Multi-UAV Collaborative Dynamic Search Decision-making Method for Unknown Moving Targets

FU Jinbo; ZHANG Dong; WANG Mengyang; DENG Jie

doi:10.12382/bgxb.2025.0057

您当前的位置：

首页 >

文章列表页 >

Multi-UAV Collaborative Dynamic Search Decision-making Method for Unknown Moving Targets

更新时间：2026-04-24

- Multi-UAV Collaborative Dynamic Search Decision-making Method for Unknown Moving Targets
- Acta Armamentarii Vol. 47, Issue 1, Pages: 250057(2026)
- 作者机构：
  
  西北工业大学航天学院，陕西西安 710072
  四川九洲电器集团有限责任公司，四川绵阳 621000
- 作者简介：
- 基金信息：
- DOI：10.12382/bgxb.2025.0057
  CLC： V249
- Received：16 January 2025，
  
  Online First：11 February 2026，
  
  Published：31 January 2026
- 稿件说明：
移动端阅览
FU Jinbo, ZHANG Dong, WANG Mengyang, et al. Multi-UAV Collaborative Dynamic Search Decision-making Method for Unknown Moving Targets[J]. Acta Armamentarii, 2026, 47(1): 250057.
DOI：

FU Jinbo, ZHANG Dong, WANG Mengyang, et al. Multi-UAV Collaborative Dynamic Search Decision-making Method for Unknown Moving Targets[J]. Acta Armamentarii, 2026, 47(1): 250057. DOI： 10.12382/bgxb.2025.0057.

摘要

为高效指引无人机群搜索指定区域内的多个未知动态目标，设计一种基于深度强化学习的预测驱动协同搜索决策方法（Deep Reinforcement Learning-Predictive Collaborative Search Decision Method

DRL-P-CSDM）。基于栅格化方法，综合环境信息和历史搜索信息构建环境信息图与信息确定性图，并通过设计时间衰减因子生成状态量，引导无人机进行区域重访以应对目标的主动规避，提升搜索效率。设计一个功能分区的深度神经网络架构，能够自主对环境进行预测，避免人工设计模型适配性差的问题。基于强化学习方法设计奖励函数，在稠密奖励中引入捕获概率，加速收敛过程，采用分布式架构，以适应任意数量无人机的部署要求，并在通信距离受限和信息更新延迟的情况下仍能完成任务。通过算法对比、鲁棒性分析以及半实物仿真验证新方法的有效性。仿真结果表明：DRL-P-CSDM在目标检获率上较传统深度强化学习方法提高11. 45%，任务完成时间减少48. 02%，无人机生存概率提高10. 31%；DRL-P-CSDM具有较强的综合性、鲁棒性和通用性，能在多尺度复杂环境下稳定运行，不受集群规模限制，在安全监控、战场侦察、林区巡检和灾后救援等领域具有广泛的工程应用价值。

Abstract

In order to efficiently guide an unmanned aerial vehicle (UAV) swarm to search multiple unknown dynamic targets within a designated area

a deep reinforcement learning-based predictive-driven collaborative search decision-making method (DRL-P-CSDM ) is proposed. The proposed method integrates environmental and historical search information to construct the environmental information maps and information determinacy maps based on a grid-based approach. A time-decaying window is designed to generate state variables

guiding UAVs to revisit regions and counteract the active evasion of targets

thereby improving search efficiency. A deep neural network architecture is designed

which incorporates the target location prediction

survival decision-making and action judgment functionalities. This architecture enables autonomous environmental prediction

eliminating the issue of poor adaptability caused by manually designed models. A reward function is formulated based on reinforcement learning

where a capture probability is introduced into a dense reward framework to accelerate the convergence process. A distributed architecture is used to be capable of accommodating arbitrary numbers of UAVs

and still completing the task under the conditions of limited communication distance and delayed information update. The effectiveness of the proposed method is validated through algorithm comparison

robustness analysis

and semi-physical simulation. Simulated results show that the DRL-P-CSDM improves the target detection rate by 13. 72%

reduces the mission completion time by 48. 65%

and increases the UAV survival probability by 14. 86%. This method demonstrates strong comprehensiveness

robustness and versatility. It is capable of stable operation in multi-scale complex environments and is not limited by the size of UAV swarm. It holds broad engineering application potential in fields such as security monitoring

battlefield reconnaissance

forest area inspection

and post-disaster rescue operations.

关键词

Keywords

references

DANOY G, BRUST M R, BOUVRY P. Connectivity stability in autonomous multi-level UAV swarms for wide area monitoring[C]∥Proceedings of the 5th ACM Symposium on Development and Analysis of Intelligent Vehicular Networks and Applications. Cancun, Mexico:Association for Computing Machinery,2015:1-8.

甄子洋.无人机集群作战协同控制与决策[M].北京：国防工业出版社，2021.

