DGPS in the case of pose estimate algorithm. In addition, the proposed algorithms have been compared with several previous works in the state of the art, and the results prove the improvement in the accuracy and the robustness of the proposed algorithms.