Development of a method for managing a group of unmanned aerial vehicles using a population algorithm

The object of the study is a group of unmanned aerial vehicles (UAVs). The subject of the study is the decision-making process in management tasks using: – an improved brown bear algorithm (BBA), which achieves the determination of the optimal UAV movement route based on the given optimization criterion (the probability of completing the flight task), described by complex multimodal functions; – evolving artificial neural networks for deep learning of the multi-agent system knowledge base, by training both the parameters and the architecture of artificial neural networks. The originality of the method lies in using additional improved procedures that allow: – the initial BBA population and their initial position on the search plane are determined considering the degree of uncertainty in the data on the UAV group movement route; – the initial speed of each BBA is considered, enabling the prioritization of searches in the respective search plane (height, latitude, and longitude); – the suitability of the UAV group's flight route for performing the flight task is determined, considering a set of external factors, thereby reducing the decision search time; – the universality of BBA food search strategies allows classifying a set of conditions and factors affecting the completion of the flight task. This aids in identifying the most feasible movement options for the UAV group based on the defined optimization criterion for movement route. Modeling the operation of the proposed method has shown that the increase in decision-making efficiency reaches 15–18 %. The enhancement in the method's efficiency is achieved through additional procedures and ensuring the reliability of the decisions at a level of 0.9