Integrating planning and dialogue in a lifestyle agent

Cameron Smith; Marc Cavazza; Daniel Charlton; Li Zhang; Markku Turunen; Jaakko Hakulinen

doi:10.1007/978-3-540-85483-8_15

Integrating planning and dialogue in a lifestyle agent

Cameron Smith, Marc Cavazza, Daniel Charlton, Li Zhang, Markku Turunen, Jaakko Hakulinen

School of Computer Science

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

10 Citations (Scopus)

Abstract

In this paper, we describe an Embodied Conversational Agent advising users to promote a healthier lifestyle. This embodied agent provides advice on everyday user activities, in order to promote a healthy lifestyle. It operates by generating user activity models (similar to decompositional task models), using a Hierarchical Task Network (HTN) planner. These activity models are refined through various cycles of planning and dialogue, during which the agent suggests possible activities to the user, and the user expresses her preferences in return. A first prototype has been fully implemented (as a spoken dialogue system) and tested with 20 subjects. Early results show a high level of task completion despite the word error rate, and further potential for improvement.

Original language	English
Title of host publication	Intelligent Virtual Agents
Publisher	Springer
Pages	146-153
Volume	5208
ISBN (Print)	978-3-540-85482-1
DOIs	https://doi.org/10.1007/978-3-540-85483-8_15
Publication status	Published - 2008

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
ISSN (Electronic)	0302-9743

Keywords

Multimodal interaction with intelligent virtual agents
embodied cognitive modelling
conversational and non-verbal behavior

Access to Document

10.1007/978-3-540-85483-8_15

Cite this

@inbook{9cb1272230d8419a917999177b7cee38,

title = "Integrating planning and dialogue in a lifestyle agent",

abstract = "In this paper, we describe an Embodied Conversational Agent advising users to promote a healthier lifestyle. This embodied agent provides advice on everyday user activities, in order to promote a healthy lifestyle. It operates by generating user activity models (similar to decompositional task models), using a Hierarchical Task Network (HTN) planner. These activity models are refined through various cycles of planning and dialogue, during which the agent suggests possible activities to the user, and the user expresses her preferences in return. A first prototype has been fully implemented (as a spoken dialogue system) and tested with 20 subjects. Early results show a high level of task completion despite the word error rate, and further potential for improvement.",

keywords = "Multimodal interaction with intelligent virtual agents, embodied cognitive modelling, conversational and non-verbal behavior",

author = "Cameron Smith and Marc Cavazza and Daniel Charlton and Li Zhang and Markku Turunen and Jaakko Hakulinen",

year = "2008",

doi = "10.1007/978-3-540-85483-8\_15",

language = "English",

isbn = "978-3-540-85482-1",

volume = "5208",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "146--153",

booktitle = "Intelligent Virtual Agents",

address = "Germany",

}

TY - CHAP

T1 - Integrating planning and dialogue in a lifestyle agent

AU - Smith, Cameron

AU - Cavazza, Marc

AU - Charlton, Daniel

AU - Zhang, Li

AU - Turunen, Markku

AU - Hakulinen, Jaakko

PY - 2008

Y1 - 2008

N2 - In this paper, we describe an Embodied Conversational Agent advising users to promote a healthier lifestyle. This embodied agent provides advice on everyday user activities, in order to promote a healthy lifestyle. It operates by generating user activity models (similar to decompositional task models), using a Hierarchical Task Network (HTN) planner. These activity models are refined through various cycles of planning and dialogue, during which the agent suggests possible activities to the user, and the user expresses her preferences in return. A first prototype has been fully implemented (as a spoken dialogue system) and tested with 20 subjects. Early results show a high level of task completion despite the word error rate, and further potential for improvement.

AB - In this paper, we describe an Embodied Conversational Agent advising users to promote a healthier lifestyle. This embodied agent provides advice on everyday user activities, in order to promote a healthy lifestyle. It operates by generating user activity models (similar to decompositional task models), using a Hierarchical Task Network (HTN) planner. These activity models are refined through various cycles of planning and dialogue, during which the agent suggests possible activities to the user, and the user expresses her preferences in return. A first prototype has been fully implemented (as a spoken dialogue system) and tested with 20 subjects. Early results show a high level of task completion despite the word error rate, and further potential for improvement.

KW - Multimodal interaction with intelligent virtual agents

KW - embodied cognitive modelling

KW - conversational and non-verbal behavior

UR - https://www.scopus.com/pages/publications/52149111868

U2 - 10.1007/978-3-540-85483-8_15

DO - 10.1007/978-3-540-85483-8_15

M3 - Chapter

SN - 978-3-540-85482-1

VL - 5208

T3 - Lecture Notes in Computer Science

SP - 146

EP - 153

BT - Intelligent Virtual Agents

PB - Springer

ER -

Integrating planning and dialogue in a lifestyle agent

Abstract

Publication series

Keywords

Access to Document

Other files and links

Fingerprint

Cite this