Search

The control of a multiple unmanned aerial vehicle (UAV) system is popular and attracting a lot of attentions. This is motivated by many practical civil and commercial UAV applications. Collision avoidance is the fundamental in motion planning of multi-UAVs, especially for large teams of UAVs. Although several collision avoidance approaches have been reported, there is a lack of highlighting the key components shared by these approaches. In this work, we aim to provide researchers with a state-of-the-art overview of various approaches for multi-UAV collision avoidance. The existing works on collision avoidance are presented through several classifications based on algorithm used and frameworks designed, and their main features are also discussed. A discussion on the literature summary in multi-UAV collision avoidance is given, Finally, the challenges in the research directions are presented. [ABSTRACT FROM AUTHOR]

Over the past two decades, unmanned aerial vehicles (UAVs) have attracted more and more attention because of their increasing applications in the military and civil sectors. Collision avoidance is a core problem in developing UAVs. In this paper, a low-cost camera based sense and avoid control scheme is proposed. First, for the unmanned aerial vehicle (UAV) sense and avoid problem, we propose and demonstrate a low cost solution with only one monocular, wide field of view camera. We adapted a deep learning based algorithm and made it lightweight enough to run on-board the UAV. We created a synthetic dataset to increase the size of the training data set. Second, we developed a filter to estimate the 3D position and velocity of the moving obstacle. Third, based on the estimated information, we adapted the velocity obstacle approach to work in 3D. Finally, we implemented the algorithms in the software framework of our UAV testbed and conducted flight tests, demonstrating the effectiveness of the solution. [ABSTRACT FROM AUTHOR]