Novel hybrid of strong tracking Kalman filter and improved radial basis function neural network for GPS/INS integrated navagation

Xiao Chun Tian, Cheng Dong Xu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

Aiming to improve positioning precision of the GPS/INS integrated navigation system during GPS outages , a novel model combined with strong tracking Kalman filter (STKF) and improved Radial Basis Function Neural Network(IRBFNN) algorithms is proposed and tested. STKF is used to estimate INS errors as a replacement of Kalman filter (KF), and IRBFNN is trained based on STKF when GPS works well and applied to predict INS errors during GPS outages. In the IRBF neural network, the width of the hidden layer and kernel function are optimized by using genetic algorithm to obtain a high precision generalization ability of RBF network structure. The simulation indicate that the proposed model can effectively provide high accurate corrections to the standalone INS during GPS outages.

Original languageEnglish
Title of host publicationProceedings of 2016 2nd International Conference on Control Science and Systems Engineering, ICCSSE 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages72-76
Number of pages5
ISBN (Electronic)9781467398725
DOIs
Publication statusPublished - 14 Dec 2016
Event2nd International Conference on Control Science and Systems Engineering, ICCSSE 2016 - Singapore, Singapore
Duration: 27 Jul 201629 Jul 2016

Publication series

NameProceedings of 2016 2nd International Conference on Control Science and Systems Engineering, ICCSSE 2016

Conference

Conference2nd International Conference on Control Science and Systems Engineering, ICCSSE 2016
Country/TerritorySingapore
CitySingapore
Period27/07/1629/07/16

Keywords

  • GPS/INS integration
  • Genetic algorithm
  • Radial basis function neural network
  • Strong tracking Kalman filter

Fingerprint

Dive into the research topics of 'Novel hybrid of strong tracking Kalman filter and improved radial basis function neural network for GPS/INS integrated navagation'. Together they form a unique fingerprint.

Cite this