Use of swarm intelligence in unmanned vehicles

This article explores the use of swarm intelligence algorithms in unmanned vehicles (UVs), focuses on their main advantages for improving the efficiency and productivity of systems. Unmanned vehicles, which can operate autonomously or under remote control, play a significant role in such areas as surveillance, search and rescue, agriculture and military operations. The main focus of the article is on algorithms such as ant colony optimisation (ACO), artificial bee colony (ABC), particle swarm optimization (PSO), glow-worm swarm optimization (GSO), firefly algorithm (FA), bat algorithm (BA), grey wolf optimizer (GWO), and whale optimization algorithm (WOA). Each of these algorithms is discussed in detail, particularly their core principles, specific applications in UVs, and their levels of effectiveness in different environments. Each algorithm has been examined to highlight its operational strengths and its limitations, such as computational demands and environmental suitability. This paper discusses the algorithms in terms of managing critical functions of UVs, such as resource allocation and multi-agent coordination, which are essential for complex mission scenarios. Particular attention is paid to the adaptability of each algorithm, especially in unpredictable or hostile environments, where rapid recalibration of UV behaviour is necessary for mission success. By analysing each algorithm capacity to adjust the UV to new data in real-time, the article highlights their potential to optimize UV performance and reliability in challenging contexts. Special attention is given to collaborative task management in swarm intelligence, emphasizing its ability to enhance unmanned aerial vehicle (UAV) group coordination and decision-making for efficient operation in complex and dynamic scenarios. In general, the article provides deep analysis of swarm intelligence algorithms, and the information that will help choose the most effective algorithm to help solve specific tasks using different types of UVs. Future research will focus on improving the scalability, adaptability, and integration of these algorithms with latest technologies in order to enhance their effectiveness in solving complex UV missions. In addition, a comparative table of the main characteristics of the algorithms was created and a review of similar studies comparing swarm algorithms was made.