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
  • [1] Data map characteristic analysis based on aided inertial navigation
    Feng, Hao
    Yan, Lei
    Zhang, Fei-Zhou
    Liu, Guang-Jun
    Deng, Zhong-Liang
    Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications, 2004, 27 (04): : 23 - 27
  • [2] A Simple Self-Supervised IMU Denoising Method for Inertial Aided Navigation
    Yuan, Kaiwen
    Wang, Z. Jane
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (02) : 944 - 950
  • [3] A New Approach to Vision-Aided Inertial Navigation
    Tardif, Jean-Philippe
    George, Michael
    Laverne, Michel
    Kelly, Alonzo
    Stentz, Anthony
    IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010), 2010, : 4161 - 4168
  • [4] Calibration of inertial measurement unit (IMU) using neural network
    Liu, BQ
    Fang, JC
    ICEMI 2005: Conference Proceedings of the Seventh International Conference on Electronic Measurement & Instruments, Vol 2, 2005, : 624 - 627
  • [5] Nine-Axis IMU-based Extended inertial odometry neural network
    Kim, Won-Yeol
    Seo, Hong-Il
    Seo, Dong-Hoan
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 178
  • [6] The improvement of the prescision of an inertial navigation system for AUV based on the neural network
    Ishibashi, Shojiro
    OCEANS 2006 - ASIA PACIFIC, VOLS 1 AND 2, 2006, : 76 - 81
  • [7] Inertial/celestial integrated navigation method based on BP neural network
    Sun H.
    Mu R.
    Du H.
    Cui N.
    Zhongguo Guanxing Jishu Xuebao/Journal of Chinese Inertial Technology, 2019, 27 (04): : 486 - 491
  • [8] Novel approach to improve performance of inertial navigation system via neural network
    Pukhov, Evgeniy
    Cohen, Haim Israel
    2020 IEEE/ION POSITION, LOCATION AND NAVIGATION SYMPOSIUM (PLANS), 2020, : 746 - 754
  • [9] Study on Estimation Errors in ZUPT-Aided Pedestrian Inertial Navigation Due to IMU Noises
    Wang, Yusheng
    Chernyshoff, Andrei
    Shkel, Andrei M.
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2020, 56 (03) : 2280 - 2291
  • [10] Approach of navigation data processing based on ANN
    Zeng, Liansun
    Shanghai Haiyun Xueyuan Xuebao/Journal of Shanghai Maritime University, 1999, 20 (03): : 23 - 28