GNSS拒止下神经网络辅助的航天器集群协同导航
收稿日期: 2025-05-28
修回日期: 2025-06-27
录用日期: 2025-09-03
网络出版日期: 2025-09-05
基金资助
国家自然科学基金基础科学中心项目(62188101);国家重点研发计划(2024YFF0504702);国家自然科学基金(62273116);思源人工智能科学与技术协同创新联盟基金(HTKJ2023SY502003)
Neural network-assisted cooperative navigation of spacecraft clusters under GNSS denials
Received date: 2025-05-28
Revised date: 2025-06-27
Accepted date: 2025-09-03
Online published: 2025-09-05
Supported by
Science Center Program of National Natural Science Foundation of China(62188101);National Key Research and Development Program of China(2024YFF0504702);National Natural Science Foundation of China(62273116);SiYuan Collaborative Innovation Alliance of Artificial Intelligence Science and Technology(HTKJ2023SY502003)
针对航天器集群在轨自主导航时全球卫星导航系统(GNSS)短期拒止情况下的导航发散问题,引入航天器间基于数据链(DL)的相对测距系统及神经网络辅助系统,提升拒止期间导航品质。考虑到惯性导航系统(INS)、GNSS及DL系统采样频率不同,构建具有即插即用特点的因子图(FG)架构,并采用置信传播规则动态融合INS/GNSS/DL多源测量信息,实现多航天器协同导航。为避免数据链测距信息解算时的误差放大,设计基于旋转矩阵的相对测距信息解算方法;设计基于惯性积分状态及历史测量残差的复合故障诊断环节,结合因子图即插即用特点,实现GNSS故障及DL故障的检测与隔离;此外,针对GNSS拒止情况,设计广义回归神经网络(GRNN)与Elman神经网络(ENN)组合的辅助系统,对历史时刻GNSS与INS导航数据之间的潜在关系进行拟合,并对缺失GNSS导航数据进行在线预测与补偿。将GNSS预测数据与INS/DL数据进一步融合,获得GNSS拒止情况下的组合导航结果。仿真结果表明,在所设计的基于因子图的协同框架下,组合使用基于数据链的相对测距信息及GRNN-ENN神经网络辅助系统能有效缓解GNSS拒止情况下的导航发散情况。
刘明 , 吴姣 . GNSS拒止下神经网络辅助的航天器集群协同导航[J]. 航空学报, 2026 , 47(9) : 532303 -532303 . DOI: 10.7527/S1000-6893.2025.32339
To address the problems of navigation dispersion in the Global Navigation Satellite System (GNSS) short-term denial scenario during the on-orbit autonomous navigation of spacecraft clusters, we introduce a Data-Link-based (DL) relative ranging system and a neural network auxiliary module to improve the navigation effect under GNSS denial. Considering the different sampling frequencies of INS, GNSS, and DL systems, this paper constructs the Factor Graph (FG) architecture, which has the feature of plug-and-play, and adopts the belief propagation rules to dynamically fuse the multi-source measurement information of INS/GNSS/DL, enabling spacecraft cooperative positioning. To avoid the error amplification when solving the ranging information of the data links, a relative ranging information solving method based on the rotation matrix is designed. A composite fault diagnosis mechanism based on the inertial integral state and the historical measurement residuals is designed, which together with the plug-and-play characteristics of the FG, enables detection and isolation of the GNSS faults and DL faults. Moreover, for the GNSS denial case, an auxiliary system combining General Regression Neural Network (GRNN) and Elman Neural Network (ENN) is designed to fit the potential relationship between GNSS and INS navigation data at historical moments and provide an online prediction and compensation of missed GNSS navigation data. The predicted GNSS data are further fused with the INS/DL data to obtain the combined navigation results under the GNSS denial case. The simulation results show that the introduction of datalink-based relative ranging information and the GRNN-ENN neural network-assisted system can effectively mitigate the navigation divergence in the GNSS denial case.
