Localization of outdoor mobile robots using curb features in urban road environments

Hyunsuk Lee, Jooyoung Park, Woo Jin Chung

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Urban road environments that have pavement and curb are characterized as semistructured road environments. In semistructured road environments, the curb provides useful information for robot navigation. In this paper, we present a practical localization method for outdoor mobile robots using the curb features in semistructured road environments. The curb features are especially useful in urban environment, where the GPS failures take place frequently. A curb extraction is conducted on the basis of the Kernel Fisher Discriminant Analysis (KFDA) to minimize false detection. We adopt the Extended Kalman Filter (EKF) to combine the curb information with odometry and Differential Global Positioning System (DGPS). The uncertainty models for the sensors are quantitatively analyzed to provide a practical solution.

Original languageEnglish
Article number368961
JournalMathematical Problems in Engineering
Volume2014
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Curbs
Mobile Robot
Mobile robots
Global positioning system
Fisher Discriminant Analysis
Robot Navigation
Global Positioning System
Model Uncertainty
Differential System
Kalman Filter
Extended Kalman filters
Discriminant analysis
Pavements
kernel
Navigation
Minimise
Sensor
Robots
Sensors

ASJC Scopus subject areas

  • Mathematics(all)
  • Engineering(all)

Cite this

Localization of outdoor mobile robots using curb features in urban road environments. / Lee, Hyunsuk; Park, Jooyoung; Chung, Woo Jin.

In: Mathematical Problems in Engineering, Vol. 2014, 368961, 01.01.2014.

Research output: Contribution to journalArticle

@article{5e22f8aa03344895af099ef6a6201646,
title = "Localization of outdoor mobile robots using curb features in urban road environments",
abstract = "Urban road environments that have pavement and curb are characterized as semistructured road environments. In semistructured road environments, the curb provides useful information for robot navigation. In this paper, we present a practical localization method for outdoor mobile robots using the curb features in semistructured road environments. The curb features are especially useful in urban environment, where the GPS failures take place frequently. A curb extraction is conducted on the basis of the Kernel Fisher Discriminant Analysis (KFDA) to minimize false detection. We adopt the Extended Kalman Filter (EKF) to combine the curb information with odometry and Differential Global Positioning System (DGPS). The uncertainty models for the sensors are quantitatively analyzed to provide a practical solution.",
author = "Hyunsuk Lee and Jooyoung Park and Chung, {Woo Jin}",
year = "2014",
month = "1",
day = "1",
doi = "10.1155/2014/368961",
language = "English",
volume = "2014",
journal = "Mathematical Problems in Engineering",
issn = "1024-123X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Localization of outdoor mobile robots using curb features in urban road environments

AU - Lee, Hyunsuk

AU - Park, Jooyoung

AU - Chung, Woo Jin

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Urban road environments that have pavement and curb are characterized as semistructured road environments. In semistructured road environments, the curb provides useful information for robot navigation. In this paper, we present a practical localization method for outdoor mobile robots using the curb features in semistructured road environments. The curb features are especially useful in urban environment, where the GPS failures take place frequently. A curb extraction is conducted on the basis of the Kernel Fisher Discriminant Analysis (KFDA) to minimize false detection. We adopt the Extended Kalman Filter (EKF) to combine the curb information with odometry and Differential Global Positioning System (DGPS). The uncertainty models for the sensors are quantitatively analyzed to provide a practical solution.

AB - Urban road environments that have pavement and curb are characterized as semistructured road environments. In semistructured road environments, the curb provides useful information for robot navigation. In this paper, we present a practical localization method for outdoor mobile robots using the curb features in semistructured road environments. The curb features are especially useful in urban environment, where the GPS failures take place frequently. A curb extraction is conducted on the basis of the Kernel Fisher Discriminant Analysis (KFDA) to minimize false detection. We adopt the Extended Kalman Filter (EKF) to combine the curb information with odometry and Differential Global Positioning System (DGPS). The uncertainty models for the sensors are quantitatively analyzed to provide a practical solution.

UR - http://www.scopus.com/inward/record.url?scp=84899918524&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899918524&partnerID=8YFLogxK

U2 - 10.1155/2014/368961

DO - 10.1155/2014/368961

M3 - Article

AN - SCOPUS:84899918524

VL - 2014

JO - Mathematical Problems in Engineering

JF - Mathematical Problems in Engineering

SN - 1024-123X

M1 - 368961

ER -