Multiple UAVs Target Allocation via Stochastic Dominant Learning Pigeon-inspired Optimization in Beyond-visual-range Air Combat

Abstract

Target attack mission is considered to be one of the crucial problems in the background of beyond-visual-range aerial combat. In this paper, a stochastic adaptive dominant pigeon-inspired optimization is proposed to solve multiple unmanned aerial vehicles (UAVs) target allocation problem. The situation assessment functions between UAVs are constructed by considering their relative distance, angles, velocities, on-board radar and missile capabilities. The cooperative target allocation model is designed by the game theory with payoff matrix. To handle this problem, a stochastic dominant learning pigeon-inspired optimization (SDLPIO) is introduced, which not only keeps pigeon diversity and convergence speed, but also consumes less time and space to search the optima. In addition, four classical optimization algorithm are compared to prove the effectiveness of the SDLPIO algorithm by experimental results.