ZHEN Z Y.Cooperative control and decision-making for UAV swarm operations[M].Beijing:National Defense Industry Press, 2021.（in Chinese）

LI Y M, MA M Q, CAO J, et al. A method for multi-AUV cooperative area search in unknown environment based on reinforcement learning [J]. Journal of Marine Science and Engineering,2024,12:1194.

ZHAN H W, ZHANG Y, HUANG J B, et al. A reinforcement learning-based evolutionary algorithm for the unmanned aerial vehicles maritime search and rescue path planning problem considering multiple rescue centers [J]. Memetic Computing,2024,16:373-386.

侯岳奇，梁晓龙，何吕龙，等.未知环境下无人机集群协同区域搜索算法[J].北京航空航天大学学报，2019,45（2）:347-356.

HOU Y Q, LIANG X L, HE L L, et al.Cooperative area search algorithm for UAV swarms in unknown environment[J].Journal of Beijing University of Aeronautics and Astronautics,2019,45（2）:347-356.（in Chinese）

王宁，李哲，梁晓龙，等.通信距离受限条件下的无人机集群协同区域搜索[J].系统工程与电子技术，2022,44（5）:1615-1625.

WANG N, LI Z, LIANG X L, et al.Cooperative region search of UAV swarm with limited communication distance[J].Systems Engineering and Electronics,2022,44（5）:1615-1625.（in Chinese）

张哲璇，龙腾，徐广通，等.重访机制驱动的多无人机协同动目标搜索方法[J].航空学报，2020,41（5）:323314.

ZHANG Z X, LONG T, XU G T, et al.Revisit mechanism driven multi-UAV cooperative search planning method for moving targets [J].Acta Aeronautica et Astronautica Sinica, 2020, 41（5）:323314.（in Chinese）

WANG Z, LIU L, LONG T, et al. Multi-UAV reconnaissance task allocation for heterogeneous targets using an opposition-based genetic algorithm with double-chromosome encoding [J]. Chinese Journal of Aeronautics,2018,31（2）:339-350.

曾国奇，白宇，林伟，等.地面运动目标的多UAV协同搜索方法[J].系统工程与电子技术，2018,40（7）:1498-1505.

ZENG G Q, BAI Y, LIN W, et al.Multi-UAV cooperative search method for ground moving targets[J].Systems Engineering and Electronics,2018,40（7）:1498-1505.（in Chinese）

于驷男，周锐，夏洁，等.多无人机协同搜索区域分割与覆盖[J].北京航空航天大学学报，2015,41（1）:167-173.

YU S N, ZHOU R, XIA J, et al.Decomposition and coverage of multi-UAV cooperative search area [J].Journal of Beijing University of Aeronautics and Astronautics,2015,41（1）:167-173.（in Chinese）

戴健，许菲，陈琪锋.多无人机协同搜索区域划分与路径规划[J].航空学报，2020,41（增刊1）:723770.

DAI J, XU F, CHEN Q F.Multi-UAV cooperative search on region division and path planning [J].Acta Aeronautica et Astronautica Sinica,2020,41（S1）:723770.（in Chinese）

PHUNG M D, HA Q P. Safety-enhanced UAV path planning with spherical vector-based particle swarm optimization [J]. Applied Soft Computing,2021,107:107376.

赖幸君，唐鑫，林磊，等.基于差分进化粒子群混合算法的多无人机协同区域搜索策略[J].弹箭与制导学报，2024, 44（1）:89-97.

LAI X J, TANG X, LIN L, et al.Multi-UAV collaborative area search strategy based on differential evolution particle swarm mixing algorithm[J].Journal of Projectiles, Rockets, Missiles and Guidance,2024,44（1）:89-97.（in Chinese）

LUO D L, SHAO J, XU Y, et al. Coevolution pigeon-inspired optimization with cooperation-competition mechanism for multi-UAV cooperative region search [J]. Applied Sciences, 2019, 9（5）:827.

DUAN H B, ZHAO J X, DENG Y M, et al. Dynamic discrete pigeon-inspired optimization for multi-UAV cooperative search-attack mission planning[J]. IEEE Transactions on Aerospace and Electronic Systems,2021,57（1）:706-720.

闫川，甄子洋，张继豪，等.突防飞行与多区域搜索一体化侦察航迹规划[J].飞行力学，2023,41（1）:20-26,46.

YAN C, ZHEN Z Y, ZHANG J H, et al.Integrated reconnaissance path planning of penetration flight and multi area search[J].Flight Dynamics,2023,41（1）:20-26,46.（in Chinese）

ZHEN Z Y, ZHU P, XUE Y X, et al. Distributed intelligent self-organized mission planning of multi-UAV for dynamic targets cooperative search-attack [J]. Chinese Journal of Aeronautics, 2019,32（12）:2706-2716.

彭辉，沈林成，朱华勇.基于分布式模型预测控制的多UAV协同区域搜索[J].航空学报，2010,31（3）:593-601.

PENG H, SHEN L C, ZHU H Y.Multi-UAV cooperative area search based on distributed model predictive control[J].Acta Aeronautica et Astronautica Sinica,2010,31（3）:593-601.（in Chinese）

刘重，高晓光，符小卫.带信息素回访机制的多无人机分布式协同目标搜索[J].系统工程与电子技术，2017,39（9）:1998-2011.

