Robot learning by observation based on Bayesian networks and game pattern graphs for human-robot game interactions

Hyunglae Lee, Hyoungnyoun Kim, Kyung Hwa Park, Ji Hyung Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper describes a new learning by observation algorithm based on Bayesian networks and game pattern graphs. Even with minimal knowledge of a game or human instructions, the robot can learn the game rules by watching human demonstrators repeatedly play the game multiple times. Based on the knowledge acquired from this learning process, represented in Bayesian networks and game pattern graphs, the robot can play games as robustly as humans do. Our learning algorithm for human-robot game interaction is implemented using a teddy bear-like robot and is demonstrated by application to well-known social games, specifically Rock-Paper-Scissors, Muk-Chi-ba and Blackjack.

Original languageEnglish (US)
Title of host publication2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
Pages319-325
Number of pages7
DOIs
StatePublished - 2008
Externally publishedYes
Event2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS - Nice, France
Duration: Sep 22 2008Sep 26 2008

Other

Other2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
CountryFrance
CityNice
Period9/22/089/26/08

Fingerprint

Robot learning
Bayesian networks
Robots
Learning algorithms
Rocks

ASJC Scopus subject areas

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

Cite this

Lee, H., Kim, H., Park, K. H., & Park, J. H. (2008). Robot learning by observation based on Bayesian networks and game pattern graphs for human-robot game interactions. In 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS (pp. 319-325). [4650861] https://doi.org/10.1109/IROS.2008.4650861

Robot learning by observation based on Bayesian networks and game pattern graphs for human-robot game interactions. / Lee, Hyunglae; Kim, Hyoungnyoun; Park, Kyung Hwa; Park, Ji Hyung.

2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2008. p. 319-325 4650861.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, H, Kim, H, Park, KH & Park, JH 2008, Robot learning by observation based on Bayesian networks and game pattern graphs for human-robot game interactions. in 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS., 4650861, pp. 319-325, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS, Nice, France, 9/22/08. https://doi.org/10.1109/IROS.2008.4650861
Lee H, Kim H, Park KH, Park JH. Robot learning by observation based on Bayesian networks and game pattern graphs for human-robot game interactions. In 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2008. p. 319-325. 4650861 https://doi.org/10.1109/IROS.2008.4650861
Lee, Hyunglae ; Kim, Hyoungnyoun ; Park, Kyung Hwa ; Park, Ji Hyung. / Robot learning by observation based on Bayesian networks and game pattern graphs for human-robot game interactions. 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2008. pp. 319-325
@inproceedings{b29f8d9afa184be5ab540102b4a09312,
title = "Robot learning by observation based on Bayesian networks and game pattern graphs for human-robot game interactions",
abstract = "This paper describes a new learning by observation algorithm based on Bayesian networks and game pattern graphs. Even with minimal knowledge of a game or human instructions, the robot can learn the game rules by watching human demonstrators repeatedly play the game multiple times. Based on the knowledge acquired from this learning process, represented in Bayesian networks and game pattern graphs, the robot can play games as robustly as humans do. Our learning algorithm for human-robot game interaction is implemented using a teddy bear-like robot and is demonstrated by application to well-known social games, specifically Rock-Paper-Scissors, Muk-Chi-ba and Blackjack.",
author = "Hyunglae Lee and Hyoungnyoun Kim and Park, {Kyung Hwa} and Park, {Ji Hyung}",
year = "2008",
doi = "10.1109/IROS.2008.4650861",
language = "English (US)",
isbn = "9781424420582",
pages = "319--325",
booktitle = "2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS",

}

TY - GEN

T1 - Robot learning by observation based on Bayesian networks and game pattern graphs for human-robot game interactions

AU - Lee, Hyunglae

AU - Kim, Hyoungnyoun

AU - Park, Kyung Hwa

AU - Park, Ji Hyung

PY - 2008

Y1 - 2008

N2 - This paper describes a new learning by observation algorithm based on Bayesian networks and game pattern graphs. Even with minimal knowledge of a game or human instructions, the robot can learn the game rules by watching human demonstrators repeatedly play the game multiple times. Based on the knowledge acquired from this learning process, represented in Bayesian networks and game pattern graphs, the robot can play games as robustly as humans do. Our learning algorithm for human-robot game interaction is implemented using a teddy bear-like robot and is demonstrated by application to well-known social games, specifically Rock-Paper-Scissors, Muk-Chi-ba and Blackjack.

AB - This paper describes a new learning by observation algorithm based on Bayesian networks and game pattern graphs. Even with minimal knowledge of a game or human instructions, the robot can learn the game rules by watching human demonstrators repeatedly play the game multiple times. Based on the knowledge acquired from this learning process, represented in Bayesian networks and game pattern graphs, the robot can play games as robustly as humans do. Our learning algorithm for human-robot game interaction is implemented using a teddy bear-like robot and is demonstrated by application to well-known social games, specifically Rock-Paper-Scissors, Muk-Chi-ba and Blackjack.

UR - http://www.scopus.com/inward/record.url?scp=69549121869&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69549121869&partnerID=8YFLogxK

U2 - 10.1109/IROS.2008.4650861

DO - 10.1109/IROS.2008.4650861

M3 - Conference contribution

AN - SCOPUS:69549121869

SN - 9781424420582

SP - 319

EP - 325

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

ER -