Terrain Classification for Mobile Robots on the Basis of Support Vector Data Description

Hyunsuk Lee, Woo Jin Chung

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The ability to detect traversable terrains is essential for autonomous mobile robots to guarantee safe navigation. In this paper, we present a method for terrain classification for wheeled mobile robots. Our scope is limited to mobile service robots that are used for surveillance or delivery in semi-structured urban environments. A reliable terrain detection scheme is required for both indoor and outdoor applications anytime. A low-cost Lidar (Light detection and ranging) is adopted for terrain detection. To deal with intrinsic measurement errors and uncertainties of the Lidar, the classification criteria are trained through a supervised learning approach. Training data are obtained from manual driving at target environments. Various decision boundaries resulted from a variety of floor conditions, sensor types and robot platforms. The proposed terrain classification scheme is experimentally tested in success.

Original languageEnglish
Pages (from-to)1305-1315
Number of pages11
JournalInternational Journal of Precision Engineering and Manufacturing
Volume19
Issue number9
DOIs
Publication statusPublished - 2018 Sep 1

Fingerprint

Data description
Mobile robots
Robots
Supervised learning
Measurement errors
Navigation
Sensors
Costs

Keywords

  • Classification
  • Mapping
  • Mobile robot
  • Obstacle detection
  • Traversability analysis

ASJC Scopus subject areas

  • Mechanical Engineering
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Cite this

Terrain Classification for Mobile Robots on the Basis of Support Vector Data Description. / Lee, Hyunsuk; Chung, Woo Jin.

In: International Journal of Precision Engineering and Manufacturing, Vol. 19, No. 9, 01.09.2018, p. 1305-1315.

Research output: Contribution to journalArticle

@article{bf910a45817646b69f26cc3240115526,
title = "Terrain Classification for Mobile Robots on the Basis of Support Vector Data Description",
abstract = "The ability to detect traversable terrains is essential for autonomous mobile robots to guarantee safe navigation. In this paper, we present a method for terrain classification for wheeled mobile robots. Our scope is limited to mobile service robots that are used for surveillance or delivery in semi-structured urban environments. A reliable terrain detection scheme is required for both indoor and outdoor applications anytime. A low-cost Lidar (Light detection and ranging) is adopted for terrain detection. To deal with intrinsic measurement errors and uncertainties of the Lidar, the classification criteria are trained through a supervised learning approach. Training data are obtained from manual driving at target environments. Various decision boundaries resulted from a variety of floor conditions, sensor types and robot platforms. The proposed terrain classification scheme is experimentally tested in success.",
keywords = "Classification, Mapping, Mobile robot, Obstacle detection, Traversability analysis",
author = "Hyunsuk Lee and Chung, {Woo Jin}",
year = "2018",
month = "9",
day = "1",
doi = "10.1007/s12541-018-0154-4",
language = "English",
volume = "19",
pages = "1305--1315",
journal = "International Journal of Precision Engineering and Manufacturing",
issn = "1229-8557",
publisher = "Korean Society of Precision Engineering",
number = "9",

}

TY - JOUR

T1 - Terrain Classification for Mobile Robots on the Basis of Support Vector Data Description

AU - Lee, Hyunsuk

AU - Chung, Woo Jin

PY - 2018/9/1

Y1 - 2018/9/1

N2 - The ability to detect traversable terrains is essential for autonomous mobile robots to guarantee safe navigation. In this paper, we present a method for terrain classification for wheeled mobile robots. Our scope is limited to mobile service robots that are used for surveillance or delivery in semi-structured urban environments. A reliable terrain detection scheme is required for both indoor and outdoor applications anytime. A low-cost Lidar (Light detection and ranging) is adopted for terrain detection. To deal with intrinsic measurement errors and uncertainties of the Lidar, the classification criteria are trained through a supervised learning approach. Training data are obtained from manual driving at target environments. Various decision boundaries resulted from a variety of floor conditions, sensor types and robot platforms. The proposed terrain classification scheme is experimentally tested in success.

AB - The ability to detect traversable terrains is essential for autonomous mobile robots to guarantee safe navigation. In this paper, we present a method for terrain classification for wheeled mobile robots. Our scope is limited to mobile service robots that are used for surveillance or delivery in semi-structured urban environments. A reliable terrain detection scheme is required for both indoor and outdoor applications anytime. A low-cost Lidar (Light detection and ranging) is adopted for terrain detection. To deal with intrinsic measurement errors and uncertainties of the Lidar, the classification criteria are trained through a supervised learning approach. Training data are obtained from manual driving at target environments. Various decision boundaries resulted from a variety of floor conditions, sensor types and robot platforms. The proposed terrain classification scheme is experimentally tested in success.

KW - Classification

KW - Mapping

KW - Mobile robot

KW - Obstacle detection

KW - Traversability analysis

UR - http://www.scopus.com/inward/record.url?scp=85053310566&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053310566&partnerID=8YFLogxK

U2 - 10.1007/s12541-018-0154-4

DO - 10.1007/s12541-018-0154-4

M3 - Article

AN - SCOPUS:85053310566

VL - 19

SP - 1305

EP - 1315

JO - International Journal of Precision Engineering and Manufacturing

JF - International Journal of Precision Engineering and Manufacturing

SN - 1229-8557

IS - 9

ER -