| [1] | MO J R, HU S B, YAN T T, et al. Transmit power allocation with connectivity probability for multi-QoS in cluster flight spacecraft network[J]. Wireless Communications and Mobile Computing, 2020, 2020: 8676835. |
| [2] | 苏继东, 徐伟琳, 翟盛华, 等. 航天器自组网技术实践与展望[J]. 航空学报, 2024, 45(5): 529912. |
| SU J D, XU W L, ZHAI S H, et al. Practice and prospect of space AD hoc network technology[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(5): 529912 (in Chinese). | |
| [3] | 陈庆, 张锦绣, 曹喜滨. 集群航天器网络发展现状及关键技术[J]. 哈尔滨工业大学学报, 2017, 49(4): 1-7. |
| CHEN Q, ZHANG J X, CAO X B. Development status and key technology of spacecraft cluster network[J]. Journal of Harbin Institute of Technology, 2017, 49(4): 1-7 (in Chinese). | |
| [4] | 牛小骥, 班亚龙, 张提升, 等. GNSS/INS深组合技术研究进展与展望[J]. 航空学报, 2016, 37(10): 2895-2908. |
| NIU X J, BAN Y L, ZHANG T S, et al. Research progress and prospects of GNSS/INS deep integration[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(10): 2895-2908 (in Chinese). | |
| [5] | WANG X G, CUI N G, GUO J F. INS/VisNav/GPS relative navigation system for UAV[J]. Aerospace Science and Technology, 2013, 28(1): 242-248. |
| [6] | HARDY J, STRADER J, GROSS J N, et al. Unmanned aerial vehicle relative navigation in GPS denied environments[C]∥2016 IEEE/ION Position, Location and Navigation Symposium (PLANS). Piscataway: IEEE Press, 2016: 344-352. |
| [7] | 方文轩, 丛佃伟. 卫星/惯性/视觉组合导航多源融合技术现状及发展[J]. 无线电工程, 2022, 52(10): 1813-1820. |
| FANG W X, CONG D W. Status and development of multi-source information fusion technology for satellite/inertial/visual integrated navigation[J]. Radio Engineering, 2022, 52(10): 1813-1820 (in Chinese). | |
| [8] | 武成锋, 程进, 郭晓云, 等. 飞行器集群协同定位与导航对抗技术发展与展望[J]. 宇航学报, 2022, 43(2): 131-142. |
| WU C F, CHENG J, GUO X Y, et al. Development and prospect of aircraft clusters cooperative positioning and navigation countermeasures technology[J]. Journal of Astronautics, 2022, 43(2): 131-142 (in Chinese). | |
| [9] | 谢启龙, 宋龙, 鲁浩, 等. 协同导航技术研究综述[J]. 航空兵器, 2019, 26(4): 23-30. |
| XIE Q L, SONG L, LU H, et al. Review of Collaborative Navigation Technology[J]. Aero Weaponry, 2019, 26(4): 23-30 (in Chinese). | |
| [10] | 杜君南. 基于相对测量信息的集群飞行器协同导航关键技术研究[D]. 南京: 南京航空航天大学, 2021. |
| DU J N. Research on key technologies of cooperativenavigation of aircraft swarm based on relative measurement information[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2021 (in Chinese). | |
| [11] | 王振宇. 基于惯性/线激光三角测量组合的航天器相对导航技术[D]. 南京: 南京航空航天大学, 2017. |
| WANG Z Y. Relative navigation of spacecraft based on the combination of inertial navigation and linear laser triangulation[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2017 (in Chinese). | |
| [12] | 龚柏春, 王沙, 张伟夫, 等. 近地轨道航天器编队仅测距相对导航方法[J]. 宇航学报, 2022, 43(8): 1088-1096. |
| GONG B C, WANG S, ZHANG W F, et al. Range-only relative navigation for spacecraft formation in low earth orbit[J]. Journal of Astronautics, 2022, 43(8): 1088-1096 (in Chinese). | |
| [13] | 周子寒. 基于数据链相对信息的无人车协同导航与路径规划算法研究[D]. 南京: 南京航空航天大学, 2021: 18-22. |
| ZHOU Z H. Research on collaborative navigation and path planning algorithm of unmanned vehicle based on relative information assisted by data link[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2021: 18-22 (in Chinese). | |
| [14] | 高超, 黄郑, 赵轩, 等. 基于构型优选的5G集群无人机协同导航方法[J]. 2024(4): 981-990. |
