Seamless INS/GPS Integration Based on Support Vector Machines

Tian Lai Xu

doi:10.4028/www.scientific.net/AMM.336-338.277

Paper Titles

Clustering-Based Data Gathering in Wireless Sensor Network with Mobile Collector
p.261

Research of Event Localization in WSN Environmental Monitoring Based on Mobile Agent
p.265

Compare of Two Intrinsic Fabry-Perot Interferometric Fiber Pressure Sensor Structures
p.269

Design and Realize of a Universal High Precision Tester of Attack and Slide Angle Sensor
p.273

Seamless INS/GPS Integration Based on Support Vector Machines
p.277

Design and Simulation of a Novel Horizontal Sensitive Inertial Micro-Switch with Low G Value
p.281

A New Type of Electroacoustic Transducer Used for Downhole Acoustic Telemetry System
p.286

Study of the Conjugate Height for Solar Multi-Conjugate Adaptive Optics
p.290

Integrated Sensor System for Rock Mass Underground Deformation Measurement and Data Analysis
p.295

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 336-338Seamless INS/GPS Integration Based on Support...

Seamless INS/GPS Integration Based on Support Vector Machines

Abstract:

The combination of Inertial Navigation System (INS) and Global Positioning System (GPS) provides superior performance in comparison with either a stand-alone INS or GPS. However, the positioning accuracy of INS/GPS deteriorates with time in the absence of GPS signals. A least squares support vector machines (LS-SVM) regression algorithm is applied to INS/GPS integrated navigation system to bridge the GPS outages to achieve seamless navigation. In this method, LS-SVM is trained to model the errors of INS when GPS is available. Once the LS-SVM is properly trained in the training phase, its prediction can be used to correct the INS errors during GPS outages. Simulations in INS/GPS integrated navigation showed improvements in positioning accuracy when GPS outages occur.

You might also be interested in these eBooks

Industrial Instrumentation and Control Systems II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 336-338)

Pages:

277-280

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.336-338.277

Citation:

Cite this paper

Online since:

July 2013

Authors:

Tian Lai Xu

Keywords:

GPS Outages, INS/GPS, Integrated Navigation System, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Huang Xiaorui, Development of vehicle integrated navigation system based on information fusion. Harbin: Harbin Institute of Technology (2002).

Google Scholar

[2] K.W. Chiang, A. Noureldin, N. El-Sheimy, Multisensor integration using neuron computing for land vehicle navigation, GPS Solutions. Vol. 6 (2003), pp.209-218.

DOI: 10.1007/s10291-002-0024-4

Google Scholar

[3] A. Noureldin, A. Osman, N. El-Sheimy, A neuro-wavelet method for multi-sensor system integration for vehicular navigation, J. Meas. Sci. Technol. Vol. 15 (2004) pp.404-412.

DOI: 10.1088/0957-0233/15/2/013

Google Scholar

[4] Zhenkai Xu, Yong Li, Chris Rizos, Xiaosu Xu, Novel Hybrid of LS-SVM and Kalman Filter for GPS/INS Integration, The Journal of Navigation. Vol. 63 (2010) pp.289-299.

DOI: 10.1017/s0373463309990361

Google Scholar

[5] V. Vapnik, Statistical Learning Theory, John Wiley, New-York, USA (1998).

Google Scholar

[6] A. K. Suykens, P. L. Vandewalle, Least squares support vector machine classifiers, Neural Processing Letters, Vol. 9 (1999) pp.293-300.

Google Scholar

[7] Dong Xu-rong, Zhang Shou-xin, Hua zhong-chun, GPS/INS integrated navigation system location and application. Press of National Defense Technology University, Changsha, China (1988).

Google Scholar