Competitive Evolution of a UAV Swarm for Improving Intruder Detection Rates

Abstract

In this paper we present a Predator-Prey approach to enhance the protection of a restricted area using a swarm of Unmanned Aerial Vehicles (UAV). We have chosen the CACOC (Chaotic Ant Colony optimisation for Coverage) mobility model for the UAVs and a new model for intruders based on attractive and repulsive forces. After proposing a number of parameters for each mobility model, we have conducted a competitive optimisation of them (Predators and Preys), to achieve a more robust configuration improving the success rate of UAVs when detecting intruders. We have optimised three case studies by performing 30 independent runs of our competitive coevolutionary genetic algorithm and conducted a number of master tournaments using the best specimens obtained for each case study.