Wheel slip classification method for mobile robot in sandy terrain using in-wheel sensor

Takuya Omura, Genya Ishigami

Research output: Contribution to journalArticle

Abstract

This paper proposes a method that can estimate and classify the magnitude of wheel slippage for a mobile robot in sandy terrains. The proposed method exploits a sensor suite, called an in-wheel sensor, which measures the normal force and contact angle at the wheel-sand interaction boundary. An experimental test using the in-wheel sensor reveals that the maximum normal force and exit angle of the wheel explicitly vary with the magnitude of the wheel slippage. These characteristics are then fed into a machine learning algorithm, which classifies the wheel slippage into three categories: non-stuck wheel, quasi-stuck wheel, and stuck wheel. The usefulness of the proposed method for slip classification is experimentally evaluated using a four-wheel-drive test bed rover.

Original languageEnglish
Pages (from-to)902-910
Number of pages9
JournalJournal of Robotics and Mechatronics
Volume29
Issue number5
DOIs
Publication statusPublished - 2017 Oct 1

Fingerprint

Mobile robots
Wheels
Sensors
Learning algorithms
Contact angle
Learning systems
Sand

Keywords

  • In-wheel sensor
  • Support vector machine
  • Wheel slip classification
  • Wheel-soil interaction

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Wheel slip classification method for mobile robot in sandy terrain using in-wheel sensor. / Omura, Takuya; Ishigami, Genya.

In: Journal of Robotics and Mechatronics, Vol. 29, No. 5, 01.10.2017, p. 902-910.

Research output: Contribution to journalArticle

@article{98e73fe3c56c4d8bab9c0438a9cc55d3,
title = "Wheel slip classification method for mobile robot in sandy terrain using in-wheel sensor",
abstract = "This paper proposes a method that can estimate and classify the magnitude of wheel slippage for a mobile robot in sandy terrains. The proposed method exploits a sensor suite, called an in-wheel sensor, which measures the normal force and contact angle at the wheel-sand interaction boundary. An experimental test using the in-wheel sensor reveals that the maximum normal force and exit angle of the wheel explicitly vary with the magnitude of the wheel slippage. These characteristics are then fed into a machine learning algorithm, which classifies the wheel slippage into three categories: non-stuck wheel, quasi-stuck wheel, and stuck wheel. The usefulness of the proposed method for slip classification is experimentally evaluated using a four-wheel-drive test bed rover.",
keywords = "In-wheel sensor, Support vector machine, Wheel slip classification, Wheel-soil interaction",
author = "Takuya Omura and Genya Ishigami",
year = "2017",
month = "10",
day = "1",
doi = "10.20965/jrm.2017.p0902",
language = "English",
volume = "29",
pages = "902--910",
journal = "Journal of Robotics and Mechatronics",
issn = "0915-3942",
publisher = "Fuji Technology Press",
number = "5",

}

TY - JOUR

T1 - Wheel slip classification method for mobile robot in sandy terrain using in-wheel sensor

AU - Omura, Takuya

AU - Ishigami, Genya

PY - 2017/10/1

Y1 - 2017/10/1

N2 - This paper proposes a method that can estimate and classify the magnitude of wheel slippage for a mobile robot in sandy terrains. The proposed method exploits a sensor suite, called an in-wheel sensor, which measures the normal force and contact angle at the wheel-sand interaction boundary. An experimental test using the in-wheel sensor reveals that the maximum normal force and exit angle of the wheel explicitly vary with the magnitude of the wheel slippage. These characteristics are then fed into a machine learning algorithm, which classifies the wheel slippage into three categories: non-stuck wheel, quasi-stuck wheel, and stuck wheel. The usefulness of the proposed method for slip classification is experimentally evaluated using a four-wheel-drive test bed rover.

AB - This paper proposes a method that can estimate and classify the magnitude of wheel slippage for a mobile robot in sandy terrains. The proposed method exploits a sensor suite, called an in-wheel sensor, which measures the normal force and contact angle at the wheel-sand interaction boundary. An experimental test using the in-wheel sensor reveals that the maximum normal force and exit angle of the wheel explicitly vary with the magnitude of the wheel slippage. These characteristics are then fed into a machine learning algorithm, which classifies the wheel slippage into three categories: non-stuck wheel, quasi-stuck wheel, and stuck wheel. The usefulness of the proposed method for slip classification is experimentally evaluated using a four-wheel-drive test bed rover.

KW - In-wheel sensor

KW - Support vector machine

KW - Wheel slip classification

KW - Wheel-soil interaction

UR - http://www.scopus.com/inward/record.url?scp=85031911402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031911402&partnerID=8YFLogxK

U2 - 10.20965/jrm.2017.p0902

DO - 10.20965/jrm.2017.p0902

M3 - Article

AN - SCOPUS:85031911402

VL - 29

SP - 902

EP - 910

JO - Journal of Robotics and Mechatronics

JF - Journal of Robotics and Mechatronics

SN - 0915-3942

IS - 5

ER -