Extensive and Efficient Search of Human Movements with Hierarchical Reinforcement Learning

CC
CA
2002
Computer Animation 2002
Abstract - Extensive and Efficient Search of Human Movements with Hierarchical Reinforcement Learning

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Tomohiko Mukai Articles by Shigeru Kuriyama Articles by Toyohisa Kaneko

Computer Animation 2002

Geneva, Switzerland

June 19-June 21

ISBN: 0-7695-1594-0

	ASCII Text	x
	Tomohiko Mukai, Shigeru Kuriyama, Toyohisa Kaneko, "Extensive and Efficient Search of Human Movements with Hierarchical Reinforcement Learning," Computer Animation, pp. 103, Computer Animation 2002, 2002.

	BibTex	x
	@article{ 10.1109/CA.2002.1017515, author = {Tomohiko Mukai and Shigeru Kuriyama and Toyohisa Kaneko}, title = {Extensive and Efficient Search of Human Movements with Hierarchical Reinforcement Learning}, journal ={Computer Animation}, volume = {0}, year = {2002}, issn = {1087-4844}, pages = {103}, doi = {http://doi.ieeecomputersociety.org/10.1109/CA.2002.1017515}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Computer Animation TI - Extensive and Efficient Search of Human Movements with Hierarchical Reinforcement Learning SN - 1087-4844 SP EP A1 - Tomohiko Mukai, A1 - Shigeru Kuriyama, A1 - Toyohisa Kaneko, PY - 2002 KW - Reinforcement learning KW - Virtual human KW - Motion generation KW - Hierarchical search VL - 0 JA - Computer Animation ER -

Tomohiko Mukai, Toyohashi University of Technology

Shigeru Kuriyama, Toyohashi University of Technology

Toyohisa Kaneko, Toyohashi University of Technology

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CA.2002.1017515

This paper proposes a method for creating human movements by imposing positional constraints of end-effectors at multiple key-frames. We introduce hierarchical reinforcement learning for efficiently searching postures at each key-frame among the huge number of possible candidates. The mechanical structures of virtual characters are also hierarchically decomposed so as to suit the learning mechanism, and each hierarchy prepares templates of discretely sampled postures for narrowing down the searching space. Our method automatically generates complex movements so that the resulting motions are globally optimized for a whole sequence.

Index Terms:

Reinforcement learning, Virtual human, Motion generation, Hierarchical search

Citation:

Tomohiko Mukai, Shigeru Kuriyama, Toyohisa Kaneko, "Extensive and Efficient Search of Human Movements with Hierarchical Reinforcement Learning," ca, pp.103, Computer Animation 2002, 2002

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.