基于博弈的差分进化和粒子群相结合的无人机任务分配

UAV Task Allocation Based on Game Differential Evolution and Particle Swarm Optimization

无人机具有成本低、灵活性高、部署方便等优点,在军事和民用领域得到了广泛的应用,然而,无人机的智能化水平难以应对复杂不确定的任务环境。为了提高无人机的智能性与协同能力,文章提出基于博弈的差分进化算法(Differential Evolution,DE)和粒子群算法(Particle Swarm Optimization,PSO)相结合的无人机任务分配,采用博弈论中的联盟博弈模型实现算法之间的相互协作。事实上,在每一轮迭代和特定迭代之后,DE和PSO算法进入博弈环境,基于纳什议价理论共同进行博弈,以达到联盟博弈中的纳什均衡状态。最后,通过仿真实验验证了所提算法的有效性。

UAVs have the advantages of low cost,high flexibility,and easy deployment,and have been widely used in military and civilian fields.However,the intelligence level of UAVs is difficult to cope with complex and uncertain task environment.In order to improve the intelligence and collaboration capability of UAVs,this paper proposes a UAV task allocation based on game Differential Evolution(DE)and Particle Swarm Optimization(PSO),which uses the coalitional game model in Game theory to achieve mutual cooperation among algorithms.In fact,after each iteration and a specific iteration,the DE and PSO algorithms enter the game environment and jointly engage in the game based on Nash bargaining theory to achieve the Nash equilibrium state in alliance games.Finally,the effectiveness of the proposed algorithm is verified through simulation experiments.