An Evolutionary Algorithm to Optimise a Distributed UAV Swarm Formation System

In this article, we present a distributed robot 3D formation system optimally parameterised by hybrid evolutionary algorithm (EA) in order to improve its efficiency and robustness. To achieve that, first describe the novel algorithm3 (DFA3), proposed EA, two crossover operators be tested. The EA hyperparameterisation is performed using irace package evaluation of three case studies featuring three, five, ten unmanned aerial vehicles (UAVs) through realistic simulations ARGoS scenarios evaluated parallel robustness configurations calculated. optimisation results, reported with statistical significance, validation on 270 unseen show that use metaheuristic imperative for such complex problem despite some overfitting observed under certain circumstances. All all, UAV swarm self-organised itself stable formations 95% studied plus/minus percent tolerance.