Adaptive multi-objective search in a swarm vs swarm context

As the number of commercial Unmanned Aerial Vehicles (UAVs) or drones continues to increase, there is a need to develop autonomous policing or patrolling mechanism to guard over the swarm of anonymous intruding drones having unknown heterogeneous dynamical behavior and maintain the safety and order in the sky. This paper addresses such a future need and proposes to employ a swarm of patrolling drones that can collectively search a flying zone to find and follow the other anonymous drones effectively for any relevant purposes. Specifically, the key contribution of this research is the development of a robust and flexible search mechanism, which enables the patrolling drones to overcome confusing evasive tactics by the anonymous drones. During the search process, the patrolling drones first scatter to cover a region of interest, and then proceed to find and follow an anonymous drone. For this purpose, a multi-objective optimization problem is formulated. The problem is solved using a few evolutionary algorithms, and performances/results are evaluated through simulation. It is found that multiple particle swarm optimization (MPSO) requires the least processing time.