IMU Data Processing For Inertial Aided Navigation: A Recurrent Neural Network Based Approach

被引:31
|
作者
Zhang, Ming [1 ]
Zhang, Mingming [1 ]
Chen, Yiming [1 ]
Li, Mingyang [1 ]
机构
[1] Alibaba Grp, Hangzhou, Peoples R China
关键词
D O I
10.1109/ICRA48506.2021.9561172
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this work, we propose a novel method for performing inertial aided navigation, by using deep neural networks (DNNs). To date, most DNN inertial navigation methods focus on the task of inertial odometry, by taking gyroscope and accelerometer readings as input and regressing for integrated IMU poses (i.e., position and orientation). While this design has been successfully applied on a number of applications, it is not of theoretical performance guarantee unless patterned motion is involved. This inevitably leads to significantly reduced accuracy and robustness in certain use cases. To solve this problem, we design a framework to compute observable IMU integration terms using DNNs, followed by the numerical pose integration and sensor fusion to achieve the performance gain. Specifically, we perform detailed analysis on the motion terms in IMU kinematic equations, propose a dedicated network design, loss functions, and training strategies for the IMU data processing, and conduct extensive experiments. The results show that our method is generally applicable and outperforms both traditional and DNN methods by wide margins.
引用
收藏
页码:3992 / 3998
页数:7
相关论文
共 50 条
  • [41] Tool Remaining Useful Life Prediction based on Edge Data Processing and LSTM Recurrent Neural Network
    Huang, Qingqing
    Kang, Zhen
    Zhang, Yan
    Yan, Dong
    2020 IEEE INTERNATIONAL CONFERENCE ON PROGNOSTICS AND HEALTH MANAGEMENT (ICPHM), 2020,
  • [42] RNIN-VIO: Robust Neural Inertial Navigation Aided Visual-Inertial Odometry in Challenging Scenes
    Chen, Danpeng
    Wang, Nan
    Xu, Runsen
    Xie, Weijian
    Bao, Hujun
    Zhang, Guofeng
    2021 IEEE INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY (ISMAR 2021), 2021, : 275 - 283
  • [43] A Deep Recurrent Neural Network Based Predictive Control Framework for Reliable Distributed Stream Data Processing
    Xu, Jielong
    Tang, Jian
    Xu, Zhiyuan
    Yin, Chengxiang
    Kwiat, Kevin
    Kamhoua, Charles
    2019 IEEE 33RD INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS 2019), 2019, : 262 - 272
  • [44] Neural network aided GPS/INS Integration for UAV navigation
    Meng Qing-ji
    ADVANCED DESIGN AND MANUFACTURING TECHNOLOGY III, PTS 1-4, 2013, 397-400 : 1598 - 1601
  • [45] Candidate Oil Spill Detection in SLAR Data A Recurrent Neural Network-based Approach
    Oprea, Sergiu-Ovidiu
    Gil, Pablo
    Mira, Damian
    Alacid, Beatriz
    ICPRAM: PROCEEDINGS OF THE 6TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION APPLICATIONS AND METHODS, 2017, : 372 - 377
  • [46] Estimating the visibility in foggy weather based on meteorological and video data: A Recurrent Neural Network approach
    Chen, Jian
    Yan, Ming
    Qureshi, Muhammad Rabea Hanzla
    Geng, Keke
    IET SIGNAL PROCESSING, 2023, 17 (01)
  • [47] Missing data processing based on neural network and AdaBoost
    Zhi-Min, Miao
    Zhi-Song, Pan
    Gu-Yu, Hu
    PROCEEDINGS OF 2007 IEEE INTERNATIONAL CONFERENCE ON GREY SYSTEMS AND INTELLIGENT SERVICES, VOLS 1 AND 2, 2007, : 1107 - 1111
  • [48] METHOD OF IMPROVING THE ACCURACY OF NAVIGATION MEMS DATA PROCESSING OF UAV INERTIAL NAVIGATION SYSTEM
    Fesenko, O. D.
    Bieliakov, R. O.
    Radzivilov, H. D.
    Sasin, S. A.
    Borysov, O., V
    Borysov, I., V
    Derkach, T. M.
    Kovalchuk, O. O.
    RADIO ELECTRONICS COMPUTER SCIENCE CONTROL, 2022, (03) : 196 - 207
  • [49] A Bayesian Estimation-Based Algorithm for Geomagnetic Aided Inertial Navigation
    Liu Y.
    Zheng P.
    1600, Peking University (53): : 873 - 880
  • [50] Inertial Navigation Aided by Vision-Based Simultaneous Localization and Mapping
    Sazdovski, Vasko
    Silson, Peter M. G.
    IEEE SENSORS JOURNAL, 2011, 11 (08) : 1646 - 1656