无人机自主空中加油锥套检测与定位方法

doi:10.12305/j.issn.1001-506X.2026.03.26

Abstract

Abstract:

To address the issues of insufficient robustness in refueling drogue detection and low relative positioning accuracy in autonomous aerial refueling missions, a near-infrared vision-based method for refueling drogue detection and localization is proposed. Eight near-infrared light emitting diodes are installed on the refueling drogue as feature points, while a camera equipped with a near-infrared filter is deployed on the receiver aircraft as the vision system. Firstly, the captured images of the refueling drogue are preprocessed to extract connected regions. Secondly, a shape prior-driven neighborhood search method is proposed, integrating deep learning approaches for drogue position tracking prediction and elliptical feature fitting. Finally, the relative pose is calculated using the perspective-n-point algorithm, followed by fusion filtering processing. Experimental results demonstrate that the proposed method achieves high detection success rate, efficiency, and relative positioning accuracy, showing promising application prospects in practical aerial refueling missions.

Key words: autonomous aerial refueling, visual positioning, near-infrared, refueling drogue detection, ellipse fitting

CLC Number:

V 249.32

Jiapeng LI, Shuhui BU, Zhenyu XIA, Juboxi WANG, Kun LI, Xuan JIA. Drogue detection and localization methodology for UAV autonomous aerial refueling[J]. Systems Engineering and Electronics, 2026, 48(3): 1018-1030.

