Motion recognition and generation by combining reference-point-dependent probabilistic models

Komei Sugiura; Naoto Iwahashi

doi:10.1109/IROS.2008.4651169

Motion recognition and generation by combining reference-point-dependent probabilistic models

Komei Sugiura, Naoto Iwahashi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

Abstract

This paper presents a method to recognize and generate sequential motions for object manipulation such as placing one object on another or rotating it. Motions are learned using reference-point-dependent probabilistic models, which are then transformed to the same coordinate system and combined for motion recognition/generation. We conducted physical experiments in which a user demonstrated the manipulation of puppets and toys, and obtained a recognition accuracy of 63% for the sequential motions. Furthermore, the results of motion generation experiments performed with a robot arm are presented.

Original language	English
Title of host publication	2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
Pages	852-857
Number of pages	6
DOIs	https://doi.org/10.1109/IROS.2008.4651169
Publication status	Published - 2008 Dec 1
Externally published	Yes
Event	2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS - Nice, France Duration: 2008 Sep 22 → 2008 Sep 26

Publication series

Name	2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

Other

Other	2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
Country	France
City	Nice
Period	08/9/22 → 08/9/26

ASJC Scopus subject areas

Artificial Intelligence
Computer Vision and Pattern Recognition
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/IROS.2008.4651169

Fingerprint Dive into the research topics of 'Motion recognition and generation by combining reference-point-dependent probabilistic models'. Together they form a unique fingerprint.

Cite this

Sugiura, K., & Iwahashi, N. (2008). Motion recognition and generation by combining reference-point-dependent probabilistic models. In 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS (pp. 852-857). [4651169] (2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS). https://doi.org/10.1109/IROS.2008.4651169

Motion recognition and generation by combining reference-point-dependent probabilistic models. / Sugiura, Komei; Iwahashi, Naoto.

2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2008. p. 852-857 4651169 (2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sugiura, K & Iwahashi, N 2008, Motion recognition and generation by combining reference-point-dependent probabilistic models. in 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS., 4651169, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS, pp. 852-857, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS, Nice, France, 08/9/22. https://doi.org/10.1109/IROS.2008.4651169

@inproceedings{d6f5b44cfb7c4525a11c162c623605e0,

title = "Motion recognition and generation by combining reference-point-dependent probabilistic models",

abstract = "This paper presents a method to recognize and generate sequential motions for object manipulation such as placing one object on another or rotating it. Motions are learned using reference-point-dependent probabilistic models, which are then transformed to the same coordinate system and combined for motion recognition/generation. We conducted physical experiments in which a user demonstrated the manipulation of puppets and toys, and obtained a recognition accuracy of 63% for the sequential motions. Furthermore, the results of motion generation experiments performed with a robot arm are presented.",

author = "Komei Sugiura and Naoto Iwahashi",

year = "2008",

month = dec,

day = "1",

doi = "10.1109/IROS.2008.4651169",

language = "English",

isbn = "9781424420582",

series = "2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS",

pages = "852--857",

booktitle = "2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS",

note = "2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS ; Conference date: 22-09-2008 Through 26-09-2008",

}

TY - GEN

T1 - Motion recognition and generation by combining reference-point-dependent probabilistic models

AU - Sugiura, Komei

AU - Iwahashi, Naoto

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper presents a method to recognize and generate sequential motions for object manipulation such as placing one object on another or rotating it. Motions are learned using reference-point-dependent probabilistic models, which are then transformed to the same coordinate system and combined for motion recognition/generation. We conducted physical experiments in which a user demonstrated the manipulation of puppets and toys, and obtained a recognition accuracy of 63% for the sequential motions. Furthermore, the results of motion generation experiments performed with a robot arm are presented.

AB - This paper presents a method to recognize and generate sequential motions for object manipulation such as placing one object on another or rotating it. Motions are learned using reference-point-dependent probabilistic models, which are then transformed to the same coordinate system and combined for motion recognition/generation. We conducted physical experiments in which a user demonstrated the manipulation of puppets and toys, and obtained a recognition accuracy of 63% for the sequential motions. Furthermore, the results of motion generation experiments performed with a robot arm are presented.

UR - http://www.scopus.com/inward/record.url?scp=69549120078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69549120078&partnerID=8YFLogxK

U2 - 10.1109/IROS.2008.4651169

DO - 10.1109/IROS.2008.4651169

M3 - Conference contribution

AN - SCOPUS:69549120078

SN - 9781424420582

T3 - 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

SP - 852

EP - 857

BT - 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

T2 - 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

Y2 - 22 September 2008 through 26 September 2008

ER -