Co-Evolution Genetic Algorithm for UAV Distributed Tracking in Urban Environments

A distributed approach is proposed for planning a cooperative tracking task for a team of unmanned aerial vehicles (UAVs). In the scenario of interest UAVs are required to autonomously track, using their onboard sensors, a moving target in a known urban environment. The solution methodology involves finding visibility regions, from which a UAV can maintain a line of sight to the target during the scenario; and restricted regions, in which a UAV can not fly, due to the presence of buildings or other airspace limitations. A co-evolution genetic algorithm is derived for searching, in realtime, monotonically improving solutions. In the proposed distributed search method every UAV iteratively manipulates its own population of chromosomes, each encoding its control inputs in the calculated horizon. Team performance is attained by assigning fitness to each solution in the population based on the cooperative performance when using it together with preceding iteration tracking information obtained from teammates. Important attributes of the proposed solution approach are its scalability and robustness; and consequently it can be applied to large sized problems and adapt to the loss of UAV team members. The distributed nature of the algorithm also reduces the computation and communication loads. The performance of the algorithm is studied using a high fidelity simulation test-bed incorporating a visual database of the city of Tel-Aviv, Israel.