Figures/Tables 23

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Table 1

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

Table 2

Table 3

Fig.14

Table 4

Table 5

Table 6

Fig.15

Table 7

Fig.16

References 33

1	王旭峰, 董新民, 孔星炜, 等. 视觉辅助的无人机自主空中加油建模与仿真[J]. 飞行力学, 2013, 31 (4): 331- 335.
	WANG X F, DONG X M, KONG X W, et al. Visual-aided modeling and simulation of unmanned aerial vehicle autonomous aerial refueling[J]. Flight Dynamics, 2013, 31 (4): 331- 335.
2	WEN S Y, GAO Y, HU B R, et al. AARPose: real-time and accurate drogue pose measurement based on monocular vision for autonomous aerial refueling[J]. Chinese Journal of Aeronautics, 2025, 38 (6): 557- 577. doi: 10.1016/j.cja.2024.11.017
3	REN J R, QUAN Q. Progress in modeling and control of probe-and-drogue autonomous aerial refueling[J]. Chinese Journal of Aeronautics, 2024, 37 (5): 6- 26. doi: 10.1016/j.cja.2023.11.011
4	LI W, JIA J J, GAO Y K. Research review of the autonomous aerial refueling technology [C]//Proc. of the CSAA/IET Conference on Aircraft Utility Systems, 2024: 1345−1352.
5	TONG W, GU A, WU X Y, et al. Semi-supervised image domain adaption for aerial refueling drogue detection on embedded chip under foggy conditions[J]. IEEE Trans. on Automation Science and Engineering, 2025, 22, 4748- 4759.
6	杜昕, 朱喆, 胡芳芳, 等. 空中无人加油自主对接导航制导与控制 [J]. 航空学报, 2023, 44(20): 628827.
	DU X , ZHU Z, HU F F, et al. Guidance, navigation and control for airborne docking of autonomous aerial refueling [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(20): 628827.
7	吴傲, 李寰宇, 高杨军, 等. 面向巡逻阵位保持的空中加油管理时空协同方法[J]. 航空学报, 2023, 44 (20): 116- 145.
	WU A, LI H Y, GAO Y J, et al. Time-space coordination method for air refueling management for combat air patrol position maintenance[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44 (20): 116- 145.
8	宋梦实, 张帆, 黄攀峰. 位置约束下软式自主空中加油的抗干扰控制[J]. 航空学报, 2023, 44 (20): 76- 89.
	SONG M S, ZHANG F, HUANG P F. Anti-disturbance control of hose-drogue autonomous aerial refueling with position constraints[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44 (20): 76- 89.
9	NALEPKA J, HINCHMAN J. Automated aerial refueling: extending the effectiveness of UAVs [C]//Proc. of the AIAA Modeling and Simulation Technologies Conference and Exhibit, 2005: 6005.
10	KIMMETT J, VALASEK J, JUNKINS J L. Vision based controller for autonomous aerial refueling [C]//Proc. of the International Conference on Control Applications, 2002: 1138−1143.
11	付一方, 胡欣悦, 黄与陆, 等. 基于双目视觉的无人机自主空中对接系统[J]. 航空学报, 2023, 44 (20): 58- 75.
	FU Y F, HU X Y, HUANG Y L, et al. A binocular vision-based autonomous aerial docking system design for UAVs[J]. Acta Aeronautics et Astronautica Sinica, 2023, 44 (20): 58- 75.
12	李柱. 基于双目视觉的无人机自主空中加油对接导航方法[D]. 厦门: 厦门大学, 2017.
	LI Z. Binocular-vision-based docking navigation method for UAV self-refueling [D]. Xiamen: Xiamen University, 2017.
13	WANG X F, LI J M, KONG X W, et al. Towards docking safety analysis for unmanned aerial vehicle probe-drogue autonomous aerial refueling based on docking success-probability and docking reachability[J]. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 2018, 233 (11): 3893- 3905.
14	段海滨, 张奇夫, 邓亦敏, 等. 基于仿鹰眼视觉的无人机自主空中加油[J]. 仪器仪表学报, 2014, 35 (7): 1450- 1458.
	DUAN H B, ZHANG Q F, DENG Y M, et al. Biologically eagle-eye-based autonomous aerial refueling for unmanned aerial vehicles[J]. Chinese Journal of Scientific Instrument, 2014, 35 (7): 1450- 1458.
15	赵敏琨, 刘小雄, 徐新龙, 等. 基于视觉的空中加油定位技术研究[J]. 计算机测量与控制, 2023, 31 (6): 267- 273，279.
	ZHAO M K, LIU X X, XU X L, et al. Study on visual location technology for aerial refueling[J]. Computer Measurement & Control, 2023, 31 (6): 267- 273，279.
16	吴玲, 孙永荣, 赵科东. 一种自主空中加油视觉导航图像处理方法[J]. 科学技术与工程, 2021, 21 (20): 8552- 8557. doi: 10.3969/j.issn.1671-1815.2021.20.038
	WU L, SUN Y R, ZHAO K D. An image processing method of vision navigation for autonomous aerial refueling[J]. Science Technology and Engineering, 2021, 21 (20): 8552- 8557. doi: 10.3969/j.issn.1671-1815.2021.20.038
17	THOMAS P R, BHANDARI U, BULLOCK S, et al. Advances in air to air refueling[J]. Progress in Aerospace Sciences, 2014, 71, 14- 35. doi: 10.1016/j.paerosci.2014.07.001
18	VALASEK J, GUNNAM K, KIMMETT J, et al. Vision-based sensor and navigation system for autonomous air refueling[J]. Journal of Guidance, Control, and Dynamics, 2005, 28 (5): 979- 989.
19	FRAVOLINI M L, CAMPA G, NAPOLITANO M R. Evaluation of machine vision algorithms for autonomous aerial refueling for unmanned aerial vehicles[J]. Journal of Aerospace Computing, Information, and Communication, 2007, 4 (9): 968- 985. doi: 10.2514/1.17269
20	宋春华, 赵建涛, 刘虎成, 等. 基于近红外的自主空中加油相对位置解算[J]. 电力电子技术, 2013, 47 (1): 41- 43.
	SONG C H, ZHAO J T, LIU H C, et al. Relative position calculation based on near-informed for autonomous areial refueling[J]. Power Electronics, 2013, 47 (1): 41- 43.
21	吴腾飞, 周鑫, 袁锁中. 无人机软式自主空中加油视觉导航方法[J]. 测控技术, 2015, 34 (9): 17- 20.
	WU T F, ZHOU X, YUAN S Z. Vision-based navigation method for UAV autonomous probe and drogue aerial refueling[J]. Measurement & Control Technology, 2015, 34 (9): 17- 20.
22	SCHWEIGHOFER G, PINZ A. Robust pose estimation from a planar target[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2006, 28 (12): 2024- 2030. doi: 10.1109/TPAMI.2006.252
23	杨博文, 孙永荣, 黄斌, 等. 加油锥套远距图像的Hough-LS快速检测 [J]. 光电工程, 2015, 42(4): 44−48, 55.
	YANG B W, SUN Y R, HUANG B, et al. Hough-LS rapid detection for long-distance refueling drogue image [J], Opto-Electronic Engineering, 2015, 42(4): 44−48, 55.
24	周兆钦, 赵科东, 孙永荣, 等. 面向遮挡锥套的定位特征提取方法[J]. 电子测量与仪器学报, 2024, 38 (7): 208- 216.
	ZHOU Z Q, ZHAO K D, SUN Y R, et al. Localization feature extraction method for obscured drogue[J]. Journal of Electronic Measurement and Instrumentation, 2024, 38 (7): 208- 216.
25	WORTH D, CHOATE J, LYNCH J, et al. Relative vectoring using dual object detection for autonomous aerial refueling[J]. Neural Computing and Applications, 2024, 36 (17): 10143- 10163. doi: 10.1007/s00521-024-09589-y
26	YIN S L, YU J Y, SONG Y P, et al. Prediction of aerial refueling docking results by flying-wing UAV bow wave model established on CNN[J]. Aerospace Science and Technology, 2025, 157, 109760. doi: 10.1016/j.ast.2024.109760
27	周清, 许悦雷, 加尔肯别克. 无人机软管式自主空中加油视觉导航技术[J]. 导航定位与授时, 2020, 7 (1): 40- 47.
	ZHOU Q, XU Y L, JIA E. Visual navigation technology for UAV autonomous hose-drogue aerial refueling[J]. Navigation Positioning & Timing, 2020, 7 (1): 40- 47.
28	张宇博, 曹有权. 基于Faster R-CNN算法的自主空中加油锥套识别[J]. 现代导航, 2021, 12 (4): 297- 305.
	ZHANG Y B, CAO Y Q. Automatic identification of aerial refueling cone sleeve based on faster R-CNN algorithm[J]. Modern Navigation, 2021, 12 (4): 297- 305.
29	张怡, 孙永荣, 赵科东, 等. 空中加油场景下的目标联合检测跟踪算[J]. 计算机应用, 2022, 42 (9): 2893- 2899.
	ZHANG Y, SUN Y R, ZHAO K D, et al. Joint detection and tracking algorithm of target in aerial refueling scenes[J]. Journal of Computer Applications, 2022, 42 (9): 2893- 2899.
30	张西林, 何亚坤, 张恪易, 等. 面向自主空中加油任务的目标检测技术研究[J]. 航空科学技术, 2023, 34 (2): 64- 71.
	ZHANG X L, HE Y K, ZHANG K Y, et al. Object detection technology for autonomous air to air refueling[J]. Aeronautical Science & Technology, 2023, 34 (2): 64- 71.
31	冯杨, 张云皓, 赖劲雪, 等. 面向空中加油的视觉相对定位算法研究[J]. 仪表技术, 2023, (1): 38- 41.
	FENG Y, ZHANG Y H, LAI J X, et al. Research on relative positioning vision algorithm for aerial refueling[J]. Instrumentation Technology, 2023, (1): 38- 41.
32	LYU C, ZHANG W, HUANG H, et al. Rtmdet: an empirical study of designing real-time object detectors[EB/OL]. [2025-03-01]. https://doi.org/10.48550/arXiv.2212.07784.
33	汪刚志, 王新华, 陈冠宇, 等. 基于视觉的无人机空中加油目标识别技术研究[J]. 电子测量技术, 2020, 43 (13): 89- 94.
	WANG G Z, WANG X H, CHEN G Y, et al. Research on target recognition technology for aerial refueling of UAV based on vision[J]. Electronic Measurement Technology, 2020, 43 (13): 89- 94.

