一种基于LSTM-EKF的车载GNSS/INS组合导航系统

傅率智, 陈伟, 吴迪, 孔海洋, 郑洪江, 杜路遥

傅率智, 陈伟, 吴迪, 孔海洋, 郑洪江, 杜路遥. 一种基于LSTM-EKF的车载GNSS/INS组合导航系统[J]. 武汉大学学报 ( 信息科学版). DOI: 10.13203/j.whugis20200115
引用本文: 傅率智, 陈伟, 吴迪, 孔海洋, 郑洪江, 杜路遥. 一种基于LSTM-EKF的车载GNSS/INS组合导航系统[J]. 武汉大学学报 ( 信息科学版). DOI: 10.13203/j.whugis20200115
Fu Shuaizhi, Chen Wei, Wu Di, Kong Haiyang, Zheng Hongjiang, Du Luyao. A GNSS/INS Vehicle Integrated Navigation System Based on LSTM-EKF[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20200115
Citation: Fu Shuaizhi, Chen Wei, Wu Di, Kong Haiyang, Zheng Hongjiang, Du Luyao. A GNSS/INS Vehicle Integrated Navigation System Based on LSTM-EKF[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20200115

一种基于LSTM-EKF的车载GNSS/INS组合导航系统

基金项目: 

国家重点专项研发计划“新能源汽车”专项(2018YFB0105205);2018年度广西高校中青年教师基础能力提升项目(2018KY0357);2018广西创新驱动发展专项(桂科2018AA18118025)。

详细信息
    作者简介:

    傅率智,硕士生,主要从事GNSS/INS组合导航研究。fushuaizhi@whut.edu.cn

    通讯作者:

    吴迪,博士,助理研究员。wudi324243@163.com

  • 中图分类号: P228

A GNSS/INS Vehicle Integrated Navigation System Based on LSTM-EKF

Funds: 

National Key R&D Program of China (2018YFB0105205)

  • Abstract:

    Integration of GNSS and INS can provide continuous and accurate positioning information for vehicles. However, the accuracy of low-cost GNSS/INS vehicle integrated navigation systems is unreliable during GNSS outages, which are common in urban areas. So, a long and short-term memory (LSTM) networks-aided GNSS/INS integrated navigation system based on extended Kalman filter (EKF) is proposed in this paper. LSTM networks are trained to learn the relationship between position error and INS output when GNSS available. When GNSS outage occurs, LSTM networks predict and correct errors of the integrated navigation system to improve location precision. The experiment shows that the north error and east error of the GNSS/INS integrated navigation systems based on EKF is 1.93m and 13.92m during the 15s GNSS outage. Meanwhile, the north error and east error of the GNSS/INS integrated navigation systems based on LSTM-EKF is 1.17m and 0.84m. The comparison results indicate that the proposed system can effectively improve location precision during GNSS outages.

  • [1]

    Renfro B A, Stein M, Boeker N, et al. An analysis of global positioning system (GPS) standard positioning service (SPS) performance for 2017[J]. See https://www.gps.gov/systems/gps/performance/2014-GPS-SPS-performance-analysis.pdf, 2018.

    [2] Li Yanjie, Yang Yuanxi, He Haibo. Effects Analysis of Constraints on GNSS/INS Integrated Navigation. Geomatics and Information Science of Wuhan University, 2017, 42(9):1249-1255(李彦杰, 杨元喜, 何海波. 附加约束条件对GNSS/INS组合导航结果的影响分析[J]. 武汉大学学报·信息科学版, 2017, 42(9):1249-1255.).
    [3]

    Sasani S, Asgari J, Amiri-Simkooei A R. Improving MEMS-IMU/GPS Integrated Systems for Land Vehicle Navigation Applications[J]. GPS solutions, 2016, 20(1):89-100.

    [4]

    Tan X, Wang J, Jin S, et al. GA-SVR and Pseudo-Position-Aided GPS/INS Integration during GPS Outage[J]. The Journal of Navigation, 2015, 68(4):678-696.

    [5]

    Yao Y, Xu X. A RLS-SVM Aided Fusion Methodology for INS during GPS Outages[J]. Sensors, 2017, 17(3):432-445.

    [6]

    Belhajem I, Maissa Y B, Tamtaoui A. A Hybrid Low Cost Approach using Extended Kalman Filter and Neural Networks for Real time Positioning[C]. 2016 International Conference on Information Technology for Organizations Development (IT4OD). IEEE, 2016:1-5.

    [7]

    Clark B J, Simmons C M, Berkowitz L E, et al. The retrosplenial-parietal network and reference frame coordination for spatial navigation[J]. Behavioral neuroscience, 2018, 132(5):416.

    [8] Guo Shiluo, Wu miao, Xu Jiangning, et al. Adaptive Fading Kalman Filter and Its Application in SINS Initial Alignment[J]. Geomatics and Information Science of Wuhan University, 2018, 43(11):1667-1672(郭士荦, 吴苗, 许江宁, 等. 自适应渐消卡尔曼滤波及其在SINS初始对准中的应用[J]. 武汉大学学报·信息科学版, 2018, 43(11):1667-1672).
    [9]

    Barrau A, Bonnabel S. The Invariant Extended Kalman Filter as A Stable Observer[J]. IEEE Transactions on Automatic Control, 2016, 62(4):1797-1812.

    [10]

    Ko N Y, Youn W, Choi I H, et al. Features of invariant extended Kalman filter applied to unmanned aerial vehicle navigation[J]. Sensors, 2018, 18(9):2855.

    [11]

    Groves P D. Navigation using Inertial Sensors[Tutorial] [J]. IEEE Aerospace and Electronic Systems Magazine, 2015, 30(2):42-69.

    [12]

    Li X, Wang Y, Khoshelham K. Comparative analysis of robust extended Kalman filter and incremental smoothing for UWB/PDR fusion positioning in NLOS environments[J]. Acta Geodaetica et Geophysica, 2019, 54(2):157-179.

    [13]

    Jozefowicz R, Zaremba W, Sutskever I. An Empirical Exploration of Recurrent Network Architectures[C]. International conference on machine learning. 2015:2342-2350.

    [14]

    El-Mowafy A. Analysis of Web-based GNSS Post-Processing Services for Static and Kinematic Positioning using Short Data Spans[J]. Survey review, 2011, 43(323):535-549.

    [15] Huang Yongshuai, Shi Junbo, Ouyang Chenhao, et al. Real-time Observation Decoding and Positioning Analysis Based on Qianxun BeiDou Ground Based Augmentation System[J]. Bull Surv Mapp, 2017, 00(09):11-14(黄永帅, 史俊波, 欧阳晨皓, 等. 千寻北斗地基增强网络下的实时观测数据解码及定位性能分析[J]. 测绘通报, 2017, 00(09):11-14).
    [16] Groves P D. Principles of GNSS, Inertial, and Multisensor Integrated Navigation Systems[M]. National Defense Industry Press, 2015(格鲁夫. GNSS与惯性及多传感器组合导航系统原理[M]. 国防工业出版社, 2015).
计量
  • 文章访问数:  1798
  • HTML全文浏览量:  252
  • PDF下载量:  208
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-05-24
  • 网络出版日期:  2023-09-26

目录

    /

    返回文章
    返回