基于改进EKF与GBNN的双层动态目标围捕算法

doi:10.12305/j.issn.1001-506X.2026.04.27

系统工程与电子技术 ›› 2026, Vol. 48 ›› Issue (4): 1386-1395.doi: 10.12305/j.issn.1001-506X.2026.04.27

• 制导、导航与控制 • 上一篇

基于改进EKF与GBNN的双层动态目标围捕算法

孙骞¹^,²^,*, 周星宇¹^,², 赵伟洋¹^,², 简鑫¹^,²

1. 哈尔滨工程大学信息与通信工程学院，黑龙江哈尔滨 150001
2. 哈尔滨工程大学先进船舶通信与信息技术重点实验室，黑龙江哈尔滨 150001

收稿日期:2025-03-19 修回日期:2025-05-12 出版日期:2025-12-10 发布日期:2025-12-10
通讯作者: 孙骞
作者简介:周星宇（2001—），男，硕士研究生，主要研究方向为多智能体路径规划
赵伟洋（2000—），男，硕士研究生，主要研究方向为多智能体协同搜索
简　鑫（2001—），男，硕士研究生，主要研究方向为多传感器融合技术
基金资助:
国家自然科学基金（52271311）；黑龙江省优秀青年科学基金（YQ2024F017）；中央高校基本科研业务费（3072024XX0802）资助课题

Double layer dynamic target capture algorithm based on improved EKF and GBNN

Qian SUN¹^,²^,*, Xingyu ZHOU¹^,², Weiyang ZHAO¹^,², Xin JIAN¹^,²

1. College of Information and Communication Engineering，Harbin Engineering University，Harbin 150001，China
2. Key Laboratory of Advanced Marine Communication and Information Technology，Harbin Engineering University，Harbin 150001，China

Received:2025-03-19 Revised:2025-05-12 Online:2025-12-10 Published:2025-12-10
Contact: Qian SUN

摘要/Abstract

摘要：

水下动态目标围捕任务具有能量受限、高实时性、强对抗的特点，针对多水下自主潜航器（autonomous underwater vehicle，AUV）系统在围捕任务中面临的效率低、协同性差的问题，提出了一种双层动态目标围捕算法。首先，根据围捕者与目标之间的速度关系，将阿波罗尼奥斯圆原理扩展至三维空间，使围捕更贴近实际场景。其次，针对声纳系统固有的探测误差问题，设计一种自适应卡尔曼滤波器，在有效抑制噪声干扰的同时对目标AUV的运动轨迹进行实时预测。然后，重构Glasius生物启发神经网络的神经元活性传播机制，优化决策过程以提高任务执行效率。最后，通过仿真实验验证了该围捕算法的有效性和优越性。

关键词: 动态目标围捕, 阿波罗尼奥斯圆, 自适应卡尔曼滤波, Glasius生物启发神经网络

Abstract:

Aiming at the characteristics of energy limitation, high real-time performance, and strong confrontation in underwater dynamic target capture tasks, a two-layer dynamic target capture algorithm is proposed to solve the problems of low efficiency and poor collaboration faced by multi autonomous underwater vehicle （AUV） systems in capture tasks. Firstly, based on the velocity relationship between the pursuer and the target, the Apollonian circle principle is extended to three-dimensional space to make the encirclement more realistic. Secondly, in response to the inherent detection error problem of sonar systems, an adaptive Kalman filter is designed to effectively suppress noise interference while predicting the real-time motion trajectory of the target AUV. Then, reconstruct the neural activity propagation mechanism of Glasius bio-inspired neural network and optimize the decision-making process to improve task execution efficiency. Finally, the effectiveness and superiority of the encirclement algorithm were verified through simulation experiments.

Key words: dynamic target capture, apollonius circle, adaptive Kalman filter, Glasius bio-inspired neural networks

中图分类号:

孙骞, 周星宇, 赵伟洋, 简鑫. 基于改进EKF与GBNN的双层动态目标围捕算法[J]. 系统工程与电子技术, 2026, 48(4): 1386-1395.

Qian SUN, Xingyu ZHOU, Weiyang ZHAO, Xin JIAN. Double layer dynamic target capture algorithm based on improved EKF and GBNN[J]. Systems Engineering and Electronics, 2026, 48(4): 1386-1395.

