城市区域多物流无人机任务分配问题研究  

Research on Task Allocation of Multiple Logistics Unmanned Aerial Vehicles in Urban Area

作　　者：张连东 张洪海[1] 冯棣坤 李博文 费毓晗 刘皞[1] ZHANG Lian-dong;ZHANG Hong-hai;FENG Di-kun;LI Bo-wen;FEI Yu-han;LIU Hao(Nanjing University of Aeronautics and Astronautics,Nanjing 211000,China)

机构地区：[1]南京航空航天大学,江苏南京211000

出　　处：《航空计算技术》2021年第6期69-73,共5页Aeronautical Computing Technique

基　　金：国家自然科学基金项目资助(71971114);南京航空航天大学研究生创新基地(实验室)开放基金项目资助(kfjj20200716)。

摘　　要：针对城市配送场景下多物流无人机任务分配问题,以物流运输成本最小和顾客满意度最高为优化目标,建立多物流无人机任务分配模型。设计改进遗传算法进行求解:为提高优秀个体选出概率,采用含精英保留的多轮盘赌选择机制;为提高算法搜索精度和收敛速度,选用自适应交叉和变异概率;为保护优秀个体并促进较差个体进化,采用多种交叉和变异方式相结合的进化方式。仿真结果表明:与遗传算法相比,改进算法适应度函数平均值优化6.0%,可求解得到运输成本低、顾客满意度高的任务分配方案。Aiming at the task allocation problem of multiple logistics unmanned aerial vehicles in urban distribution scenario,a task allocation model of multiple logistics unmanned aerial vehicles was established with the aim of minimizing logistics transportation cost and maximizing customer satisfaction.An improved genetic algorithm was designed to solve the problem.In order to improve the selection probability of excellent individuals,a multi-roulette selection mechanism with elite retention was adopted.In order to improve the searching accuracy and convergence speed of the algorithm,the adaptive crossover and mutation probability were selected.In order to protect the excellent individuals and promote the evolution of the poor individuals,a variety of crossover and variation methods were adopted.The simulation results show that compared with the genetic algorithm,the average fitness value of the improved algorithm is optimized by 6.0%,and the task allocation scheme with low transportation cost and high customer satisfaction can be obtained.

关 键 词：航空运输 任务分配 改进遗传算法 物流无人机 

分 类 号：V279[航空宇航科学与技术—飞行器设计]