| GAO C, HUANG Z, ZHAO X, et al. Collaborative navigation method for 5G cluster UAV based on configuration optimization [J]. 2024(4): 981-990 (in Chinese). | |
| [15] | 魏帅迎, 杜雨桐, 胡博, 等. GNSS拒止环境下UAV集群协同导航技术发展现状及分析[J]. 导航与控制, 2023, 22(4): 5-16. |
| WEI S Y, DU Y T, HU B, et al. Development status and analysis of UAV swarm cooperative navigation technology in GNSS-denied environment[J]. Navigation and Control, 2023, 22(4): 5-16 (in Chinese). | |
| [16] | 刘鹏, 田玉平, 张亚. 有限时间一致无迹Kalman滤波器[J]. 自动化学报, 2020, 46(7): 1357-1366. |
| LIU P, TIAN Y P, ZHANG Y. Finite-time consensus based unscented Kalman filter[J]. Acta Automatica Sinica, 2020, 46(7): 1357-1366 (in Chinese). | |
| [17] | XU Y, WANG K, YANG C, et al. GNSS/INS/OD/NHC adaptive integrated navigation method considering the vehicle motion state[J]. IEEE Sensors Journal, 2023, 23(12): 13511-13523. |
| [18] | 李杰, 陈帅, 王琮, 等. 基于因子图的无人机多源组合导航算法研究[J]. 航天控制, 2021, 39(1): 52-57. |
| LI J, CHEN S, WANG C, et al. Research on UAV multi-source integrated navigation algorithm based on factor graph[J]. Aerospace Control, 2021, 39(1): 52-57 (in Chinese). | |
| [19] | ALI J, FANG J C. SINS/ANS/GPS integration using federated Kalman filter based on optimized information-sharing coefficients[C]∥ AIAA Guidance, Navigation, and Control Conference and Exhibit. Reston: AIAA, 2005. |
| [20] | 戴海发, 卞鸿巍, 马恒, 等. 基于因子图的鲁棒性增量平滑算法的水面无人艇组合导航方法[J]. 中国惯性技术学报, 2018, 26(6): 778-786. |
| DAI H F, BIAN H W, MA H, et al. Application of robust incremental smoothing algorithm based on factor graph in integrated navigation of unmanned surface vehicle[J]. Journal of Chinese Inertial Technology, 2018, 26(6): 778-786 (in Chinese). | |
| [21] | FRASER C T, ULRICH S. Adaptive extended Kalman filtering strategies for spacecraft formation relative navigation[J]. Acta Astronautica, 2021, 178: 700-721. |
| [22] | 潘献飞, 宁治文, 王茂松, 等. 基于因子图的导航定位技术应用分析与思考[J]. 控制理论与应用, 2023, 40(12): 2130-2141. |
| PAN X F, NING Z W, WANG M S, et al. Analysis and reflection on the navigation and positioning application based on factor graph[J]. Control Theory Applications, 2023, 40(12): 2130-2141 (in Chinese). | |
| [23] | LOELIGER H A. An introduction to factor graphs[J]. IEEE Signal Processing Magazine, 2004, 21(1): 28-41. |
| [24] | 罗子岩, 陈帅, 王国栋, 等. 多源融合导航系统的因子图算法综述[J]. 导航与控制, 2021, 20(3): 9-16. |
| LUO Z Y, CHEN S, WANG G D, et al. A survey of factor graph algorithms for multi-source fusion navigation system[J]. Navigation and Control, 2021, 20(3): 9-16 (in Chinese). | |
| [25] | 牛皓飞, 蔡庆中, 李健, 等. 基于图优化的通信受限环境下协同导航方法[J]. 航空学报, 2023, 44(11): 327342. |
| NIU H F, CAI Q Z, LI J, et al. Method for cooperative navigation in constrained environment based on graph optimization[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(11): 327342 (in Chinese). | |
| [26] | 熊骏, 解相朋, 熊智, 等. 基于图模型的无人集群同步自定位与相对定位[J]. 航空学报, 2023, 44(S2): 729708. |
| XIONG J, XIE X P, XIONG Z, et al. Synchronized self-localization and relative-localization of unmanned swarms based on graph model [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S2): 729708. | |
| [27] | 陈恩庆, 肖素珍, 高新利. 因子图在卫星姿态估计中的应用[J]. 计算机仿真, 2015, 32(6): 63-66. |
| CHEN E Q, XIAO S Z, GAO X L. Estimation of satellite attitude angular velocity based on factor graph[J]. Computer Simulation, 2015, 32(6): 63-66 (in Chinese). | |
| [28] | 唐成凯, 张玲玲, 廉保旺. 基于因子图协同定位辅助的单星定位方法[J]. 系统工程与电子技术, 2017, 39(5): 1085-1090. |