图/表 18

图1

图2

图3

表1

表2

图4

图5

图6

图7

图8

表3

表4

图9

图10

表5

表6

图11

图12

参考文献 36

1	LI L, LI Y P, WANG Y L, et al. Multi-AUV coverage path planning algorithm using side-scan sonar for maritime search[J]. Ocean Engineering, 2024, 300, 117396. doi: 10.1016/j.oceaneng.2024.117396
2	ZHANG Y X, WANG Q, SHEN Y, et al. Multi-AUV cooperative search method based on dynamic optimal coverage[J]. Ocean Engineering, 2023, 288, 116168. doi: 10.1016/j.oceaneng.2023.116168
3	YAO P, QIU L Y, QI J P, et al. AUV path planning for coverage search of static target in ocean environment[J]. Ocean Engineering, 2021, 241, 110050. doi: 10.1016/j.oceaneng.2021.110050
4	ZHANG Y X, LI Y P, LI S, et al. Multi-target tracking in underwater multistatic AUV networks with a robust Poisson multi-Bernoulli filter[J]. Ocean Engineering, 2023, 284, 115167. doi: 10.1016/j.oceaneng.2023.115167
5	CUI J K, HOU M X, PENG Z, et al. Hamiltonian based AUV navigation using adaptive finite-time trajectory tracking control[J]. Ocean Engineering, 2025, 320, 120329. doi: 10.1016/j.oceaneng.2025.120329
6	GUO Y Y, QIN H D, XU B, et al. Composite learning adaptive sliding mode control for AUV target tracking[J]. Neurocomputing, 2019, 351, 180- 186. doi: 10.1016/j.neucom.2019.03.033
7	ZHAO Z Y, FENG X L, JIANG C, et al. Distributed short-term predictive control for AUV clusters in underwater cooperative hunting tasks[J]. Ocean Engineering, 2024, 301, 117343. doi: 10.1016/j.oceaneng.2024.117343
8	YU J B, CHEN Z H, ZHAO Z Y, et al. A cooperative hunting method for multi-USVs based on trajectory prediction by OR-LSTM[J]. IEEE Trans. on Vehicular Technology, 2024, 73 (12): 18087- 18101. doi: 10.1109/TVT.2024.3432739
9	CAO Z Q, TAN M, LI L, et al. Cooperative hunting by distributed mobile robots based on local interaction[J]. IEEE Trans. on Robotics, 2006, 22 (2): 402- 406. doi: 10.1109/TRO.2006.862495
10	SUN Z Y, SUN H B, LI P, et al. Cooperative strategy for pursuit-evasion problem in the presence of static and dynamic obstacles[J]. Ocean Engineering, 2023, 279, 114476. doi: 10.1016/j.oceaneng.2023.114476
11	CUI Y F, XU J, WEN X, et al. Anti-disturbance cooperative formation containment control for multiple autonomous underwater vehicles with actuator saturation[J]. Ocean Engineering, 2022, 266, 113026. doi: 10.1016/j.oceaneng.2022.113026
12	HU J Q, WU H S, ZHAN R J, et al. Self-organized search-attack mission planning for UAV swarm based on wolf pack hunting behavior[J]. Journal of Systems Engineering and Electronics, 2021, 32 (6): 1463- 1476. doi: 10.23919/JSEE.2021.000124
13	HUANG Z R, ZHU D Q, SUN B. A multi-AUV cooperative hunting method in 3-D underwater environment with obstacle[J]. Engineering Applications of Artificial Intelligence, 2016, 50, 192- 200. doi: 10.1016/j.engappai.2016.01.036
14	PENG Y, ZHAO Z Y. Improved Glasius bio-inspired neural network for target search by multi-agents[J]. Information Sciences, 2021, 568, 40- 53. doi: 10.1016/j.ins.2021.03.056
15	ZHANG A, WANG W H, BI W H, et al. A path planning method based on deep reinforcement learning for AUV in complex marine environment[J]. Ocean Engineering, 2024, 313, 119354. doi: 10.1016/j.oceaneng.2024.119354
16	江涌, 王林波, 王蒙一, 等. 基于覆盖理论的高速强机动目标协同围捕策略[J]. 工程科学学报, 2024, 46 (7): 1169- 1178.
	JIANG Y, WANG L B, WANG M Y, et al. Collaborative capture strategy for high-speed and highly maneuverable targets based on coverage theory[J]. Journal of Engineering Science, 2024, 46 (7): 1169- 1178.
17	HUA X, LIU J, ZHANG J J, et al. An apollonius circle based game theory and Q-learning for cooperative hunting in unmanned aerial vehicle cluster[J]. Computers and Electrical Engineering, 2023, 110, 108876. doi: 10.1016/j.compeleceng.2023.108876
18	HASAN A, ASFIHANI T, OSEN O, et al. Leveraging digital twins for fault diagnosis in autonomous ships[J]. Ocean Engineering, 2024, 292, 116546. doi: 10.1016/j.oceaneng.2023.116546
19	盛孟刚, 娄兴, 陈洋卓, 等. 基于最优传播路径的EMA/EKF定位算法研究[J]. 导航定位与授时, 2022, 9 (6): 141- 149.
	SHENG M G, LOU X, CHEN Y Z, et al. Research on EMA/EKF positioning algorithm based on optimal propagation path[J]. Navigation and Timing, 2022, 9 (6): 141- 149.
20	MOHAMMAD M, NAIARI A, HOSSEYNZADEH M. Passive tracking of a target based on supervisory adaptive EKF and CKF[C]//Proc. of the IEEE 17th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI, 2020.
21	AKHLAGHI S, ZHOU N, HUANG Z Y. Adaptive adjustment of noise covariance in Kalman filter for dynamic state estimation[C]//Proc. of the IEEE Power & Energy Society General Meeting, 2017.
22	DO H V, KIM Y H, KWON Y S, et al. An adaptive approach based on multi-state constraint Kalman filter for UAVs[C]//Proc. of the 21st International Conference on Control, Automation and Systems, 2021: 481−485.
23	YAO P, WU K Q, LOU Y T. Path planning for multiple unmanned surface vehicles using Glasius bio-inspired neural network with Hungarian algorithm[J]. IEEE Systems Journal, 2022, 17 (3): 3906- 3917.
24	DU H G, SONG Y P, ZHOU J W, et al. A novel parameter estimation method for polynomial phase signals via adaptive EKF[J]. IEEE Internet of Things Journal, 2024, 11 (11): 20816- 20830. doi: 10.1109/JIOT.2024.3373642
25	CHEN L, JIANG B W, LIU Y Q, et al. Application of adaptive EKF in real-time orbit determination[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2021, 43 (4): 187. doi: 10.1007/s40430-021-02867-z
26	LIU J J, CHEN H M, LIU N B. Effective sage-Husa Kalman filter for SINS/ Doppler/ platform compass integrated navigation system [C]//Proc. of the IEEE Chinese Guidance, Navigation and Control Conference, 2016: 541−546.
27	ZHAO W Q, WEI H Q, AI Q, et al. Real-time model predictive control of path-following for autonomous vehicles towards model mismatch and uncertainty[J]. Control Engineering Practice, 2024, 153, 106126. doi: 10.1016/j.conengprac.2024.106126
28	LIPPIELLO V, SICILIANO B, VILLANI L. Adaptive extended Kalman filtering for visual motion estimation of 3D objects[J]. Control Engineering Practice, 2007, 15 (1): 123- 134. doi: 10.1016/j.conengprac.2006.05.006
29	YI L, WAN A Y S, LE A V, et al. Complete coverage path planning for reconfigurable omni-directional mobile robots with varying width using GBNN（n）[J]. Expert Systems with Applications, 2023, 228, 120349. doi: 10.1016/j.eswa.2023.120349
30	CAO X, SUN H B, JAN G E. Multi-AUV cooperative target search and tracking in unknown underwater environment[J]. Ocean Engineering, 2018, 150, 1- 11. doi: 10.1016/j.oceaneng.2017.12.037
31	MUTHUGALA M A V J, SAMARAKOON S M B P, ELARA M R. Toward energy-efficient online complete coverage path planning of a ship hull maintenance robot based on glasius bio-inspired neural network[J]. Expert Systems with Applications, 2022, 187, 115940. doi: 10.1016/j.eswa.2021.115940
32	LI Y B, HUANG Y J, ZOU Z L, et al. Multi-AUV underwater static target search method based on consensus-based bundle algorithm and improved Glasius bio-inspired neural network[J]. Information Sciences, 2024, 673, 120684. doi: 10.1016/j.ins.2024.120684
33	WANG Y C, LI J L, ZHAO S Q, et al. Hybrid path planning for USV with kinematic constraints and COLREGS based on improved APF-RRT and DWA[J]. Ocean Engineering, 2025, 318, 120128. doi: 10.1016/j.oceaneng.2024.120128
34	GLASIUS R, KOMODA A, GIELEN S C A M. Neural network dynamics for path planning and obstacle avoidance[J]. Neural Networks, 1995, 8 (1): 125- 133. doi: 10.1016/0893-6080(94)E0045-M
35	CHEN M Z, ZHU D Q. A novel cooperative hunting algorithm for inhomogeneous multiple autonomous underwater vehicles[J]. IEEE Access, 2018, 6, 7818- 7828. doi: 10.1109/ACCESS.2018.2801857
36	HUANG Z R, ZHU D Q. A cooperative hunting algorithm of multi-AUV in 3-D dynamic environment[C]//Proc. of the 27th Chinese Control and Decision Conference, 2015: 2571−2575.

