A fusion method based on ANN to overcome the GNSS Outages for GNSS/INS System

Xuan Xiao, Jia Xing Sun, Qin Zhang

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

1 Citation (Scopus)

Abstract

The performance of the GNSS/INS integrated navigation system will be reduced during GNSS outages. In order to deal with GNSS outages, a fusion method based on ANN is proposed. First, the ELM network is used to achieve rapid detection of the sudden outages of the GNSS signal. Then, according to the output of the INS system, the BP neural network is used to predict the incremental output of GNSS, and the accuracy is improved by adopting the past information of the INS in different steps.This method has been verified in actual vehicle data experiments.The accuracy of the ELM detection method was tested through comparative experiments, and the improvement of navigation accuracy based on the improved BPNN fusion method during GNSS outages.Comprehensive experiment show that the integrated navigation fusion algorithm based on ELM and BPNN can effectively reduce the navigation error during GNSS signal interruption.At the same time, different algorithm options are provided to balance the computational burden and navigation accuracy.

Original languageEnglish
Title of host publicationProceeding - 2021 China Automation Congress, CAC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4914-4919
Number of pages6
ISBN (Electronic)9781665426473
DOIs
Publication statusPublished - 2021
Event2021 China Automation Congress, CAC 2021 - Beijing, China
Duration: 22 Oct 202124 Oct 2021

Publication series

NameProceeding - 2021 China Automation Congress, CAC 2021

Conference

Conference2021 China Automation Congress, CAC 2021
Country/TerritoryChina
CityBeijing
Period22/10/2124/10/21

Keywords

  • BP neural network
  • ELM
  • GNSS outages
  • GNSS/INS integrated navigation

Fingerprint

Dive into the research topics of 'A fusion method based on ANN to overcome the GNSS Outages for GNSS/INS System'. Together they form a unique fingerprint.

Cite this