Localization of mobile robots via an enhanced particle filter incorporating tournament selection and nelder-mead simplex search

Chen-Chien James Hsu, Ching Chang Wong, Hung Chih Teng, Nai Jen Li, Cheng Yao Ho

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

A localization method based on an enhanced particle filter incorporating tournament selection and Nelder-Mead simplex search (NM-EPF) for autonomous mobile robots navigating in a soccer robot game field is proposed in this paper. To analyze the environment, an omnidirectional vision device is mounted on top of the robot. Through detecting the white boundary lines relative to the robot in the game field, weighting for each particle representing the robot's pose can be iteratively updated via the proposed NM-EPF algorithm. Thanks to the hybridization effect of the NM-EPF, particles converge to the actual position of the robot in a responsive way while tackling uncertainties. Simulation and experiment results have confirmed that the proposed NM-EPF has better localization performance in the soccer robot game field in comparison to the conventional particle filter.

Original languageEnglish
Pages (from-to)3725-3737
Number of pages13
JournalInternational Journal of Innovative Computing, Information and Control
Volume7
Issue number7 A
Publication statusPublished - 2011 Jul 1

    Fingerprint

Keywords

  • Nelder-mead simplex search
  • Omnidirectional vision
  • Particle filter
  • Robot localization
  • Soccer robot
  • Tournament selection

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Computational Theory and Mathematics

Cite this