Dynamic attack motion prediction for kendo agent

Yasufumi Tanaka; Kazuhiro Kosuge

doi:10.1109/IROS.2014.6942857

Dynamic attack motion prediction for kendo agent

Yasufumi Tanaka, Kazuhiro Kosuge

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

4 Citations (Scopus)

Abstract

A motion prediction method using Gaussian Mixture Models (GMM) is applied to a kendo agent (Kendo is a traditional Japanese martial art). Human player motion is measured by a motion capture system, using markers attached to each of the player's joints. Measurement information is converted to a state vector with Euler angles to indicate orientation of the sword and orientation of each part of the player's body. To model the motion as a nonlinear dynamical system, GMMs are generated from a demonstration set when an opponent is attacked. The efficiency of the proposed method is experimentally verified.

Original language	English
Title of host publication	IROS 2014 Conference Digest - IEEE/RSJ International Conference on Intelligent Robots and Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2187-2193
Number of pages	7
ISBN (Electronic)	9781479969340
DOIs	https://doi.org/10.1109/IROS.2014.6942857
Publication status	Published - 2014 Oct 31
Externally published	Yes
Event	2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014 - Chicago, United States Duration: 2014 Sep 14 → 2014 Sep 18

Publication series

Name	IEEE International Conference on Intelligent Robots and Systems
ISSN (Print)	2153-0858
ISSN (Electronic)	2153-0866

Other

Other	2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014
Country/Territory	United States
City	Chicago
Period	14/9/14 → 14/9/18

ASJC Scopus subject areas

Control and Systems Engineering
Software
Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1109/IROS.2014.6942857

Cite this

Tanaka, Y., & Kosuge, K. (2014). Dynamic attack motion prediction for kendo agent. In IROS 2014 Conference Digest - IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 2187-2193). [6942857] (IEEE International Conference on Intelligent Robots and Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IROS.2014.6942857

Dynamic attack motion prediction for kendo agent. / Tanaka, Yasufumi; Kosuge, Kazuhiro.

IROS 2014 Conference Digest - IEEE/RSJ International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc., 2014. p. 2187-2193 6942857 (IEEE International Conference on Intelligent Robots and Systems).

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

Tanaka, Y & Kosuge, K 2014, Dynamic attack motion prediction for kendo agent. in IROS 2014 Conference Digest - IEEE/RSJ International Conference on Intelligent Robots and Systems., 6942857, IEEE International Conference on Intelligent Robots and Systems, Institute of Electrical and Electronics Engineers Inc., pp. 2187-2193, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014, Chicago, United States, 14/9/14. https://doi.org/10.1109/IROS.2014.6942857

@inproceedings{c78c56c6cbbb49929176650a64e954cb,

title = "Dynamic attack motion prediction for kendo agent",

abstract = "A motion prediction method using Gaussian Mixture Models (GMM) is applied to a kendo agent (Kendo is a traditional Japanese martial art). Human player motion is measured by a motion capture system, using markers attached to each of the player's joints. Measurement information is converted to a state vector with Euler angles to indicate orientation of the sword and orientation of each part of the player's body. To model the motion as a nonlinear dynamical system, GMMs are generated from a demonstration set when an opponent is attacked. The efficiency of the proposed method is experimentally verified.",

author = "Yasufumi Tanaka and Kazuhiro Kosuge",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014 ; Conference date: 14-09-2014 Through 18-09-2014",

year = "2014",

month = oct,

day = "31",

doi = "10.1109/IROS.2014.6942857",

language = "English",

series = "IEEE International Conference on Intelligent Robots and Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2187--2193",

booktitle = "IROS 2014 Conference Digest - IEEE/RSJ International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - Dynamic attack motion prediction for kendo agent

AU - Tanaka, Yasufumi

AU - Kosuge, Kazuhiro

PY - 2014/10/31

Y1 - 2014/10/31

N2 - A motion prediction method using Gaussian Mixture Models (GMM) is applied to a kendo agent (Kendo is a traditional Japanese martial art). Human player motion is measured by a motion capture system, using markers attached to each of the player's joints. Measurement information is converted to a state vector with Euler angles to indicate orientation of the sword and orientation of each part of the player's body. To model the motion as a nonlinear dynamical system, GMMs are generated from a demonstration set when an opponent is attacked. The efficiency of the proposed method is experimentally verified.

AB - A motion prediction method using Gaussian Mixture Models (GMM) is applied to a kendo agent (Kendo is a traditional Japanese martial art). Human player motion is measured by a motion capture system, using markers attached to each of the player's joints. Measurement information is converted to a state vector with Euler angles to indicate orientation of the sword and orientation of each part of the player's body. To model the motion as a nonlinear dynamical system, GMMs are generated from a demonstration set when an opponent is attacked. The efficiency of the proposed method is experimentally verified.

UR - http://www.scopus.com/inward/record.url?scp=84911485911&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911485911&partnerID=8YFLogxK

U2 - 10.1109/IROS.2014.6942857

DO - 10.1109/IROS.2014.6942857

M3 - Conference contribution

AN - SCOPUS:84911485911

T3 - IEEE International Conference on Intelligent Robots and Systems

SP - 2187

EP - 2193

BT - IROS 2014 Conference Digest - IEEE/RSJ International Conference on Intelligent Robots and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014

Y2 - 14 September 2014 through 18 September 2014

ER -

Dynamic attack motion prediction for kendo agent

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this