| 59 | 0 | 153 |
| 下载次数 | 被引频次 | 阅读次数 |
针对多无人机协同任务分配中威胁环境复杂、任务负载不均衡及算法易陷入局部最优等问题，提出一种考虑混合威胁规避与负载均衡的多无人机任务分配算法。首先，面向侦察、攻击和评估三阶段协同任务，建立多无人机任务分配模型，综合考虑无人机能力、任务时序、弹药资源、航程限制、路径可行性及返航等约束。其次，构建由静态威胁惩罚和未攻击目标诱导风险惩罚组成的混合威胁模型，并采用参与任务无人机执行时间刻画负载均衡程度。在此基础上，以最大任务完成时间、混合威胁惩罚和负载均衡惩罚为优化目标，建立综合适应度函数。最后，在自适应多教师教与学优化算法（AMTLBO）框架下引入精英保留、自适应变异和负载感知局部搜索策略，以提高算法搜索能力和收敛稳定性。仿真结果表明，与遗传算法（GA）、教与学优化算法（TLBO）和AMTLBO相比，所提算法的综合适应度分别降低29.35%、4.73%和19.09%，最大任务完成时间分别降低12.70%、6.21%和24.54%，混合威胁惩罚分别降低9.15%、15.99%和29.58%，负载均衡惩罚分别降低63.37%、63.24%和62.55%。结果表明，所提算法能够在满足多类约束的前提下，实现任务效率、路径安全性和负载均衡之间的协调优化。
Abstract：To address the problems of complex threat environments, unbalanced task loads, and the tendency of optimization algorithms to fall into local optima in multi-UAV cooperative task assignment, a multi-UAV task assignment algorithm considering hybrid threat avoidance and load balancing is proposed. Firstly, a cooperative task assignment model for reconnaissance-attack-assessment missions is established, incorporating constraints such as UAV capability, task precedence, ammunition resources, range limitations, path feasibility, and return-to-platform requirements. Secondly, a hybrid threat model that integrates static threat penalties and unattacked-target-induced risk penalties is constructed, and the coefficient of variation of task execution time among participating UAVs is adopted to characterize load balancing. On this basis, a normalized weighted fitness function is formulated with maximum mission completion time, hybrid threat penalty, and load balancing penalty as optimization objectives. Finally, elitism preservation, adaptive mutation, and load-aware local search strategies are incorporated into the adaptive multi-teacher teaching-learningbased optimization(AMTLBO) framework to enhance search capability and convergence stability. Simulation results demonstrate that, compared with GA, TLBO, and AMTLBO, the proposed algorithm reduces the comprehensive fitness by 29.35%, 4.73%, and 19.09%; decreases the maximum mission completion time by 12.70%, 6.21%, and 24.54%; lowers the hybrid threat penalty by 9.15%,15.99%, and 29.58%; and reduces the load balancing penalty by 63.37%, 63.24%, and 62.55%, respectively. The results indicate that the proposed algorithm achieves coordinated optimization among mission efficiency, path safety, and load balancing while satisfying multiple operational constraints.
[1]赵恩娇，莫小艳，王洪志，等.面向水面目标搜索的无人机-无人艇集群编队控制方法[J/OL].飞控与探测. 2026-4-15[2026-06-17]. https：//link. cnki. net/urlid/10.1567.TJ.20260414.1804.002.
[2]WANG J Z, SU Y F, SHEN L, et al. Real-time automatic route generation for unmanned aerial vehicle based patrol inspection in power distribution system[C]//2022 IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference, Beijing,China, October 3-5, 2022.
[3]郭超勐，张振华，边疆，等.面向合围作战场景的多无人机任务规划方法[J].火力与指挥控制，2026,51(1):165-175.
[4]方伟，田源，徐涛，等.基于多智能体强化学习的无人机集群协同综述[J/OL].计算机工程与应用.2026-5-13[2026-06-17]. https：//link. cnki. net/urlid/11.2127.TP.20260513.1337.028.
[5]BAI X, WANG P, WANG Z Y, et al. 3D multi-uav collaboration based on the hybrid algorithm of artificial bee colony and A*[C]//2019 Chinese Control Conference, Guangzhou, China, July 27-30, 2019.
[6]郭常员，李永福，莫淄麟，等.低空无人机编队协同控制技术综述[J/OL].重庆邮电大学学报（自然科学版）. 2026-04-30[2026-06-17]. https：//link.cnki.net/urlid/50.1181.N.20260430.1313.012.
[7]DONG H, WU N, FENG G S, et al. Research on computing task allocation method based on multi-uavs collaboration[C]//2020 IEEE International Conference on Smart Internet of Things, Beijing, China, August 14-16, 2020.
