Intention reading from a fuzzy-based human engagement model and behavioural features

Sang Seok Yun, Mun Taek Choi, Munsang Kim, Jae-Bok Song

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This paper presents a novel approach for a quantitative appraisal model to identify human intent so as to interact with a robot and determine an engagement level. To efficiently select an attention target for communication in multi-person interactions, we propose a fuzzy-based classification algorithm which is developed by an incremental learning procedure and which facilitates a multi-dimensional pattern analysis for ambiguous human behaviours. From acquired participants' non-verbal behaviour patterns, we extract the dominant feature data, analyse the generality of the model and verify the effectiveness for proper and prompt gaze behaviour. The proposed model works successfully in multiple people interactions.

Original languageEnglish
Article number49
JournalInternational Journal of Advanced Robotic Systems
Volume9
DOIs
Publication statusPublished - 2012 Aug 10

Fingerprint

Robots
Communication

Keywords

  • Focus of attention
  • Fuzzy min-max neural networks (FMMNN)
  • Gaze behaviour
  • Human-robot interaction
  • Intention reading
  • Multi-modal sensors

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Science Applications

Cite this

Intention reading from a fuzzy-based human engagement model and behavioural features. / Yun, Sang Seok; Choi, Mun Taek; Kim, Munsang; Song, Jae-Bok.

In: International Journal of Advanced Robotic Systems, Vol. 9, 49, 10.08.2012.

Research output: Contribution to journalArticle

@article{5e88bb3518ae4933afd5746f7ac39f58,
title = "Intention reading from a fuzzy-based human engagement model and behavioural features",
abstract = "This paper presents a novel approach for a quantitative appraisal model to identify human intent so as to interact with a robot and determine an engagement level. To efficiently select an attention target for communication in multi-person interactions, we propose a fuzzy-based classification algorithm which is developed by an incremental learning procedure and which facilitates a multi-dimensional pattern analysis for ambiguous human behaviours. From acquired participants' non-verbal behaviour patterns, we extract the dominant feature data, analyse the generality of the model and verify the effectiveness for proper and prompt gaze behaviour. The proposed model works successfully in multiple people interactions.",
keywords = "Focus of attention, Fuzzy min-max neural networks (FMMNN), Gaze behaviour, Human-robot interaction, Intention reading, Multi-modal sensors",
author = "Yun, {Sang Seok} and Choi, {Mun Taek} and Munsang Kim and Jae-Bok Song",
year = "2012",
month = "8",
day = "10",
doi = "10.5772/50648",
language = "English",
volume = "9",
journal = "International Journal of Advanced Robotic Systems",
issn = "1729-8806",
publisher = "Vienna University of Technology",

}

TY - JOUR

T1 - Intention reading from a fuzzy-based human engagement model and behavioural features

AU - Yun, Sang Seok

AU - Choi, Mun Taek

AU - Kim, Munsang

AU - Song, Jae-Bok

PY - 2012/8/10

Y1 - 2012/8/10

N2 - This paper presents a novel approach for a quantitative appraisal model to identify human intent so as to interact with a robot and determine an engagement level. To efficiently select an attention target for communication in multi-person interactions, we propose a fuzzy-based classification algorithm which is developed by an incremental learning procedure and which facilitates a multi-dimensional pattern analysis for ambiguous human behaviours. From acquired participants' non-verbal behaviour patterns, we extract the dominant feature data, analyse the generality of the model and verify the effectiveness for proper and prompt gaze behaviour. The proposed model works successfully in multiple people interactions.

AB - This paper presents a novel approach for a quantitative appraisal model to identify human intent so as to interact with a robot and determine an engagement level. To efficiently select an attention target for communication in multi-person interactions, we propose a fuzzy-based classification algorithm which is developed by an incremental learning procedure and which facilitates a multi-dimensional pattern analysis for ambiguous human behaviours. From acquired participants' non-verbal behaviour patterns, we extract the dominant feature data, analyse the generality of the model and verify the effectiveness for proper and prompt gaze behaviour. The proposed model works successfully in multiple people interactions.

KW - Focus of attention

KW - Fuzzy min-max neural networks (FMMNN)

KW - Gaze behaviour

KW - Human-robot interaction

KW - Intention reading

KW - Multi-modal sensors

UR - http://www.scopus.com/inward/record.url?scp=84868091724&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868091724&partnerID=8YFLogxK

U2 - 10.5772/50648

DO - 10.5772/50648

M3 - Article

AN - SCOPUS:84868091724

VL - 9

JO - International Journal of Advanced Robotic Systems

JF - International Journal of Advanced Robotic Systems

SN - 1729-8806

M1 - 49

ER -