无人机水上船舶物流配送任务规划研究  

Research on Planning UAV Waterborne Logistics Delivery Missions for Ships

作　　者：高翔宇 羊钊[1] 李娜[1] GAO Xiang-yu;YANG Zhao;LI Na(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》2023年第4期81-85,共5页Aeronautical Computing Technique

基　　金：国家自然科学基金项目资助(52172328);中央高校基本科研业务费专项资金项目资助(NS20220093);南京航空航天大学科研与实践创新计划项目资助(xcxjh20220738)。

摘　　要：针对水上船舶物流配送场景下的无人机任务规划问题,综合考虑了无人机自身性能限制和物流配送任务要求,以飞行路径长度最短为目标函数构建了多无人机物流配送任务规划模型。为提高算法求解效率和寻优性能,在粒子群算法基础上进行改进,融入遗传算法的精英选择策略、交叉策略和自适应高斯变异策略。仿真实验结果表明,相较于遗传算法和粒子群算法,该混合算法具有更快的收敛速度和更高的精度,具备较强的寻优能力,能够找到更佳的船舶物流配送任务规划方案。In order to address the problem of unmanned aerial vehicle(UAV)mission planning in waterborne ship logistics distribution scenarios,this article comprehensively considers the performance of UAVs and logistics mission requirements,and constructs a multi UAVs logistics distribution mission planning model with the shortest flight path length as the objective function.To improve the efficiency and optimization performance of the algorithm,improvements have been made on the basis of the particle swarm algorithm.It incorporates the elite selection strategy,crossover strategy and adaptive Gaussian mutation strategy of genetic algorithm.Simulation experiment results show that compared to genetic algorithm and particle swarm optimization,this hybrid algorithm has a faster convergence speed and higher accuracy,as well as strong optimization capabilities.It can find better ship logistics distribution mission planning solutions.

关 键 词：水上船舶物流配送 无人机任务规划 遗传算法 粒子群算法 融合算法 

分 类 号：V279[航空宇航科学与技术—飞行器设计]