Improved method for action modeling using Bayesian probability theory

Yunsick Sung; Kyhyun Um; Kyungeun Cho

doi:10.1007/978-94-007-5860-5_122

Improved method for action modeling using Bayesian probability theory

Yunsick Sung, Kyhyun Um, Kyungeun Cho

Department of Computer Science and Artificial Intelligence

Dongguk University

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

Abstract

The technical development of service robots has enhanced the variety of services provided by them to human beings. Service robots need to interact with human beings; hence, they require considerable learning time. The learning time can be reduced by adopting a learning approach in a virtual environment. To this end, it is necessary to describe a human being's movements in the virtual environment. In this paper, we propose a method to generate an action model of a virtual character by calculating the probability of human movements using Bayesian probability. The virtual character selects actions based on the action model, and it executes these actions. Using the proposed method, the path of a virtual character was decreased by around 74 %, as compared to related methods based on Bayesian probability.

Original language	English
Title of host publication	IT Convergence and Security 2012
Pages	1009-1013
Number of pages	5
DOIs	https://doi.org/10.1007/978-94-007-5860-5_122
State	Published - 2013
Event	International Conference on IT Convergence and Security, ICITCS 2012 - Pyeong Chang, Korea, Republic of Duration: 5 Dec 2012 → 7 Dec 2012

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	215 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	International Conference on IT Convergence and Security, ICITCS 2012
Country/Territory	Korea, Republic of
City	Pyeong Chang
Period	5/12/12 → 7/12/12

Keywords

Bayesian probability
Programming by demonstration
Service robot
Virtual environment

Access to Document

10.1007/978-94-007-5860-5_122

Cite this

@inproceedings{6b4ac040447942ca9bd8e19383bb5a3e,

title = "Improved method for action modeling using Bayesian probability theory",

abstract = "The technical development of service robots has enhanced the variety of services provided by them to human beings. Service robots need to interact with human beings; hence, they require considerable learning time. The learning time can be reduced by adopting a learning approach in a virtual environment. To this end, it is necessary to describe a human being's movements in the virtual environment. In this paper, we propose a method to generate an action model of a virtual character by calculating the probability of human movements using Bayesian probability. The virtual character selects actions based on the action model, and it executes these actions. Using the proposed method, the path of a virtual character was decreased by around 74 %, as compared to related methods based on Bayesian probability.",

keywords = "Bayesian probability, Programming by demonstration, Service robot, Virtual environment",

author = "Yunsick Sung and Kyhyun Um and Kyungeun Cho",

year = "2013",

doi = "10.1007/978-94-007-5860-5_122",

language = "English",

isbn = "9789400758599",

series = "Lecture Notes in Electrical Engineering",

pages = "1009--1013",

booktitle = "IT Convergence and Security 2012",

note = "International Conference on IT Convergence and Security, ICITCS 2012 ; Conference date: 05-12-2012 Through 07-12-2012",

}

TY - GEN

T1 - Improved method for action modeling using Bayesian probability theory

AU - Sung, Yunsick

AU - Um, Kyhyun

AU - Cho, Kyungeun

PY - 2013

Y1 - 2013

N2 - The technical development of service robots has enhanced the variety of services provided by them to human beings. Service robots need to interact with human beings; hence, they require considerable learning time. The learning time can be reduced by adopting a learning approach in a virtual environment. To this end, it is necessary to describe a human being's movements in the virtual environment. In this paper, we propose a method to generate an action model of a virtual character by calculating the probability of human movements using Bayesian probability. The virtual character selects actions based on the action model, and it executes these actions. Using the proposed method, the path of a virtual character was decreased by around 74 %, as compared to related methods based on Bayesian probability.

AB - The technical development of service robots has enhanced the variety of services provided by them to human beings. Service robots need to interact with human beings; hence, they require considerable learning time. The learning time can be reduced by adopting a learning approach in a virtual environment. To this end, it is necessary to describe a human being's movements in the virtual environment. In this paper, we propose a method to generate an action model of a virtual character by calculating the probability of human movements using Bayesian probability. The virtual character selects actions based on the action model, and it executes these actions. Using the proposed method, the path of a virtual character was decreased by around 74 %, as compared to related methods based on Bayesian probability.

KW - Bayesian probability

KW - Programming by demonstration

KW - Service robot

KW - Virtual environment

UR - http://www.scopus.com/inward/record.url?scp=84874130048&partnerID=8YFLogxK

U2 - 10.1007/978-94-007-5860-5_122

DO - 10.1007/978-94-007-5860-5_122

M3 - Conference contribution

AN - SCOPUS:84874130048

SN - 9789400758599

T3 - Lecture Notes in Electrical Engineering

SP - 1009

EP - 1013

BT - IT Convergence and Security 2012

T2 - International Conference on IT Convergence and Security, ICITCS 2012

Y2 - 5 December 2012 through 7 December 2012

ER -

Improved method for action modeling using Bayesian probability theory

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this