极端环境下的无人机复杂配送问题建模及优化  

Modeling and Optimization of UAV Delivery Complex Problems in Extreme Environments

作　　者：郭振兴 张玉州 陈浩源 GUO Zhenxing;ZHANG Yuzhou;CHEN Haoyuan(School of Computer and Information,Anqing Normal University,Anqing 246133,China;School of Information Engineering,Nanjing Xiaozhuang University,Nanjing 211171,China)

机构地区：[1]安庆师范大学计算机与信息学院,安徽安庆246133 [2]南京晓庄学院信息工程学院,江苏南京211171

出　　处：《安庆师范大学学报(自然科学版)》2024年第4期73-81,共9页Journal of Anqing Normal University(Natural Science Edition)

基　　金：安徽省自然科学基金面上项目(1808085MF173,1908085MF194);南京晓庄学院高层次人才科研启动项目(4172322)。

摘　　要：取货和送货问题是一类复杂且重要的路径规划问题,亦是无人机物资配送路径规划中的热点问题。本文围绕无人机在极端环境下进行多任务多路径、非并发同步物资问题,构建了一种考虑充电驿站能量供给的优化模型。针对问题特点,本文提出了一种基于分层集编码策略的遗传算法以进行求解。在遗传算法中,对任务与取送进行分级,并采用交叉变异算子对个体进行进化操作。以Solomon benchmark标准算例为基础构造算例并进行测试,同时将求解结果与其他典型启发式算法进行比较。结果表明,所提方法能够实现极端环境下无人机配送的路径规划,具有快速收敛能力,且在保障多目标先取后送约束情况下,更逼近最优轨迹。The pickup and delivery is a class of complex and important path planning issues,and is also a hot topic in path planning for UAV material distribution.This paper addresses the multi-task multi-path,non-concurrent synchronization of material delivery problem of UAVs in extreme environments by constructing an optimization model that considers the energy supply of charging stations.A genetic algorithm based on hierarchical set encoding strategy is proposed to solve the problem,in which tasks and pickups and deliveries are hierarchical,and cross dissimilarity is used to perform evolutionary operations on individuals.The Solomon benchmark standard algorithm is used as the basis to construct the algorithm for testing,and the solution results are compared with other typical heuristic algorithms.The results show that the proposed method is capable of realizing path planning for UAV delivery in extreme environments,has fast convergence capability,and can more closely approximate the optimal trajectory while ensuring multi-objective fetch-and-deliver constraints.

关 键 词：路径优化 多路径同步取送 无人机配送 遗传算法 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]