[1]李卓娟,陶伟,李辉.基于改进能量谷优化算法的多目标无人机任务分配[J].计算机技术与发展,2025,(10):105-113.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0140]
　LI Zhuo-juan,TAO Wei,LI Hui.UAV Task Allocation Based on Improved Energy Valley Optimization Algorithm[J].,2025,(10):105-113.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0140]
点击复制

基于改进能量谷优化算法的多目标无人机任务分配()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年10期
页码:
105-113
栏目:
人工智能
出版日期:
2025-10-10

文章信息/Info

Title:
UAV Task Allocation Based on Improved Energy Valley Optimization Algorithm
文章编号:
1673-629X(2025)10-0105-09
作者:
李卓娟1; 陶伟2; 李辉1; 3
1. 四川大学 计算机学院(软件学院),四川成都 610065;
2. 中国舰船研究设计中心,湖北武汉 430064;
3. 四川大学 视觉合成图形图像技术国家级重点实验室,四川成都 610065
Author(s):
LI Zhuo-juan1; TAO Wei2; LI Hui1; 3
1. School of Computer Science (Software),Sichuan University,Chengdu 610065,China;
2. China Ship Research and Design Center,Wuhan 430064,China;
3. National Key Laboratory of Fundamental Science on Synthetic Vision,Sichuan University,Chengdu 610065,China
关键词:
多无人机; 无人机侦察; 任务分配; 多目标优化; 能量谷优化算法
Keywords:
multiple unmanned aerial vehicles;  UAV reconnaissance;  task allocation;  multi-objective optimization;  energy valley optimization algorithm
分类号:
TP18
DOI:
10.20165/j.cnki.ISSN1673-629X.2025.0140
摘要:
无人机侦察是未来实施军事侦察和收集情报的重要方式,在多约束条件下无人机的任务分配问题是协同侦察中的难点。针对此问题,提出了一种改进多目标能量谷优化算法(IMOEVO)。首先,关注能量消耗和目标收益两个层面,考虑三维场景中无人机不同运动模式的能耗以及无人机执行效率对任务收益的影响,建立了一种无人机能耗和任务收益的多目标优化问题模型。然后,结合最佳粒子选择策略和帕累托前沿精英优化策略拓展并改进能量谷优化算法,融合遗传算法中的交叉重组算子进行改进以加快收敛速度,提高种群多样性,并使用Levy飞行策略进行变步长移动以优化随机移动过程,增大探索空间,提高种群跳出局部最优的能力。任务分配仿真实验结果表明,提出的改进算法在前沿解的多样性、优越性及目标函数的收敛效果方面更具优势,能够有效求解多无人机在多约束环境的任务分配问题。
Abstract:
Unmanned aerial vehicle (UAV) reconnaissance is an important way to conduct military reconnaissance and gather intelligence in the future. The task allocation problem of UAVs under multiple constraints is a difficult point in collaborative reconnaissance. To address this issue,an improved multi-objective energy valley optimization algorithm (IMOEVO) is proposed. Firstly,focusing on the two aspects of energy consumption and target benefit,the energy consumption of different movement modes of UAVs in a three-dimensional scene and the impact of the execution efficiency of UAVs on task benefits are considered,and a multi-objective optimization problem model of UAV energy consumption and task benefits is established. Then,the energy valley optimization algorithm is extended and improved by combining the best particle selection strategy and the Pareto front elite optimization strategy,and the crossover and re-combination operators in genetic algorithms are integrated for improvement to accelerate the convergence speed,enhance the diversity of the population,and the Levy flight strategy is used for variable step size movement to optimize the random movement process,expand the exploration space, and enhance the ability of the population to escape from local optima. The simulation results of the task allocation ex-periment show that the improved algorithm proposed has more advantages in the diversity and superiority of the frontier solutions and theconvergence effect of the objective function,and can effectively solve the task allocation problem of multiple UAVs in a multi-constraint environment.

相似文献/References:

[1]江 雪,赵 亮.多无人机辅助移动边缘计算中的轨迹优化[J].计算机技术与发展,2023,33(05):110.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 017]
　JIANG Xue,ZHAO Liang.Trajectory Scheduling for Multi-UAV Assisted Mobile Edge Computing[J].,2023,33(10):110.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 017]

更新日期/Last Update: 2025-10-10