Robotic intelligence with behavior selection network for bayesian network ensemble

Keum Sung Hwang, Han Saem Park, Sung-Bae Cho

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

1 Citation (Scopus)

Abstract

Scene understanding is an important and difficult problem in intelligent robotics and computer vision. Since visual information is uncertain due to several reasons, we need a novel method that has robustness to the uncertainty. Bayesian probabilistic approach is robust to manage the uncertainty and powerful to model high-level contexts. Moreover, Bayesian network can be adapted to environment efficiently by learning. In this paper, we propose a Bayesian network ensemble technique based on behavior selection network. The method includes how to handle uncertainty based on probabilistic approach, and how to combine multiple Bayesian networks. An experiment with a mobile robot simulation presents how the proposed ensemble method works and can be used effectively.

Original languageEnglish
Title of host publication2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings
Pages151-154
Number of pages4
DOIs
Publication statusPublished - 2009 Jul 20
Event2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Nashville, TN, United States
Duration: 2009 Mar 302009 Apr 2

Publication series

Name2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings

Other

Other2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009
CountryUnited States
CityNashville, TN
Period09/3/3009/4/2

Fingerprint

Bayesian networks
Robotics
Mobile robots
Computer vision
Uncertainty
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition

Cite this

Hwang, K. S., Park, H. S., & Cho, S-B. (2009). Robotic intelligence with behavior selection network for bayesian network ensemble. In 2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings (pp. 151-154). [4937920] (2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings). https://doi.org/10.1109/RIISS.2009.4937920
Hwang, Keum Sung ; Park, Han Saem ; Cho, Sung-Bae. / Robotic intelligence with behavior selection network for bayesian network ensemble. 2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings. 2009. pp. 151-154 (2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings).
@inproceedings{d942336c516b41fc830e5d710ed51126,
title = "Robotic intelligence with behavior selection network for bayesian network ensemble",
abstract = "Scene understanding is an important and difficult problem in intelligent robotics and computer vision. Since visual information is uncertain due to several reasons, we need a novel method that has robustness to the uncertainty. Bayesian probabilistic approach is robust to manage the uncertainty and powerful to model high-level contexts. Moreover, Bayesian network can be adapted to environment efficiently by learning. In this paper, we propose a Bayesian network ensemble technique based on behavior selection network. The method includes how to handle uncertainty based on probabilistic approach, and how to combine multiple Bayesian networks. An experiment with a mobile robot simulation presents how the proposed ensemble method works and can be used effectively.",
author = "Hwang, {Keum Sung} and Park, {Han Saem} and Sung-Bae Cho",
year = "2009",
month = "7",
day = "20",
doi = "10.1109/RIISS.2009.4937920",
language = "English",
isbn = "9781424427536",
series = "2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings",
pages = "151--154",
booktitle = "2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings",

}

Hwang, KS, Park, HS & Cho, S-B 2009, Robotic intelligence with behavior selection network for bayesian network ensemble. in 2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings., 4937920, 2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings, pp. 151-154, 2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009, Nashville, TN, United States, 09/3/30. https://doi.org/10.1109/RIISS.2009.4937920

Robotic intelligence with behavior selection network for bayesian network ensemble. / Hwang, Keum Sung; Park, Han Saem; Cho, Sung-Bae.

2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings. 2009. p. 151-154 4937920 (2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings).

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

TY - GEN

T1 - Robotic intelligence with behavior selection network for bayesian network ensemble

AU - Hwang, Keum Sung

AU - Park, Han Saem

AU - Cho, Sung-Bae

PY - 2009/7/20

Y1 - 2009/7/20

N2 - Scene understanding is an important and difficult problem in intelligent robotics and computer vision. Since visual information is uncertain due to several reasons, we need a novel method that has robustness to the uncertainty. Bayesian probabilistic approach is robust to manage the uncertainty and powerful to model high-level contexts. Moreover, Bayesian network can be adapted to environment efficiently by learning. In this paper, we propose a Bayesian network ensemble technique based on behavior selection network. The method includes how to handle uncertainty based on probabilistic approach, and how to combine multiple Bayesian networks. An experiment with a mobile robot simulation presents how the proposed ensemble method works and can be used effectively.

AB - Scene understanding is an important and difficult problem in intelligent robotics and computer vision. Since visual information is uncertain due to several reasons, we need a novel method that has robustness to the uncertainty. Bayesian probabilistic approach is robust to manage the uncertainty and powerful to model high-level contexts. Moreover, Bayesian network can be adapted to environment efficiently by learning. In this paper, we propose a Bayesian network ensemble technique based on behavior selection network. The method includes how to handle uncertainty based on probabilistic approach, and how to combine multiple Bayesian networks. An experiment with a mobile robot simulation presents how the proposed ensemble method works and can be used effectively.

UR - http://www.scopus.com/inward/record.url?scp=67650373832&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650373832&partnerID=8YFLogxK

U2 - 10.1109/RIISS.2009.4937920

DO - 10.1109/RIISS.2009.4937920

M3 - Conference contribution

SN - 9781424427536

T3 - 2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings

SP - 151

EP - 154

BT - 2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings

ER -

Hwang KS, Park HS, Cho S-B. Robotic intelligence with behavior selection network for bayesian network ensemble. In 2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings. 2009. p. 151-154. 4937920. (2009 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2009 - Proceedings). https://doi.org/10.1109/RIISS.2009.4937920