Path Planning via Swarm Intelligence Algorithms in Unmanned Aerial Vehicle Population

Abstract

Unmanned Aerial Vehicle (UAV) is an autonomous aerial vehicle capable of operating autonomously or in swarm cooperation, performing various tasks in civilian and military domains that exceed human capabilities. These vehicles, which can be produced in different models with varying hardware and software features, include flight control systems, route tracking systems, sensors, and numerous additional components. UAVs have the ability to process data from themselves, the control center, and the external environment. Data processing enables functions such as flight management, swarm optimization, and target and route analysis. In this analysis process, optimization algorithms and especially swarm intelligence algorithms inspired by creatures that move in flocks in nature are used. In this study, the aim was to determine the optimal route and distance from 10 different coordinate points for collective task optimization within a UAV swarm. Artificial Bee Colony (ABC) Optimization and Particle Swarm Optimization (PSO) were used during the task optimization process. The application was coded in Python. As a result of the application, the optimal distance was calculated as 0.123 km for the ABC algorithm and 0.167 km for the PSO algorithm. In addition, both algorithms determined the best routes according to different start and end points in route planning task optimisation.