[1]夏炎,潘树国,赵鹏飞,等.基于无监督学习的卫星NLOS信号检测方法[J].东南大学学报(自然科学版),2019,49(3):565-572.[doi:10.3969/j.issn.1001-0505.2019.03.023]
 Xia Yan,Pan Shuguo,Zhao Pengfei,et al.Unsupervised learning based satellite NLOS signal detection method[J].Journal of Southeast University (Natural Science Edition),2019,49(3):565-572.[doi:10.3969/j.issn.1001-0505.2019.03.023]
点击复制

基于无监督学习的卫星NLOS信号检测方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
49
期数:
2019年第3期
页码:
565-572
栏目:
测绘与导航
出版日期:
2019-05-20

文章信息/Info

Title:
Unsupervised learning based satellite NLOS signal detection method
作者:
夏炎1潘树国1赵鹏飞1赵庆2叶飞1
1东南大学仪器科学与工程学院, 南京 210096; 2东南大学交通学院, 南京 210096
Author(s):
Xia Yan1 Pan Shuguo1 Zhao Pengfei1 Zhao Qing2 Ye Fei1
1School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
2School of Transportation, Southeast University, Nanjing 210096, China
关键词:
无监督学习 NLOS k-means++聚类算法 双系统 伪距单点定位
Keywords:
unsupervised learning non-line-of-sight k-means++ clustering algorithm dual-system single point positioning
分类号:
P228.1
DOI:
10.3969/j.issn.1001-0505.2019.03.023
摘要:
针对复杂环境下NLOS信号接收造成的GNSS定位精度恶化问题,提出了一种基于无监督学习的卫星NLOS信号检测方法.综合考虑了信号载噪比、伪距残差和卫星高度角对于GNSS接收信号的影响,采用k-means++聚类算法将观测数据划分为LOS、多径和NLOS三类,并对NLOS信号进行分离.使用GPS/BDS双系统伪距单点定位对信号分类效果进行了验证.结果表明,采用该方法剔除NLOS信号后定位精度得到了显著的提升.静态实验中,对1 h的数据样本进行聚类,事后定位精度提高了约30%,实时定位精度提高约12%.动态实验中,城市峡谷路段东、北、天3个方向的定位精度分别提高了27.98%、8.06%和3.66%.相较于有监督学习的分类方法,该方法简单有效、易于实现,且无需使用先验信息,能显著降低运算负荷和GNSS设备成本.与传统的阈值法以及RAIM算法相比较,该方法在改善定位的精度方面具有一定的优势.
Abstract:
Aiming at the problem of global navigation satellite system(GNSS)positioning accuracy deterioration caused by non-line-of-sight(NLOS)signal reception in complex environments, a detection method for satellite NLOS signal based on unsupervised learning was proposed. The effects of carrier-to-noise ratio, pseudorange residual and satellite elevation angle on received GNSS signals were overall considered. The observation data were divided into three categories of line of sight(LOS), multipath and NLOS using k-means++ clustering algorithm, and then NLOS signal was separated from the dataset. GPS/BDS dual-system single point positioning was used to verify the signal classification effect. The results show that the positioning accuracy is improved after removing the NLOS signal by the proposed method. In the static experiment, 1 h data samples are clustered, and the post-positioning accuracy is improved by about 30%, while the real-time positioning accuracy is improved by about 12%. In the dynamic experiment, the positioning accuracies in the east, north, and up directions of the urban canyon section are improved by 27.98%, 8.06%, and 3.66%, respectively. Compared with the supervised learning classification method, the proposed method is simple and effective, easy to implement, and does not require the use of prior information, thus reducing the computational load and GNSS equipment cost. Compared with the traditional threshold method and receiver autonomous integrity monitoring(RAIM)algorithm, the method can improve the positioning accuracy.

参考文献/References:

