Aiming at the problem of how to determine the position of jumping and shooting independently in the cooperative attack combat of unmanned combat vehicle (UCAV), a decision-making mathematical model for determining the position of jumping and shooting independently is constructed. Considering the battlefield terrain environment, enemy force distribution, leap distance, leap direction, fire coordination between friendly neighbors and other factors, an adaptive multi-population genetic algorithm (GA) with the best individual is proposed to solve the model. The experimental results show that the model can achieve the purpose of determining the jump position and shooting position of unmanned combat vehicle autonomously. The proposed improved genetic algorithm has the advantages of strong global search ability, fast convergence speed and good stability, which has a certain reference value for the research and promotion of autonomous capability of unmanned combat equipment.