ANALYSIS OF SWARM CONTROL METHODS FOR UNMANNED AERIAL VEHICLES

Abstract

This study presents a comprehensive analysis and comparison of swarm intelligence algorithms for controlling unmanned aerial vehicle (UAV) swarms in dynamic environments. The research focuses on Particle Swarm Optimization, Ant Colony Optimization, and Artificial Bee Colony algorithms, examining their operational principles, advantages, limitations, and practical applications. To ensure an objective evaluation, a set of performance criteria was established, including convergence speed, flexibility, robustness to environmental changes, computational complexity, and energy efficiency. The results highlight the most suitable algorithms for tasks such as search, reconnaissance, mapping, and cooperative cargo delivery. Furthermore, promising directions for future research are identified, particularly the development of hybrid approaches that combine the strengths of different methods and the adaptation of swarm algorithms to uncertain and rapidly changing conditions. The practical significance of the study lies in providing a foundation for the development of more autonomous and efficient UAV swarm control systems applicable in agriculture, search and rescue, environmental monitoring, and infrastructure inspection. The findings may serve as a methodological basis for further integration of swarm-based approaches into practical UAV control systems.