| TANG C K, ZHANG L L, LIAN B W. Cooperation factor map of co-location aided single satellite navigation algorithm[J]. Systems Engineering and Electronics, 2017, 39(5): 1085-1090 (in Chinese). | |
| [29] | 南子寒, 刘大禹, 苏牡丹, 等. 拒止环境下基于LSTM神经网络的自主导航方法[J]. 中国惯性技术学报, 2025, 33(4): 331-339, 349. |
| NAN Z H, LIU D Y, SU M D, et al. Autonomous navigation method based on LSTM neural network in denial environment[J]. Journal of Chinese Inertial Technology, 2025, 33(4): 331-339, 349 (in Chinese). | |
| [30] | 李正帅, 缪玲娟, 周志强, 等. 神经网络修正的速度约束辅助车载SINS定位算法[J]. 宇航学报, 2022, 43(9): 1236-1245. |
| LI Z S, MIAO L J, ZHOU Z Q, et al. Vehicle SINS positioning algorithm assisted by velocity constraint based on neural network modification[J]. Journal of Astronautics, 2022, 43(9): 1236-1245 (in Chinese). | |
| [31] | FANG W, JIANG J G, LU S Q, et al. A LSTM algorithm estimating pseudo measurements for aiding INS during GNSS signal outages[J]. Remote Sensing, 2020, 12(2): 256. |
| [32] | 白相文, 杨建华, 杨志强. 神经网络辅助的组合导航算法研究[J]. 导航定位学报, 2020, 8(1): 93-98. |
| BAI X W, YANG J H, YANG Z Q. Research on neural network-assisted integrated navigation algorithm[J]. Journal of Navigation and Positioning, 2020, 8(1): 93-98 (in Chinese). | |
| [33] | ZHANG L, HSU L T, ZHANG T. A novel INS/USBL integrated navigation scheme via factor graph optimization[J]. IEEE Transactions on Vehicular Technology, 2022, 71(9): 9239-9249. |
| [34] | 赵仁杰, 李开龙, 胡柏青, 等. 基于改进四元数阻尼误差模型的SINS初始对准算法[J]. 系统工程与电子技术, 2021, 43(11): 3330-3337. |
| ZHAO R J, LI K L, HU B Q, et al. SINS initial alignment algorithm based on improved quaternion damping error model[J]. Systems Engineering and Electronics, 2021, 43(11): 3330-3337 (in Chinese). | |
| [35] | LI X, CHEN W, CHAN C, et al. Multi-sensor fusion methodology for enhanced land vehicle positioning[J]. Information Fusion, 2019, 46: 51-62. |
| [36] | WEN W S, HSU L T. Towards robust GNSS positioning and real-time kinematic using factor graph optimization[C]∥ 2021 IEEE International Conference on Robotics and Automation (ICRA). Piscataway: IEEE Press, 2021: 5884-5890. |
| [37] | 乔广欣, 张慧君, 李博, 等. GNSS驯服芯片级原子钟方法研究[J]. 导航定位与授时, 2022, 9(2): 153-159. |
| QIAO G X, ZHANG H J, LI B, et al. Research on the method of GNSS-disciplined chip-scale atomic clock[J]. Navigation Positioning and Timing, 2022, 9(2): 153-159 (in Chinese). | |
| [38] | 范世伟. 自主水下航行器协同定位算法研究[D]. 哈尔滨: 哈尔滨工业大学, 2020: 47-66. |
| FAN S W. Research on cooperative position algorithm for autonomous underwater vehicles [D]. Harbin: Harbin Institute of Technology, 2020: 47-66 (in Chinese). | |
| [39] | SPECHT D F. The general regression neural network-Rediscovered[J]. Neural Networks, 1993, 6(7): 1033-1034. |
| [40] | 陈秀德, 刘惠, 蔚保国, 等. 北斗/GNSS广域精密定位技术与服务: 现状与展望[J]. 武汉大学学报(信息科学版), 2025, 50(3): 413-429. |
| CHEN X D, LIU H, YU B G, et al. BeiDou/GNSS wide-area precise positioning technology and service: Current situation and prospects[J]. Geomatics and Information Science of Wuhan University, 2025, 50(3): 413-429 (in Chinese). | |
| [41] | 韩德强, 钟斌, 张龙平, 等. 基于星载单频BDS/GPS数据的实时低轨卫星定轨精度分析[C]∥第十二届中国卫星导航年会论文集. 北京:中国卫星导航系统管理办公室学术交流中心, 2021: 136-141. |
| HAN D Q, ZHONG B, ZHANG L P, et al. Accuracy analysis of real time LEO satellite orbit determination based on single frequency BDS/GPS data[C]∥12th China Satellite Navigation Conference (CSNC). Beijing: Academic Exchange Center of China Satellite Navigation Office, 2021: 136-141 (in Chinese). |
/
| 〈 |
|
〉 |