名称	型号	说明
工业面阵相机	海康机器人MV-CE060-10UC 工业面阵相机	分辨率为 3072×2048，采样帧率30 帧/秒
镜头	LOMOSEN ZX-SF03524C 工业视觉镜头	3.5 MM焦距2.4 F光圈
滤光片	850 nm近红外滤光片	厚度0.9 cm
机载运算设备	Inter NUC 12	CPU i7-1165G7内存 16 G，频率3200 MHz

参数名称	参数含义	数值
Epochs	训练总轮次	300
Input size	输入图像分辨率	640×640
Batch size	批量大小	16
Basic learning rate	基础学习率	0.0001
Weight decay	权重衰减	0.05

参数名称	结果数值
mAP@[.5∶.95]	90.1
mAP@.50	97.9
mAP@.75	96.7
小目标mAP	90.6
大目标mAP	92.1

图像帧数	特殊处理	椭圆拟合失败帧数	椭圆拟合失败后深度学习方法检测成功帧数	总失败帧数	总检测成功率/%
2000	无遮挡	17	7	10	99.5
300	遮挡1个LED灯	14	9	5	98.3
300	遮挡2个LED灯	20	8	12	96.0
300	遮挡3个LED灯	21	4	17	94.3
300	烟雾遮挡	12	2	10	96.7
300	高速运动	24	10	14	95.3

图像帧数	平均时间/ms	最长检测时间/ms	最短检测时间/ms	标准差
3500	24.6	30.7	19.6	1.42

Drogue detection and localization methodology for UAV autonomous aerial refueling

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 23

References 33

Related Articles 1

Recommended Articles

Metrics

Comments

图像帧数	平均时间/ms	最长时间/ms	最短时间/ms	标准差
3500	28.9	32.2	23.1	1.56

图像帧数	距离范围/m	平均误差/cm
图像帧数	距离范围/m	x	y	z
1 933	[0.00, 5.00）	6.40	2.15	2.72
	[5.00, 10.00）	8.42	3.98	4.03
	[10.00, 16.91）	9.34	5.52	5.17