MACHINE LEARNING MODEL OF SWARM EVASION FROM THE INFLUENCE OF ANTAGONISTIC ENVIRONMENT

One of the priority areas of group control theory for the near future is swarm control of groups ofsmall unmanned aerial vehicles - micro-, mini- and nano-classes, performing a collective task under enemyinfluence. Here, two antagonistic strategies collide - minimization of losses from the point of view ofthe attacking swarm and maximization of such losses from the point of view of the defense system. Research objective: development of an approach to solving a practical problem - penetration of a swarm ofunmanned aerial vehicles into an object protected by a defense system. The objectives of the study were toanalyze the characteristics of the factors influencing the processes of detection, tracking, recognition ofswarm intentions by the defense system and the development of a machine learning model for creatingspatio-temporal formations that minimize the number of swarm elements affected by the defense system.The main parameters of the defense system are the detection range and duration of swarm recognition, thetime to make a decision on the actions of the swarm, the size of the zone of destruction of defense means.The method of machine learning on convolutional neural networks with reinforcement was chosen as theresearch method. The counteraction effect against the defense system is created due to the swarm's dynamics;it can actively maneuver, creating spatio-temporal maneuvers during the mission. To simulate the"Swarm vs. Defense System" situation, a swarm agent (a neural network with a transformer architecturethat initiates swarm formations) and a defense system agent are introduced that recognizes the swarm andattacks it, creating a zone of destruction in the conventional center of mass of the swarm. The swarm isguided by a stochastic rule, asking the defense system (environment) to react to its maneuver. The environmentresponds by attacking the swarm, creating a damaging factor at the point where the swarm or themain part of the swarm is expected to be. The reward of the swarm strategy is the number of undestroyedobjects under the conditions of constraints; for the defense system, this "reward" acts as a "punishment".An interesting phenomenon was established in the process of machine learning: each swarm element,remaining within a given space and implementing the biological principles of swarm control without aLeader, independently evades the area of destruction, which together creates a random spatio-temporalformation for defense means with minimal losses of swarm elements. Thus, using the method of machinelearning with reinforcement, a model was created that allows varying the behavior of the swarm and synthesizingspatio-temporal formations that complicate detection, tracking, recognition of intentions anddecision-making on the impact of the defense system on a swarm of attacking small unmanned aerial vehicles,as well as significantly reducing their losses.