[1]PEI Jiaming,KONG Weili,YU Changdong,et al.A multi-UAV collaborative system and federated learning for target detection and tracking based on federated learning[J].CAAI Transactions on Intelligent Systems,2025,20(5):1158-1166.[doi:10.11992/tis.202412031]
Copy

A multi-UAV collaborative system and federated learning for target detection and tracking based on federated learning

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 20 Number of periods: 2025 5 Page number: 1158-1166 Column: 学术论文—机器感知与模式识别 Public date: 2025-09-05
Title:
A multi-UAV collaborative system and federated learning for target detection and tracking based on federated learning
Author(s):
PEI Jiaming1; 2;  KONG Weili3;  YU Changdong4;  WANG Lukun2
1. School of Computer Science, The University of Sydney, Sydney 2006, Australia;
2. Department of Intelligent Equipment, Shandong University of Science and Technology, Taian 271019, China;
3. College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China;
4. College of Artificial Intelligence, Dalian Maritime University, Dalian 116026, China
Keywords:
unmanned aerial vehicle; federated learning; target detection; communication; collaborative multi-UAV system; target tracking; cooperative system; coordination algorithm; neural network
CLC:
TP319
DOI:
10.11992/tis.202412031
Abstract:
This paper presents a multi-UAV collaborative system designed to achieve efficient and reliable target detection and tracking. The system employs and federated learning techniques to ensure balanced task allocation across different operational environments with high coverage rate, low redundancy and high efficiency. Extensive simulations and real-world experiments were conducted to evaluate the system’s performance in various scenarios, including open fields and complex urban areas under challenging conditions such as nighttime and rainy weather. Key metrics such as coverage rate, redundancy rate, task allocation balance, response time, and tracking continuity were used to assess the system’s effectiveness. The results demonstrate that while the system excels in simpler environments, it maintains robust performance in more demanding conditions, highlighting areas for further optimization. The paper concludes with discussions on deployment strategies and future research directions, particularly focusing on enhancing system adaptability in dynamic and GPS-denied environments.
References:
[1] SHAN Jinhuan, JIANG Wei, HUANG Yue, et al. Unmanned aerial vehicle (UAV)-based pavement image stitching without occlusion, crack semantic segmentation, and quantification[J]. IEEE transactions on intelligent transportation systems, 2024, 25(11): 17038-17053.
[2] AL RADI M, ALMALLAHI M N, AL-SUMAITI A S, et al. Progress in artificial intelligence-based visual servoing of autonomous unmanned aerial vehicles (UAVs)[J]. International journal of thermofluids, 2024, 21: 100590.
[3] ALAMI R, HACID H, BELLONE L, et al. SOREO: a system for safe and autonomous drones fleet navigation with reinforcement learning[J]. Proceedings of the AAAI conference on artificial intelligence, 2023, 37(13): 16398-16400.
[4] PEI Jiaming, YU Zhi, LIU Wenxuan, et al. Clustered federated learning multi-classifier for non-IID scenario in drone devices[C]//Proceedings of the 5th International ACM Mobicom Workshop on Drone Assisted Wireless Communications for 5G and beyond. Sydney: ACM, 2022: 79-84.
[5] MU Junsheng, ZHANG Ronghui, CUI Yuanhao, et al. UAV meets integrated sensing and communication: challenges and future directions[J]. IEEE communications magazine, 2023, 61(5): 62-67.
[6] LI Yiting, FAN Qingsong, HUANG Haisong, et al. A modified YOLOv8 detection network for UAV aerial image recognition[J]. Drones, 2023, 7(5): 304.
[7] NGUYEN X T, JEON G, VY V, et al. A hybrid approach for vision-based structural displacement measurement using transforming model prediction and KLT[J]. Mechanical systems and signal processing, 2025, 223: 111866.
[8] SAMY I, POSTLETHWAITE I, GU Dawei. Neural network based sensor validation scheme demonstrated on an unmanned air vehicle (UAV) model[C]//2008 47th IEEE Conference on Decision and Control. Cancun: IEEE, 2008: 1237-1242.
