基于A-ACO算法的物流车配送路径优化分析与研究  

Route Optimization of Logistics Vehicle Distribution Based on A-ACO Algorithm

作　　者：周艳玲[1] 王子龙 沈鑫 付余涛 崔精涛 ZHOU Yan-ling;WANG Zi-long;SHEN Xin;FU Yu-tao;CUI Jing-tao(School of Artificial Intelligence and Big Data,Heifei University,Hefei 230041,China)

机构地区：[1]合肥学院人工智能与大数据学院,安徽合肥230601

出　　处：《榆林学院学报》2025年第2期87-92,共6页Journal of Yulin University

基　　金：安徽省高校优秀人才培养资助项目(gxgwfx2019065);安徽省质量工程项目(2021xxkc158);校级教学研究项目(2022hfujyzd06)。

摘　　要：随着物流行业的不断发展,配送环节是连接买家和卖家的主要纽带,配送时的速度、效率、安全性和经济性影响着客户的满意程度,这使得物流车在配送时追求最优路径。为了使物流车在运输货物的过程中可以有效的躲避路上的障碍物并寻找到最优路径,本文提出A-ACO算法,该算法通过对传统的蚁群算法的基础上增加了躲避障碍物的功能和障碍物影响因子。通过Netlogo对算法进行仿真,在仿真的过程中通过改变蚂蚁的数量来得出起点与终点的最短路径。改进后的蚁群算法相比传统的蚁群算法在安全性条件下获得最优路径。最后通过仿真实验证明,A-ACO算法可以在不同障碍物分布和数量下寻找最优路径的安全性和有效性,为物流公司选择配送路径的选择提供了一定参考价值。With the continuous development of the logistics industry,the distribution link is the main link between buyers and sellers.The speed,efficiency,safety and economy of the distribution affect the competition of the logistics company,making the logistics vehicle pursue the optimal path in the distribution.In order to effectively avoid obstacles on the road and find the optimal path in the process of logistics vehicle distribution,this paper adds an algorithm to avoid obstacles based on the ant colony algorithm,and obtains the shortest path between the starting point and the end point by changing the number of ants through the simulation software Netlogo.Compared with the traditional ant colony algorithm,it can improve the safety of logistics vehicles in the transportation process and improve the reference value for logistics companies.

关 键 词：蚁群算法 NETLOGO 障碍物 最优路径 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]