符号	含义	值
$ \tau /\mathrm{m} $	栅格分辨率	10
${\chi \mathord{\left/ {\vphantom {\chi \mathrm{m}}} \right.} \mathrm{m}}$	涡旋中心坐标	(500, 0), (500, 500), (250, 150), (0, 300), (100, 550), (50, 50)
$\varOmega $	涡旋强度	−1, 1, −1, 1, 1, −1
${{{r_c}} \mathord{\left/ {\vphantom {{{r_c}} \mathrm{m}}} \right. } \mathrm{m}}$	涡旋半径	60, 80, 60, 120, 80, 120
${{{v_a}} \mathord{\left/ {\vphantom {{{v_a}} {(\mathrm{m}/\mathrm{s})}}} \right. } {(\mathrm{m}/\mathrm{s})}}$	围捕AUV的推进速度	1
${{{v_{\mathrm{tar}}}} \mathord{\left/ {\vphantom {{{v_{tar}}} {(\mathrm{m/s})}}} \right. } {(\mathrm{m/s})}}$	目标AUV的推进速度	0.5
$ \rho $	测量噪声矩阵的比例因子	0.99
$ \lambda $	过程噪声矩阵的更新因子	0.1
$ \delta $	平滑系数	0.9
$\eta $	连接权重衰减因子	0.95
$ \beta $	转化函数衰减因子	0.1
$ {G_m} $	栅格m被占据的惩罚	−10
$ \xi $	置信函数加权因子	0.6
$s$	均值池化核大小	5

