Gaussian mixture-sound field landmark model for robot localization

Li Wei Wu*, Chieh Cheng Cheng, Wei Han Liu, Jwu-Sheng Hu

*Corresponding author for this work

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

4 Scopus citations

Abstract

This investigation proposes a robust robot localization system. The system contains a novel Gaussian Mixture-Sound Field Landmark Model (GM-SFLM) and can localize the robot accurately in noisy environments. Moreover, the proposed method depends nothing on the geometry relation between source locations and two microphones; it is able to cover both near-field and far-field problems. With this proposed GM-SFLM, we can localize robot in 2-dimentional indoor environments. Furthermore, we realize the GM-SFLM into a quadruped robot system composed of an eRobot and a robot agent by using embedded Ethernet technology. The experiment demonstrates that when the robot is completely non-line-of-sight, this system still provides high detection accuracy. Additionally, the proposed method has advantages of high accuracy, low-cost, easy to implement and environmental adaptation.

Original languageEnglish
Title of host publicationIEEE International Conference on Mechatronics and Automation, ICMA 2005
Pages438-443
Number of pages6
DOIs
StatePublished - 17 Nov 2005
EventIEEE International Conference on Mechatronics and Automation, ICMA 2005 - Niagara Falls, ON, Canada
Duration: 29 Jul 20051 Aug 2005

Publication series

NameIEEE International Conference on Mechatronics and Automation, ICMA 2005

Conference

ConferenceIEEE International Conference on Mechatronics and Automation, ICMA 2005
CountryCanada
CityNiagara Falls, ON
Period29/07/051/08/05

Keywords

  • GMM
  • Localization
  • Robot
  • Sound field

Fingerprint Dive into the research topics of 'Gaussian mixture-sound field landmark model for robot localization'. Together they form a unique fingerprint.

Cite this