Scholarlink

<p>Unmanned Aerial Vehicles (UAVs) have gradually played an increasingly important role in the low-altitude economy. The task allocation problem has become a vital issue in the application of the logistics of groups of low-altitude UAVs, and the focus of UAV logistics enterprises is to improve the system’s operation efficiency and economic benefits. Currently, mainstream multi-UAV task allocation algorithms cannot solve the satisfactory task allocation scheme in an acceptable time. The contribution of this paper is the proposal of a new two-stage heuristic algorithm based on a combination of the Hungarian algorithm and an improved genetic algorithm that achieves global performance optimization and obtains an overall superior solution in less time. The experiments showed that the proposed algorithm performed 15.26% better than the traditional genetic algorithm regarding overall task allocation revenue and required 17.6% less calculation time, indicating a better overall solution. The algorithm proposed in this paper provides a new optimization strategy for solving the problem of low-altitude multi-UAV task allocation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Two-stage heuristic genetic optimization algorithm for multi-UAV logistics task allocation

  • 期刊论文

  • 发表日期：

    2025年8月1日

查看全文
  • Hao Guo,
  • Xiaochong Tong,
  • Yuekun Sun,
  • Jiayuan Cheng,
  • Chang Yuan,
  • Yunrui Bai,
  • He Li,
  • Congzhou Guo

摘要

Unmanned Aerial Vehicles (UAVs) have gradually played an increasingly important role in the low-altitude economy. The task allocation problem has become a vital issue in the application of the logistics of groups of low-altitude UAVs, and the focus of UAV logistics enterprises is to improve the system’s operation efficiency and economic benefits. Currently, mainstream multi-UAV task allocation algorithms cannot solve the satisfactory task allocation scheme in an acceptable time. The contribution of this paper is the proposal of a new two-stage heuristic algorithm based on a combination of the Hungarian algorithm and an improved genetic algorithm that achieves global performance optimization and obtains an overall superior solution in less time. The experiments showed that the proposed algorithm performed 15.26% better than the traditional genetic algorithm regarding overall task allocation revenue and required 17.6% less calculation time, indicating a better overall solution. The algorithm proposed in this paper provides a new optimization strategy for solving the problem of low-altitude multi-UAV task allocation.