算法	距离/m				围捕平均值
算法	AUV1	AUV2	AUV3	目标	距离/m	时间步
IEKF-IGBNN	421.6	486.9	359.2	213.9	422.6	496
GBNN_CBBA	607.8	665.8	536.9	348.6	603.5	652
GBNN_RES	649.4	710.9	586.5	367.8	648.9	698
GBNN_DIS	763.0	836.4	698.1	384.2	765.8	848
GBNN	1420.1	1096.9	1280.3	753.9	1265.8	1428

算法	最大总航行距离	最小总航行距离	平均航行距离
IEKF-IGBNN	1706	1269	1455
GBNN_CBBA	3150	1632	2162
GBNN_RES	2390	1400	1872
GBNN_DIS	2285	1343	1827
GBNN	4194	2712	3153

算法	最大航行时间	最小航行时间	平均航行时间
IEKF-IGBNN	629	496	552
GBNN_CBBA	1137	618	797
GBNN_RES	909	549	705
GBNN_DIS	862	522	680
GBNN	1581	1091	1237

算法	测量误差均值为5 m	测量误差均值为10 m	测量误差均值为15 m	测量误差均值为25 m
IEKF-IGBNN	1369	1407	1430	1513
GBNN_CBBA	1945	2171	2258	2344
GBNN_RES	1697	1730	2063	2462
GBNN_DIS	1924	1838	1801	2148
GBNN	3232	3046	3161	3715

基于改进EKF与GBNN的双层动态目标围捕算法

Double layer dynamic target capture algorithm based on improved EKF and GBNN

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 18

参考文献 36

相关文章 5

编辑推荐

Metrics

本文评价

[1]	赵云龙, 孙骞, 简鑫, 李一兵, 于飞. 基于改进EMD-CIIT降噪算法的INS/5G组合导航方法[J]. 系统工程与电子技术, 2024, 46(12): 4203-4212.
[2]	符小卫, 陈子浩. 基于一致性协议的多无人机协同围捕控制方法[J]. 系统工程与电子技术, 2021, 43(9): 2501-2507.
[3]	王志达, 薛林, 陈阳阳, 李建国. 引入测速信息的雷达导引头无偏转换跟踪方法[J]. 系统工程与电子技术, 2020, 42(8): 1695-1702.
[4]	葛宝爽, 张海, 晋燕琼. 基于冗余量测的GNSS多路径误差抑制算法[J]. 系统工程与电子技术, 2019, 41(11): 2581-2587.
[5]	于金涛,1,2,梁廷伟2. FLAKF在无陀螺惯性测量组合中的应用[J]. Journal of Systems Engineering and Electronics, 2009, 31(11): 2710-2713 .

算法	测量误差均值为5 m	测量误差均值为10 m	测量误差均值为15 m	测量误差均值为25 m
IEKF-IGBNN	531	541	551	573
GBNN_CBBA	730	732	839	883
GBNN_RES	731	653	774	932
GBNN_DIS	692	703	664	779
GBNN	1243	1182	1239	1424