[1] Groves P D, Jiang Z Y. Height aiding, C/N0 weighting and consistency checking for GNSS NLOS and multipath mitigation in urban areas[J]. Journal of Navigation, 2013, 66(5): 653-669. DOI:10.1017/s0373463313000350.
[2] Groves P, Jiang Z, Rudi M, et al. A portfolio approach to NLOS and multipath mitigation in dense urban areas[C]// Proceedings of ION GNSS. Nashville, TN, USA, 2013: 3231–3247.
[3] Groves P D, Jiang Z, Wang L, et al. Intelligent urban positioning using multi-constellation GNSS with 3D mapping and NLOS signal detection[C]// Proceedings of ION GNSS. Nashville, TN, USA, 2012: 458-472.
[4] Miura S, Hisaka S, Kamijo S. GPS multipath detection and rectification using 3D maps[C]//16th International IEEE Conference on Intelligent Transportation Systems. the Hague, Netherlands, 2013: 1528-1534. DOI:10.1109/ITSC.2013.6728447.
[5] Jiang Z Y, Groves P D. NLOS GPS signal detection using a dual-polarisation antenna[J]. GPS Solutions, 2014, 18(1): 15-26. DOI:10.1007/s10291-012-0305-5.
[6] Jiang Z, Groves P D, Ochieng W Y, et al. Multi-constellation GNSS multipath mitigation using consistency checking[C]// Proceedings of ION GNSS. Portland, OR,USA, 2011:3889-3902.
[7] Hsu L T, Jan S S, Groves P D, et al. Multipath mitigation and NLOS detection using vector tracking in urban environments[J]. GPS Solutions, 2015, 19(2): 249-262. DOI:10.1007/s10291-014-0384-6.
[8] Hsu L T, Tokura H, Kubo N, et al. Multiple faulty GNSS measurement exclusion based on consistency check in urban canyons[J]. IEEE Sensors Journal, 2017, 17(6): 1909-1917. DOI:10.1109/jsen.2017.2654359.
[9] Li B, Cui W, Wang B. A robust wireless sensor network localization algorithm in mixed LOS/NLOS scenario[J]. Sensors, 2015, 15(9): 23536-23553. DOI:10.3390/s150923536.
[10] Hsu L T, Gu Y L, Kamijo S. 3D building model-based pedestrian positioning method using GPS/GLONASS/QZSS and its reliability calculation[J]. GPS Solutions, 2016, 20(3): 413-428. DOI:10.1007/s10291-015-0451-7.
[11] Groves P D, Adjrad M. Likelihood-based GNSS positioning using LOS/NLOS predictions from 3D mapping and pseudoranges[J]. GPS Solutions, 2017, 21(4): 1805-1816. DOI:10.1007/s10291-017-0654-1.
[12] Adjrad M, Groves P D. Intelligent urban positioning: Integration of shadow matching with 3D-mapping-aided GNSS ranging[J]. Journal of Navigation, 2018, 71(1): 1-20. DOI:10.1017/s0373463317000509.
[13] Socharoentum M, Karimi H A. A machine learning approach to detect non-line of sight satellites in Nav2 Nav[C]// ITS World Congress. Melbourne, Australia, 2014: 117-138.
[14] Yozevitch R, Moshe B B, Weissman A. A robust GNSS LOS/NLOS signal classifier[J]. Navigation, 2016, 63(4): 429-442. DOI:10.1002/navi.166.
[15] Hsu L T. GNSS multipath detection using a machine learning approach[C]//2017 IEEE 20th International Conference on Intelligent Transportation Systems(ITSC).Yokohama, Japan, 2017: 1-6. DOI:10.1109/ITSC.2017.8317700.
[16] Groves P D. Shadow matching: A new GNSS positioning technique for urban canyons[J]. Journal of Navigation, 2011, 64(3): 417-430. DOI:10.1017/s0373463311000087.
[17] Wang L, Groves P D, Ziebart M K. Urban positioning on a smartphone: Real-time shadow matching using GNSS and 3D city models[C]// Proceedings of ION GNSS. Nashville, TN, USA, 2013: 1606-1619.
[18] Hsu L T, Gu Y L, Huang Y Y, et al. Urban pedestrian navigation using smartphone-based dead reckoning and 3-D map-aided GNSS[J]. IEEE Sensors Journal, 2016, 16(5): 1281-1293. DOI:10.1109/jsen.2015.2496621.
[19] Ramalingam S, Bouaziz S, Sturm P, et al. Geolocalization using skylines from omni-images[C]//2009 IEEE 12th International Conference on Computer Vision Workshops. Kyoto, Japan, 2009: 23-30. DOI:10.1109/ICCVW.2009.5457723.
[20] Meguro J I, Murata T, Takiguchi J I, et al. GPS multipath mitigation for urban area using omnidirectional infrared camera[J]. IEEE Transactions on Intelligent Transportation Systems, 2009, 10(1): 22-30. DOI:10.1109/tits.2008.2011688.
[21] Strode P R R, Groves P D. GNSS multipath detection using three-frequency signal-to-noise measurements[J]. GPS Solutions, 2016, 20(3): 399-412. DOI:10.1007/s10291-015-0449-1.
[22] Irish A T, Isaacs J T, Quitin F, et al. Belief propagation based localization and mapping using sparsely sampled GNSS SNR measurements[C]//2014 IEEE International Conference on Robotics and Automation. Hong Kong, China, 2014: 1977-1982. DOI:10.1109/ICRA.2014.6907121.
[23] MacQueen J. Some methods for classification and analysis of multivariate observations[C]// Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability. Berkeley, USA, 1967, 1(14): 281-297.
[24] Arthur D, Vassilvitskii S. k-means++: The advantages of careful seeding[C]// Proceedings of the Eighteenth Acm-Siam Symposium on Discrete Algorithms. New Orleans, Louisiana, USA. 2007:1027-1035.
[25] Calinski T, Harabasz J. A dendrite method for cluster analysis[J]. Communications in Statistics—Theory and Methods, 1974, 3(1): 1-27. DOI:10.1080/03610927408827101.

备注/Memo

备注/Memo:
收稿日期: 2018-09-01.
作者简介: 夏炎(1987—),男,博士生;潘树国(联系人),男,博士,教授,博士生导师,psg@seu.edu.cn.
基金项目: “十三五”国家重点研发计划资助项目(2016YFB0502101)、国家自然科学基金资助项目(41574026, 41774027).
引用本文: 夏炎,潘树国,赵鹏飞,等.基于无监督学习的卫星NLOS信号检测方法[J].东南大学学报(自然科学版),2019,49(3):565-572. DOI:10.3969/j.issn.1001-0505.2019.03.023.
更新日期/Last Update: 2019-05-20