[9] WU Ying, CHEN Mou, LI Hongyi, et al. Event-triggered-based adaptive NN cooperative control of six-rotor UAVs with finite-time prescribed performance[J]. IEEE transactions on automation science and engineering, 2024, 21(2): 1867-1877.
[10] CUI Beibei, LIANG Liang, JI Baofeng, et al. Exploring the YOLO-FT deep learning algorithm for UAV-based smart agriculture detection in communication networks[J]. IEEE transactions on network and service management, 2024, 21(5): 5347-5360.
[11] SONG Zhe, ZHANG Yi, YU Yang, et al. Cooperative positioning algorithm based on manifold gradient filtering in UAV-WSN[J]. IEEE sensors journal, 2024, 24(8): 12676-12688.
[12] 姚元志. 区块链赋能的移动边缘计算辅助无人机系统性能优化研究[D]. 南昌: 南昌大学, 2024.
YAO Yuanzhi. Research on performance optimization of UAV system assisted by blockchain enabled mobile edge computing[D]. Nanchang: Nanchang University, 2024.
[13] 张艺龄, 张正华, 肖胜川, 等. 基于分布式控制的多无人机协作喷洒技术[J]. 信息技术, 2024, 48(4): 59-63, 69.
ZHANG Yiling, ZHANG Zhenghua, XIAO Shengchuan, et al. Collaborative spraying technology of multiple-UAVs based on distributed control[J]. Information technology, 2024, 48(4): 59-63, 69.
[14] 曹腾飞, 尹润天, 朱亮, 等. 个性化位置隐私保护技术综述[J]. 计算机科学, 2025, 52(5): 307-321.
CAO Tengfei, YIN Runtian, ZHU Liang, et al. Survey of personalized location privacy protection technologies[J]. Computer science, 2025, 52(5): 307-321.
[15] 苗可. 基于新型纵向联邦学习的隐私保护物联网数据共享方案[J]. 物联网技术, 2024, 14(9): 60-63, 68.
MIAO Ke. Privacy protection data sharing scheme for internet of things based on new vertical federated learning[J]. Internet of Things technologies, 2024, 14(9): 60-63, 68.
[16] 王华华, 黄烨霞, 李玲, 等. 无蜂窝网络中的联邦学习用户调度与资源优化[J/OL]. 计算机工程, 2024: 1-18. (2024-09-12). http://kns.cnki.net/KCMS/detail/detail.aspx?filename=JSJC20240911003&dbname=CJFD&dbcode=CJFQ.
WANG Huahua, HUANG Yexia, LI Ling, et al. Federated learning user scheduling and resource optimization in cellular-free networks[J/OL]. China industrial economics, 2024: 1-18. (2024-09-12). http://kns.cnki.net/KCMS/detail/detail.aspx?filename=JSJC20240911003&dbname=CJFD&dbcode=CJFQ.
[17] PEI Jiaming, LIU Wenxuan, LI Jinhai, et al. A review of federated learning methods in heterogeneous scenarios[J]. IEEE transactions on consumer electronics, 2024, 70(3): 5983-5999.
[18] PEI Jiaming, XUE Rubing, LIU Chao, et al. Toward Byzantine-resilient secure AI: a federated learning communication framework for 6G consumer electronics[J]. IEEE transactions on consumer electronics, 2024, 70(3): 5719-5728.
[19] YANG Qiang, LIU Yang, CHEN Tianjian, et al. Federated machine learning[J]. ACM transactions on intelligent systems and technology, 2019, 10(2): 1-19.
[20] 林瑞阳, 杨东升, 邱锋. Unscented卡尔曼滤波对目标位置预测[J]. 现代电子技术, 2014, 37(1): 34-37.
LIN Ruiyang, YANG Dongsheng, QIU Feng. Target position prediction of unscented Kalman filter[J]. Modern electronics technique, 2014, 37(1): 34-37.
[21] 徐琦, 蔡聪, 王熠钊. 一种基于数据融合的机动目标跟踪预测算法[J]. 系统仿真学报, 2011, 23(11): 2444-2448.
XU Qi, CAI Cong, WANG Yizhao. Forecast algorithm for tracking moving targets based on data fusion[J]. Journal of system simulation, 2011, 23(11): 2444-2448.
[22] MAHFOUZ S, MOURAD-CHEHADE F, HONEINE P, et al. Target tracking using machine learning and Kalman filter in wireless sensor networks[J]. IEEE sensors journal, 2014, 14(10): 3715-3725.
[23] HUANG Yecheng, CHEN Jiaxin, HUANG Di. UFPMP-det: toward accurate and efficient object detection on drone imagery[J]. Proceedings of the AAAI conference on artificial intelligence, 2022, 36(1): 1026-1033.
[24] XIA Guisong, BAI Xiang, DING Jian, et al. DOTA: a large-scale dataset for object detection in aerial images[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3974-3983.
[25] ZHU Pengfei, WEN Longyin, DU Dawei, et al. VisDrone-DET2018: the vision meets drone object detection in image challenge results[C]//Computer Vision–ECCV 2018 Workshops. Cham: Springer International Publishing, 2019: 437-468.
[26] ABADI M. TensorFlow: learning functions at scale[C]//Proceedings of the 21st ACM SIGPLAN International Conference on Functional Programming. Nara: ACM, 2016: 1.
Similar References:

Memo

-

Last Update: 2025-09-05

Copyright © CAAI Transactions on Intelligent Systems