基于DAPF与EACO算法的无人机博弈策略

UAV gaming strategy based on DAPF and EACO algorithms

针对双方无人机之间的动态对抗博弈问题,提出了动态人工势场法(dynamic artificial potential field method,DAPF)和精英蚁群优化(elite ant colony optimization,EACO)算法相结合的求解方法。首先,采用动态人工势场法,以敌我双方无人机作为博弈的局中人,构建双方无人机动态对抗博弈模型。其次,提出精英蚁群算法,计算双方博弈的纳什均衡策略。该算法引入对立学习和划分精英蚂蚁加快算法收敛速度,并引入遗传算法中的变异操作以避免局部最优值的问题。最后,仿真验证了所提方法的可行性和有效性。

To deal with the dynamic confrontation game problem between unmanned aerial vehicles(UAVs)on both sides,a solution method combining dynamic artificial potential field(DAPF)method and elite ant colony optimization(EACO)algorithm was proposed.Firstly,the dynamic artificial potential field method was adopted to construct a dynamic confrontation game model for the UAVs,with both the enemy and our UAVs as the central players.Secondly,an elite ant colony algorithm was proposed to calculate the Nash equilibrium strategy of the game between the two sides.The algorithm incorporated opposite-learning and division of elite ants to accelerate the convergence speed,and introduced the mutation operation in the genetic algorithm to avoid the problem of local optimal value.Finally,the feasibility and effectiveness of the proposed method were verified by simulation.