Hostname: page-component-8448b6f56d-cfpbc Total loading time: 0 Render date: 2024-04-23T17:07:02.663Z Has data issue: false hasContentIssue false
  • English
  • Français

Dealing with Observation Outages within Navigation Data using Gaussian Process Regression

Published online by Cambridge University Press:  14 February 2014

Hongmei Chen ,
Xianghong Cheng ,
Haipeng Wang  and
Xu Han
Hongmei Chen
Affiliation:
(School of Instrument Science and Engineering, Southeast University, China) (Key Laboratory of Micro-Inertial Instrument and Advanced Navigation, China) (Luoyang Institute of Science and Technology, China)
Xianghong Cheng*
Affiliation:
(School of Instrument Science and Engineering, Southeast University, China) (Key Laboratory of Micro-Inertial Instrument and Advanced Navigation, China)
Haipeng Wang
Affiliation:
(School of Instrument Science and Engineering, Southeast University, China) (Key Laboratory of Micro-Inertial Instrument and Advanced Navigation, China)
Xu Han
Affiliation:
(School of Instrument Science and Engineering, Southeast University, China) (Key Laboratory of Micro-Inertial Instrument and Advanced Navigation, China)
*
(E-mail: xhcheng@seu.edu.cn)
Get access Rights & Permissions [Opens in a new window]

Abstract

Gaussian process regression (GPR) is used in a Spare-grid Quadrature Kalman filter (SGQKF) for Strap-down Inertial Navigation System (SINS)/odometer integrated navigation to bridge uncertain observation outages and maintain an estimate of the evolving SINS biases. The SGQKF uses nonlinearized dynamic models with complex stochastic nonlinearities so the performance degrades significantly during observation outages owing to the uncertainties and noise. The GPR calculates the residual output after factoring in the contributions of the parametric model that is used as a nonlinear SINS error predictor integrated into the SGQKF. The sensor measurements and SINS output deviations from the odometer are collected in a data set during observation availability. The GPR is then applied to predict SINS deviations from the odometer and then the predicted SINS deviations are fed to the SGQKF as an actual update to estimate all SINS biases during observation outages. We demonstrate our method's effectiveness in bridging uncertain observation outages in simulations and in real road tests. The results agree with the theoretical analysis, which demonstrate that SGQKF using GPR can maintain an estimate of the evolving SINS biases during signal outages.

Keywords

Sparse-grid quadrature Kalman filter (SGQKF)Gaussian process regressionUncertain observationsIntegrated navigation systems
Type
Research Article
Information
The Journal of Navigation , Volume 67 , Issue 4 , July 2014 , pp. 603 - 615
Copyright
Copyright © The Royal Institute of Navigation 2014 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

Abdel-Hamid, W., Noureldin, A. and El-Sheimy, N. (2007). Adaptive fuzzy prediction of low-cost inertial-based positioning errors. IEEE Transactions on Fuzzy Systems, 15(3), 519–529.CrossRefGoogle Scholar
Asheri, H., Rabiee, H. R., Pourdamghani, N. and Mohammad, H.R. (2010). A Gaussian Process Regression Framework for Spatial Error Concealment with Adaptive Kernels. 20th International Conference on Pattern Recognition, 4541–4544.Google Scholar
Atia, M.M., Noureldin, A. and Korenberg, M. (2012). Enhanced Kalman Filter for RISS/GPS Integrated Navigation using Gaussian Process Regression. Proceedings of the 2012 International Technical Meeting of The Institute of Navigation, 1148–1156.Google Scholar
Cheng, X., Ran, C. and Wang, H. (2013). Sparse-grid Quadrature Kalman Filter based on the Kronrod-Patterson Rule. IEEE International Instrumentation and Measurement Technology Conference, 1396–1401.Google Scholar
Georgy, J., Noureldin, A., Korenberg, M.J. and Mohamed, M.B. (2010). Low-cost Three-dimensional Navigation Solution for RISS/GPS Integration Using Mixture Particle Filter. IEEE Transactions on Vehicular Technology, 59(2), 599–615.Google Scholar
Hermoso-Carazo, A. and Linares-Pérez, J. (2011). Nonlinear Estimation Applying an Unscented Transformation in Systems with Correlated Uncertain Observations. Applied Mathematics and Computation, 217(20), 7998–8009.Google Scholar
Jia, B., Xin, M. and Cheng, Y. (2012). Sparse-grid Quadrature Nonlinear Filtering. Automatica, 48, 327–341.CrossRefGoogle Scholar
Jia, B., Xin, M. and Cheng, Y. (2010). Sparse Gauss-Hermite Quadrature Filter For Spacecraft Attitude Estimation. Journal of Guidance, Control and Dynamics, 27(2), 367–379.Google Scholar
Ko, J. and Fox, D. (2009). GP-Bayes Filters: Bayesian filtering using Gaussian Process Prediction and Observation Models. Autonomous Robots, 27(1), 75–90.Google Scholar
Ko, J. and Fox, D. (2011). Learning GP-Bayes Filters via Gaussian Process Latent Variable Models. Autonomous Robots, 30(1), 3–23.Google Scholar
Ko, J., Klein, D., Fox, D., and Hähnel, D. (2007). GP-UKF: Unscented Kalman filters with Gaussian process prediction and observation models. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 1901–1907.Google Scholar
Kwangyul, B. and Hyochoong, B. (2013). Adaptive sparse grid quadrature filter for spacecraft relative navigation. Acta Astronautica, 87, 96–106.Google Scholar
Lawrence, N. (2005). Probabilistic Non-linear Principal Component Analysis with Gaussian Process Latent Variable Models. Journal of Machine Learning Research 6, 1783–1816.Google Scholar
Li, L. and Xia, Y. (2012). Stochastic Stability of the Unscented Kalman Filter with Intermittent Observations. Automatica, 48(5), 978–981.Google Scholar
Loebis, D., Sutton, R., Chudley, J., Naeem, W. (2004). Adaptive tuning of a Kalman filter via fuzzy logic for an intelligent AUV navigation system. Control engineering practice, 12(12), 1531–1539.Google Scholar
Ranganathan, A., Yang, M.H. and Ho, J. (2011). Online Sparse Gaussian Process Regression and its Applications. IEEE Transactions on Image Processing, 20(2), 391–404.CrossRefGoogle ScholarPubMed
Rasmussen, C. E., Christopher, K. I. and Williams, (2006). Gaussian Processes for Machine Learning. The Massachusetts Institute of Technology Press, Boston, 215–240.Google Scholar
Semeniuk, L. and Noureldin, A. (2006). Bridging GPS outages using neural network estimates of INS position and velocity errors. Measurement science and technology, 17(10), 2783–2798.Google Scholar
Snelson, E. and Ghahramani, Z. (2012). Variable Noise and Dimensionality Reduction for Sparse Gaussian Processes. 22nd Conference on Uncertainty in Artificial Intelligence, 461–468.Google Scholar
Yan, G., Yan, W. and Xu, D. (2008). Application of simplified UKF in SINS initial alignment for large misalignment angles. Journal of Chinese Inertial Technology, 16(3), 253–264.Google Scholar
Yang, P. (2011). Key Technologies for SINS Based Vehicular Integrated Navigation System. PhD thesis, publications on Northwestern Polytechnical University, China,Xian.Google Scholar