Modal-power-based haptic motion recognition

Yusuke Kasahara, Tomoyuki Shimono, Hiroaki Kuwahara, Masataka Sato, Kouhei Ohnishi

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Motion recognition based on sensory information is important for providing assistance to human using robots. Several studies have been carried out on motion recognition based on image information. However, in the motion of humans contact with an object can not be evaluated precisely by image-based recognition. This is because the considering force information is very important for describing contact motion. In this paper, a modal-power-based haptic motion recognition is proposed; Modal power is considered to reveal information on both position and force. Modal power is considered to be one of the defining features of human motion. A motion recognition algorithm based on linear discriminant analysis is proposed to distinguish between similar motions. Haptic information is extracted using a bilateral master-slave system. Then, the observed motion is decomposed in terms of primitive functions in a modal space. The experimental results show the effectiveness of the proposed method.

Original languageEnglish
JournalIEEJ Transactions on Industry Applications
Volume130
Issue number4
Publication statusPublished - 2010

Fingerprint

Discriminant analysis
Robots

Keywords

  • Bilateral control
  • Haptics
  • Linear discriminant analysis method
  • Modal decomposition
  • Motion recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Kasahara, Y., Shimono, T., Kuwahara, H., Sato, M., & Ohnishi, K. (2010). Modal-power-based haptic motion recognition. IEEJ Transactions on Industry Applications, 130(4).

Modal-power-based haptic motion recognition. / Kasahara, Yusuke; Shimono, Tomoyuki; Kuwahara, Hiroaki; Sato, Masataka; Ohnishi, Kouhei.

In: IEEJ Transactions on Industry Applications, Vol. 130, No. 4, 2010.

Research output: Contribution to journalArticle

Kasahara, Y, Shimono, T, Kuwahara, H, Sato, M & Ohnishi, K 2010, 'Modal-power-based haptic motion recognition', IEEJ Transactions on Industry Applications, vol. 130, no. 4.
Kasahara Y, Shimono T, Kuwahara H, Sato M, Ohnishi K. Modal-power-based haptic motion recognition. IEEJ Transactions on Industry Applications. 2010;130(4).
Kasahara, Yusuke ; Shimono, Tomoyuki ; Kuwahara, Hiroaki ; Sato, Masataka ; Ohnishi, Kouhei. / Modal-power-based haptic motion recognition. In: IEEJ Transactions on Industry Applications. 2010 ; Vol. 130, No. 4.
@article{e66dfd13f5c74fe587fa9dd9b2d5589f,
title = "Modal-power-based haptic motion recognition",
abstract = "Motion recognition based on sensory information is important for providing assistance to human using robots. Several studies have been carried out on motion recognition based on image information. However, in the motion of humans contact with an object can not be evaluated precisely by image-based recognition. This is because the considering force information is very important for describing contact motion. In this paper, a modal-power-based haptic motion recognition is proposed; Modal power is considered to reveal information on both position and force. Modal power is considered to be one of the defining features of human motion. A motion recognition algorithm based on linear discriminant analysis is proposed to distinguish between similar motions. Haptic information is extracted using a bilateral master-slave system. Then, the observed motion is decomposed in terms of primitive functions in a modal space. The experimental results show the effectiveness of the proposed method.",
keywords = "Bilateral control, Haptics, Linear discriminant analysis method, Modal decomposition, Motion recognition",
author = "Yusuke Kasahara and Tomoyuki Shimono and Hiroaki Kuwahara and Masataka Sato and Kouhei Ohnishi",
year = "2010",
language = "English",
volume = "130",
journal = "IEEJ Transactions on Industry Applications",
issn = "0913-6339",
publisher = "The Institute of Electrical Engineers of Japan",
number = "4",

}

TY - JOUR

T1 - Modal-power-based haptic motion recognition

AU - Kasahara, Yusuke

AU - Shimono, Tomoyuki

AU - Kuwahara, Hiroaki

AU - Sato, Masataka

AU - Ohnishi, Kouhei

PY - 2010

Y1 - 2010

N2 - Motion recognition based on sensory information is important for providing assistance to human using robots. Several studies have been carried out on motion recognition based on image information. However, in the motion of humans contact with an object can not be evaluated precisely by image-based recognition. This is because the considering force information is very important for describing contact motion. In this paper, a modal-power-based haptic motion recognition is proposed; Modal power is considered to reveal information on both position and force. Modal power is considered to be one of the defining features of human motion. A motion recognition algorithm based on linear discriminant analysis is proposed to distinguish between similar motions. Haptic information is extracted using a bilateral master-slave system. Then, the observed motion is decomposed in terms of primitive functions in a modal space. The experimental results show the effectiveness of the proposed method.

AB - Motion recognition based on sensory information is important for providing assistance to human using robots. Several studies have been carried out on motion recognition based on image information. However, in the motion of humans contact with an object can not be evaluated precisely by image-based recognition. This is because the considering force information is very important for describing contact motion. In this paper, a modal-power-based haptic motion recognition is proposed; Modal power is considered to reveal information on both position and force. Modal power is considered to be one of the defining features of human motion. A motion recognition algorithm based on linear discriminant analysis is proposed to distinguish between similar motions. Haptic information is extracted using a bilateral master-slave system. Then, the observed motion is decomposed in terms of primitive functions in a modal space. The experimental results show the effectiveness of the proposed method.

KW - Bilateral control

KW - Haptics

KW - Linear discriminant analysis method

KW - Modal decomposition

KW - Motion recognition

UR - http://www.scopus.com/inward/record.url?scp=77953566330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953566330&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:77953566330

VL - 130

JO - IEEJ Transactions on Industry Applications

JF - IEEJ Transactions on Industry Applications

SN - 0913-6339

IS - 4

ER -