[8]WANG F, YANG H, MENG Q X. A three-dimensional coverage path planning method for multi-UAV collaboration[C]//2023 30th International Conference on Geoinformatics, London, United Kingdom, July 19-21,2023.
[9]刘正元，吴元清，李艳洲，等.多无人机群任务规划和编队飞行的综述和展望[J].指挥与控制学报，2023, 9(6):623-636.
[10]YANG M, ZHANG B, SHI Z, et al. A hybrid task allocation approach for multi-UAV systems with complex constraints:A market-based bidding strategy and improved NSGA-III optimization[J]. The Journal of Supercomputing, 2025, 81:546.
[11]ZHOU Z, GUO Y, WANG Y, et al. Multi-UAV trajectory optimization under dynamic threats:An enhanced gwo algorithm integrating a priori and real-time data[J].International Journal of Computational Intelligence Systems, 2025, 18:140.
[12]ALQEFARI S, MENAI M E B. Multi-UAV task assignment in dynamic environments:Current trends and future directions[J]. Drones, 2025, 9(1):75.
[13]宁聪，范静，孙树魁.多无人机协同规划研究综述[J].计算机工程与应用，2025, 61(1):42-56.
[14]高谦，张玉良，曹艳.多无人机协同作战中的任务分配与路径规划算法研究[J].无线互联科技，2024,21(18):23-26.
[15]胡嘉薇，贾泽群，孙延涛，等.多约束条件下多无人机协同任务规划问题分析及求解方法综述[J].计算机科学，2023, 50(7):176-193.
[16]GAO Y K, WEI C H, MA X, et al. Multi-UAV cooperative search method based on multi-group ant colony algorithm[C]//2023 International Conference on CyberPhysical Social Intelligence, Xi’an, China, October20-23, 2023.
[17]WANG C, WEN X P, NIU Y F, et al. Dynamic task allocation for heterogeneous manned-unmanned aerial vehicle teamwork[C]//2018 Chinese Automation Congress(CAC), Xi’an, China, November 30-December 2,2018.
[18]MIRZA I S, SHAH S, SIDDIQI M Z, et al. Task assignment and path planning of multiple unmanned aerial vehicles using integer linear programming[C]//TENCON 2023-2023 IEEE Region 10 Conference, Chiang Mai, Thailand, October 31-November 3, 2023.
[19]PENG Q, WU H S, XUE R S. Review of dynamic task allocation methods for UAV swarms oriented to ground targets[J]. Complex System Modeling and Simulation,2021, 1(3):163-175.
[20]LIU P F, WANG B, LIU W J, et al. Multi-task allocation of multi-UAV coalition based on improved quantum genetic algorithm[C]//2021 40th Chinese Control Conference, Shanghai, China, July 26-28, 2021.
[21]纪硕磊，陈海林，李宇程，等.改进A*与遗传算法的无人机紫外巡检路径优化策略[J].测绘通报，2026,(3):137-141.
[22]钱戈，郭崴，许学吉，等.基于遗传算法对城市无人机起降场布局规划研究[J].山东航空学院学报，2025, 42(6):47-54.
[23]LI L, GU Q, LIU L. Research on path planning algorithm for multi-UAV maritime targets search based on genetic algorithm[C]//2020 IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, Chongqing, China, November 6-8, 2020.
[24]吴潇.基于改进教与学算法的多无人机协同路径规划方法研究[D].贵阳：贵州大学，2025.
[25]JIANG X H, WU X Y, ZHANG Z F, et al. Novel 3D UAV path planning for iot services based on interactive cylindrical vector teaching-learning optimization algorithm[J]. Sensors, 2025, 25(8):2407.
[26]GUNJI A B, DEEPAK B B B V L, BAHUBALENDRUNI C M V A R, et al. An optimal robotic assembly sequence planning by assembly subsets detection method using teaching learning-based optimization algorithm[J]. IEEE Transactions on Automation Science and Engineering, 2018, 15(3):1369-1385.
[27]YE F, CHEN J, TIAN Y, et al. Cooperative task assignment of a heterogeneous multi-UAV system using an adaptive genetic algorithm[J]. Electronics, 2020, 9(4):687.
基本信息:
DOI：10.19942/j.issn.2096-5915.2026.04.37
中图分类号:V279;TP18
引用信息:
[1]陈忍,李勇,任泽荣,等.考虑混合威胁与负载均衡的多无人机任务分配算法[J].无人系统技术,2026,9(04):1-16.DOI:10.19942/j.issn.2096-5915.2026.04.37.
基金信息:
陕西省重点研发计划项目(2024GX-ZDCYL-01-17)
2026-08-15
2026-08-15