LIU C, GAO X G, FU X W.Multi-UAV distributed cooperative target search algorithm with controllable revisit mechanism based on digital pheromone[J].Systems Engineering and Electronics, 2017,39（9）:1998-2011.（in Chinese）

刘重，高晓光，符小卫，等.未知环境下异构多无人机协同搜索打击中的联盟组建[J].兵工学报，2015,36（12）:2284-2297.

LIU C, GAO X G, FU X W, et al.Coalition formation of multiple heterogeneous unmanned aerial vehicles in cooperative search and attack in unknown environment[J].Acta Armamentarii,2015, 36（12）:2284-2297.（in Chinese）

卢卓，吴启晖，周福辉.有人机/无人机智能协同目标搜索和轨迹规划算法[J].通信学报，2024,45（1）:31-40.

LU Z, WU Q H, ZHOU F H.Algorithm for intelligent cooperative target search and trajectory planning of MAV/UAV[J].Journal on Communications,2024,45（1）:31-40.（in Chinese）

XIAO J P, PISUTSIN P, FEROSKHAN M. Collaborative target search with a visual drone swarm: an adaptive curriculum embedded multistage reinforcement learning approach[J]. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36（1）:313-327.

周文宏.无人机集群多目标搜索与跟踪问题的深度强化学习方法研究[D].长沙：国防科技大学，2021.

ZHOU W H.Research on deep reinforcement learning methods for multi-target search and tracking in UAV swarm[D].Changsha:National University of Defense Technology,2021.（in Chinese）

贾兆辉，朱镭，金明鑫，等.无人机载光电载荷自主侦察的参数计算与分析[J].应用光学，2024,45（5）:930-936.

JIA Z H, ZHU L, JIN M X, et al.Parameter calculation and analysis of autonomous reconnaissance of UAV-borne photoelectric payload[J].Journal of Applied Optics,2024,45（5）:930-936.（in Chinese）

HUANG Y, WEI G L, WANG Y X. VD D3QN: the variant of double deep Q-learning network with dueling architecture[C]∥Proceedings of the 37th Chinese Control Conference. Wuhan, China:IEEE,2018:9130-9135.

贾宏宇. XTDrone仿真环境中多无人机弱通信条件下协同搜索策略研究[D].成都：电子科技大学，2024.

JIA H Y. Research on cooperative search strategies for multiple unmanned aerial vehicles under weak communication conditions in the XTDrone simulation environment[D]. Chengdu:University of Electronic Science and Technology of China,2024.（in Chinese）

张栋，王洪涛，王孟阳，等.固定翼无人机集群虚实结合半实物仿真系统的设计与实现[J].无人系统技术，2022,5（5）:90-101.

ZHANG D, WANG H T, WANG M Y, et al.Design and implementation of hardware-in-the-loop simulation system based on virtual-real combination for fixed-wing UAVs swarms [J].Unmanned System Technology,2022,5（5）:90-101.（in Chinese）

傅晋博，张栋，王孟阳，等.面向目标定位精度提升的无人机航迹规划[J].兵工学报，2023,44（11）:3394-3406.

FU J B, ZHANG D, WANG M Y, et al.Unmanned aerial vehicle path planning for improved target positioning accuracy[J].Acta Armamentarii,2023,44（11）:3394-3406.（in Chinese）

张栋，王孟阳，唐硕.面向任务的无人机集群自主决策技术[J].指挥与控制学报，2022,8（4）:365-377.

ZHANG D, WANG M Y, TANG S.Autonomous decision-making technology for task-oriented UAV swarm[J].Journal of Command and Control,2022,8（4）:365-377.（in Chinese）

Views

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

DRL-based Active Disturbance Rejection Control Strategy for Integrated Guidance and Control

Safe-DRL: A Safety-conscious Deep Reinforcement Learning Decision-making Algorithm for Unmanned Platforms

Motion Control of Quadruped Robot Based on Deep Reinforcement Learning and Nonlinear Model Predictive Control Technique

Autonomous Multi-UAV Target Search Algorithm for Unknown Environments

Related Author

FU Jinbo

ZHANG Dong

WANG Mengyang

DENG Jie

WANG Wenwen

WU Mingyu

GAO Zhanpeng

HUANG Zhengui

Related Institution

Sichuan Jiuzhou Electric Appliance Group CO., LTD

National Key Laboratory of Transient Physics, Nanjing University of Science and Technology

School of energy and Power Engineering, Nanjing University of Science and Technology

School of Mechanical Engineering, Beijing Institute of Technology

Chinese Scholartree Ridge SKL, China Northern Vehicle Research Institute

Postal code：100089
Tel：010-68963060/68962718 Fax：010-68963025 Email：bgxb@cos.org.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05059581号-4 京公网安备11010802024360号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：119049 Visits Today：36

⁰