AUTONOMOUS COOPERATIVE UNMANNED AERIAL VEHICLE

Abstract

As a quite interesting subject, there are an increasing number of researches about UAV (Unmanned Aerial Vehicle) in the literature. These robots are quite suitable to dull, dir- ty and dangerous missions (e.g., over flights at low altitude, especially at night, and long- running operations, which exposes the crew to extreme fatigue). Thus, an important applica- tion of these vehicles is the search operations involving multiple UAVs. However, despite the huge potential use of the UAVs, cooperative search operations with this kind of flying robots are not yet occurring. This research topic is a multidisciplinary area of study in its beginning. Several issues can be studied related to cooperative UAV for search operations, such as cen- tralized versus decentralized control, path planning for cooperative flies, agent reasoning for UAV tactical planning, safety assessments, reliability in automatic target reconnaissance by cameras, agent coordination mechanisms applied for UAV cooperation and the application itself (e.g., patrolling, remote sensing, search and rescue operations supporting, etc.). This paper proposes a model that combines path planning algorithms, search patterns and multi- agent coordination techniques to obtain a cooperative UAV model. Different path planning algorithms were studied aiming to get the most suitable to these kinds of operations, and the conclusions are presented. In addition, official documents of Search and Rescue operations are also studied in order to know the best practices already established for this kind of opera- tions, and, finally, an overview of the coordination multi-agent theory is presented and eva- luated to achieve the UAV coordination. The great goal for cooperative UAV is to achieve such performance that the performance of the group overcomes the sum of the individual per- formances isolatedly. Comparing two cooperative UAVs with two non-cooperative UAVs, simulations of previous work showed an average increase in efficiency by about 100%. Be- sides, another aspect was simulated and evaluated: the impact of the density of the initial sweep. The computational simulations show a high potential of reducing even more the time of search. Furthermore, it is worth noting that the usefulness of cooperative UAVs is not only the increase in efficiency, but also the reduction of costs and risks for the crew.