基于改进蚁群算法的多无人机协同任务分配

Multi UAV Collaborative Task Allocation Based on Improved Ant Colony Algorithm

针对城市物流场景下多无人机协同任务分配问题,考虑无人机性能、飞行成本和配送点紧迫度不同,建立更加符合真实场景的组合优化模型,提出了一种融合遗传算法的改进蚁群算法。基于无人机和配送点之间的访问关系,根据遗传算法中基因编码思想采用了一种整数组合基因编码方式以生成种群个体,为提高算法搜索能力设计了一种扰动算子的改进交叉操作。将遗传算法的结果转化为蚁群算法的初始信息素,通过一种自适应信息素机制和引入扩展启发量的策略来指导种群搜索方向,从而平衡算法的全局搜索能力和局部搜索能力。仿真实验表明,所提出的改进算法能很好的跳出局部最优,并且能够高效、稳定地找出合理的无人机配送方案。

Aiming at the problem of multi UAV collaborative task allocation in urban logistics scenarios,a combinatorial optimization model that is more in line with real scenarios is established by considering the different performance,flight cost and urgency of delivery points of UAVs.An improved ant colony algorithm fused with genetic algorithm is proposed.Firstly,based on the access relationship between UAVs and delivery points,an integer combination gene coding method is adopted to generate population individuals according to the gene coding idea in genetic algorithm.An improved crossover operation of perturbation operator is designed to improve the algorithm search ability.Then,the result of genetic algorithm is converted into the initial pheromone of ant colony algorithm.An adaptive pheromone mechanism and the strategy of introducing extended heuristic are used to guide the search direction of population,so as to balance the global search ability and local search ability of the algorithm.Simulation experiments show that the proposed improved algorithm can well jump out of the local optimum and can efficiently and stably find a reasonable UAV delivery solution.