Hostname: page-component-848d4c4894-5nwft Total loading time: 0 Render date: 2024-06-01T20:00:18.595Z Has data issue: false hasContentIssue false
  • English
  • Français

Novel Hybrid of LS-SVM and Kalman Filter for GPS/INS Integration

Published online by Cambridge University Press:  23 February 2010

Zhenkai Xu ,
Yong Li ,
Chris Rizos  and
Xiaosu Xu
Zhenkai Xu*
Affiliation:
(Southeast University, Nanjing, China) (University of New South Wales, Sydney, Australia)
Yong Li
Affiliation:
(University of New South Wales, Sydney, Australia)
Chris Rizos
Affiliation:
(University of New South Wales, Sydney, Australia)
Xiaosu Xu
Affiliation:
(Southeast University, Nanjing, China)
*
(Email: z.xu@student.unsw.edu.au)
Get access Rights & Permissions [Opens in a new window]

Abstract

Integration of Global Positioning System (GPS) and Inertial Navigation System (INS) technologies can overcome the drawbacks of the individual systems. One of the advantages is that the integrated solution can provide continuous navigation capability even during GPS outages. However, bridging the GPS outages is still a challenge when Micro-Electro-Mechanical System (MEMS) inertial sensors are used. Methods being currently explored by the research community include applying vehicle motion constraints, optimal smoother, and artificial intelligence (AI) techniques. In the research area of AI, the neural network (NN) approach has been extensively utilised up to the present. In an NN-based integrated system, a Kalman filter (KF) estimates position, velocity and attitude errors, as well as the inertial sensor errors, to output navigation solutions while GPS signals are available. At the same time, an NN is trained to map the vehicle dynamics with corresponding KF states, and to correct INS measurements when GPS measurements are unavailable. To achieve good performance it is critical to select suitable quality and an optimal number of samples for the NN. This is sometimes too rigorous a requirement which limits real world application of NN-based methods.

The support vector machine (SVM) approach is based on the structural risk minimisation principle, instead of the minimised empirical error principle that is commonly implemented in an NN. The SVM can avoid local minimisation and over-fitting problems in an NN, and therefore potentially can achieve a higher level of global performance. This paper focuses on the least squares support vector machine (LS-SVM), which can solve highly nonlinear and noisy black-box modelling problems. This paper explores the application of the LS-SVM to aid the GPS/INS integrated system, especially during GPS outages. The paper describes the principles of the LS-SVM and of the KF hybrid method, and introduces the LS-SVM regression algorithm. Field test data is processed to evaluate the performance of the proposed approach.

Keywords

GPS/INS integrationKalman filterSupport vector machineGPS outages
Type
Research Article
Information
The Journal of Navigation , Volume 63 , Issue 2 , April 2010 , pp. 289 - 299
Copyright
Copyright © The Royal Institute of Navigation 2010

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

[1]Li, Y., Mumford, P. and Rizos, C. (2008). “A Real-time GPS/INS Integrated System”, Coordinates, Vol. IV, No. 3, 12–17, March 2008.Google Scholar
[2]Brown, A., and Lu, Y. (2004). “Performance Test Results on an Integrated GPS/MEMS Inertial Navigation Package”, in Proc. of 17th International Technical Meeting of the Satellite Division, U.S. Institute of Navigation, Long Beach, CA, Sept 21–24. 2004, 825–832.Google Scholar
[3]Jaffe, R., Bonomi, S., and Madni, A. M.. (2004). “Miniature MEMS Quartz INS/GPS Description and Performance Attributes”, in Proc. of 17th International Technical Meeting of the Satellite Division, U.S. Institute of Navigation, Long Beach, CA, Sept 21–24. 2004, 852–863.Google Scholar
[4]Goodall, C., El-Sheimy, N., and Chiang, K. W. (2005). “The Development of a GPS/MEMS INS Integrated System Utilising a Hybrid Processing Architecture”, in Proc. of 18th International Technical Meeting of the Satellite Division, U.S. Institute of Navigation, Long Beach, CA, September 13–16. 2005, 1444–1455.Google Scholar
[5]Jwo, D. J., and Huang, H-C. (2004). “Neural Network Aided Adaptive Extended Kalman Filtering Approach for DGPS Positioning”, Journal of Navigation, 57, 449–463.CrossRefGoogle Scholar
[6]Korniyenko, O. V., Sharawi, M. S., and Aloi, D. N. (2005). “Neural Network Based Approach for Tuning Kalman Filter”, presented at IEEE Electro/Information Technology Conference (EIT 2005), Lincoln – Nebraska, May 22–25, 2005, 1–5.Google Scholar
[7]El-Rabbany, A., and El-Diasty, M. (2004). “An Efficient Neural Network Model for De-noising of MEMS-based Inertial Data”, Journal of Navigation, 57, 407–415.CrossRefGoogle Scholar
[8]Wang, J. J., Wang, J., Sinclair, D. and Watts, L. (2006). “A Neural Network and Kalman Filter Hybrid Approach for GPS/INS Integration”, 12th IAIN Congress & 2006 International Symposium on GPS/GNSS, Jeju, Korea, October 18–20, 277–282.Google Scholar
[9]Vapnik, V. (1995). The Nature of Statistical Learning Theory, Springer-Verlag, New-York.CrossRefGoogle Scholar
[10]Vapnik, V. (1998). Statistical Learning Theory, John Wiley, New-York.Google Scholar
[11]Bar-Itzhack, I. Y., and Berman, N. (1988). “Control Theoretical Approach to Inertial Navigation Systems”, Journal of Guidance, Control and Dynamics, Vol. 11, No. 3, 237–245.CrossRefGoogle Scholar
[12]Vapnik, V. (1998). “The Support Vector Method of Function Estimation”, in Nonlinear Modeling: Advanced Black-box Techniques, Suykens, J.A.K., Vandewalle, J. (Eds.), Kluwer Academic Publishers, Boston, 55–85.CrossRefGoogle Scholar
[13]Golub, G. H. and Van Loan, C. F. (1989). Matrix Computations, Baltimore MD: Johns Hopkins University Press.Google Scholar
[14]Van Gestel, T., Suykens, J. A. K., Lanckriet, G., Lambrechts, A., De Moor, B. and Vandewalle, J. (2002). “A Bayesian Framework for Least Squares Support Vector Machine Classifiers”, Nerual Computation, May 2002, Vol. 14, No. 5, Pages 1115–1147.CrossRefGoogle ScholarPubMed
[15]Li, Y., Mumford, P., and Rizos, C. (2008). “Seamless Navigation Through GPS Outages – A Low-cost GPS/INS Solution”, Inside GNSS, July/August 2008, 39–45.Google Scholar
[16]Boeing North American Inc, User's Manual of C-MIGITS II., 1997, 67.Google Scholar