Presentation 2004/3/12
Model-based state space segmentation for finding suitable procedure in game task
Yu OHIGASHI, Yugo NAGATA, Satoru ISHIKAWA, Takashi OMORI, Koji MORIKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When human beings perform planning, it seems that they segment the process to achieve a goal. In this paper, we propose the technique for state space segmentation based on primitive local predictors to predict phenomenon. This techinique achieves temporal and spatial segmentation using the event cognition with detecting a switch of multiple local predictors and the cognition of situation used each local predictor. To evaluate the proposed techinique, we perform a computer simulation using a simple ping pong game. Then, we present that the representation acquired with state space segmentation enables a long time prediction.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Model-based state space segmentation / prediction / planning
Paper # NC2003-195
Date of Issue

Conference Information
Committee NC
Conference Date 2004/3/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Model-based state space segmentation for finding suitable procedure in game task
Sub Title (in English)
Keyword(1) Model-based state space segmentation
Keyword(2) prediction
Keyword(3) planning
1st Author's Name Yu OHIGASHI
1st Author's Affiliation Graduate School of Engineering, Hokkaido Univ.()
2nd Author's Name Yugo NAGATA
2nd Author's Affiliation Graduate School of Engineering, Hokkaido Univ.
3rd Author's Name Satoru ISHIKAWA
3rd Author's Affiliation Graduate School of Engineering, Hokkaido Univ.
4th Author's Name Takashi OMORI
4th Author's Affiliation Graduate School of Engineering, Hokkaido Univ.
5th Author's Name Koji MORIKAWA
5th Author's Affiliation Advanced Technology Research Laboratory, Matsushita Electric Industrial Co., Ltd.
Date 2004/3/12
Paper # NC2003-195
Volume (vol) vol.103
Number (no) 734
Page pp.pp.-
#Pages 6
Date of Issue