Global localization for a mobile robot using laser reflectance and particle filter

Dong Xiang Zhang, Ryo Kurazume

Research output: Contribution to journalArticle

Abstract

Global localization is a fundamental requirement for a mobile robot. Map-based global localization is a popular technique and gives a precise position by comparing a provided geometric map and current sensory data. However, it is quite time-consuming if 3D range data is processed for 6D global localization. On the other hand, appearance-based global localization using a captured image and recorded images is simple and suitable for real-time processing. However, this technique does not work in the dark or in an environment in which the lighting conditions change remarkably. To cope with these problems, we have proposed a two-step strategy which combines map-based global localization and appearance-based global localization. Firstly, several candidate positions are selected according to an appearance-based technique, and then the optimum position is determined by a map-based technique. Instead of camera images, we use reflectance images, which are captured by a laser range finder as a by-product of range sensing. In this paper, a new technique based on this global localization technique is proposed by combining the two step algorithm and a sampling-based approach. To cope with the odometry data, a particle filter is adopted for tracking robot positions. The effectiveness of the proposed technique is demonstrated through experiments in real environments.

Original languageEnglish
Pages (from-to)9-16
Number of pages8
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume17
Issue number1
Publication statusPublished - 2012
Externally publishedYes

Fingerprint

Mobile robots
Lasers
Range finders
Byproducts
Lighting
Cameras
Robots
Sampling
Processing
Experiments

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Computer Science(all)

Cite this

@article{a0ec5c90eba4471bac8371eb2cbce92d,
title = "Global localization for a mobile robot using laser reflectance and particle filter",
abstract = "Global localization is a fundamental requirement for a mobile robot. Map-based global localization is a popular technique and gives a precise position by comparing a provided geometric map and current sensory data. However, it is quite time-consuming if 3D range data is processed for 6D global localization. On the other hand, appearance-based global localization using a captured image and recorded images is simple and suitable for real-time processing. However, this technique does not work in the dark or in an environment in which the lighting conditions change remarkably. To cope with these problems, we have proposed a two-step strategy which combines map-based global localization and appearance-based global localization. Firstly, several candidate positions are selected according to an appearance-based technique, and then the optimum position is determined by a map-based technique. Instead of camera images, we use reflectance images, which are captured by a laser range finder as a by-product of range sensing. In this paper, a new technique based on this global localization technique is proposed by combining the two step algorithm and a sampling-based approach. To cope with the odometry data, a particle filter is adopted for tracking robot positions. The effectiveness of the proposed technique is demonstrated through experiments in real environments.",
author = "Zhang, {Dong Xiang} and Ryo Kurazume",
year = "2012",
language = "English",
volume = "17",
pages = "9--16",
journal = "Research Reports on Information Science and Electrical Engineering of Kyushu University",
issn = "1342-3819",
publisher = "Kyushu University, Faculty of Science",
number = "1",

}

TY - JOUR

T1 - Global localization for a mobile robot using laser reflectance and particle filter

AU - Zhang, Dong Xiang

AU - Kurazume, Ryo

PY - 2012

Y1 - 2012

N2 - Global localization is a fundamental requirement for a mobile robot. Map-based global localization is a popular technique and gives a precise position by comparing a provided geometric map and current sensory data. However, it is quite time-consuming if 3D range data is processed for 6D global localization. On the other hand, appearance-based global localization using a captured image and recorded images is simple and suitable for real-time processing. However, this technique does not work in the dark or in an environment in which the lighting conditions change remarkably. To cope with these problems, we have proposed a two-step strategy which combines map-based global localization and appearance-based global localization. Firstly, several candidate positions are selected according to an appearance-based technique, and then the optimum position is determined by a map-based technique. Instead of camera images, we use reflectance images, which are captured by a laser range finder as a by-product of range sensing. In this paper, a new technique based on this global localization technique is proposed by combining the two step algorithm and a sampling-based approach. To cope with the odometry data, a particle filter is adopted for tracking robot positions. The effectiveness of the proposed technique is demonstrated through experiments in real environments.

AB - Global localization is a fundamental requirement for a mobile robot. Map-based global localization is a popular technique and gives a precise position by comparing a provided geometric map and current sensory data. However, it is quite time-consuming if 3D range data is processed for 6D global localization. On the other hand, appearance-based global localization using a captured image and recorded images is simple and suitable for real-time processing. However, this technique does not work in the dark or in an environment in which the lighting conditions change remarkably. To cope with these problems, we have proposed a two-step strategy which combines map-based global localization and appearance-based global localization. Firstly, several candidate positions are selected according to an appearance-based technique, and then the optimum position is determined by a map-based technique. Instead of camera images, we use reflectance images, which are captured by a laser range finder as a by-product of range sensing. In this paper, a new technique based on this global localization technique is proposed by combining the two step algorithm and a sampling-based approach. To cope with the odometry data, a particle filter is adopted for tracking robot positions. The effectiveness of the proposed technique is demonstrated through experiments in real environments.

UR - http://www.scopus.com/inward/record.url?scp=84904509515&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904509515&partnerID=8YFLogxK

M3 - Article

VL - 17

SP - 9

EP - 16

JO - Research Reports on Information Science and Electrical Engineering of Kyushu University

JF - Research Reports on Information Science and Electrical Engineering of Kyushu University

SN - 1342-3819

IS - 1

ER -