Metaheuristic Planner for a Swarm of UAVs

Abstract

Unmanned Aerial Vehicles (UA Vs) have become an important component in various applications, such as filmmaking or area surveillance. Many modern applications employ autonomous flight of UAV swarms, which offer advantages but also pose constraints. This paper is focused on research and testing of different metaheuristic algorithms used for swarm path planning. Specifically, this study compares the performance of Genetic Algorithm (GA), Ant Colony Optimization (ACO), Tabu Search (TS) and Gravitational Search (GS) in solving UA V path planning problem. The proposed path planner aims to generate near-optimal trajectories for area coverage while avoiding collisions within the swarm.