Flexible conversation management using a BDI agent approach

Authors:
Wilson Wong;Lawrence Cavedon;John Thangarajah;Lin Padgham
Affiliations:
School of Computer Science and IT, RMIT University, Melbourne, Australia;School of Computer Science and IT, RMIT University, Melbourne, Australia;School of Computer Science and IT, RMIT University, Melbourne, Australia;School of Computer Science and IT, RMIT University, Melbourne, Australia
Venue:
IVA'12 Proceedings of the 12th international conference on Intelligent Virtual Agents
Year:
2012

Citing 10
Cited 0

Developing Intelligent Agent Systems: A Practical Guide

Developing Intelligent Agent Systems: A Practical Guide
An agent-based approach to dialogue management in personal assistants

Proceedings of the 10th international conference on Intelligent user interfaces
Establishing and maintaining long-term human-computer relationships

ACM Transactions on Computer-Human Interaction (TOCHI)
Accurate unlexicalized parsing

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Enjoyment: lessons from Karasek

Funology
A survey on sentiment detection of reviews

Expert Systems with Applications: An International Journal
Detecting user engagement with a robot companion using task and social interaction-based features

Proceedings of the 2009 international conference on Multimodal interfaces
An Introduction to MultiAgent Systems

An Introduction to MultiAgent Systems
How was your day?: a companion ECA

Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Health conversational system based on contextual matching of community-driven question-answer pairs

Proceedings of the 20th ACM international conference on Information and knowledge management

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a BDI (Belief, Desire, Intention) goal-oriented architecture for a conversational virtual companion embodied as a child's Toy, designed to be both entertaining and capable of carrying out collaborative tasks. We argue that the goal-oriented approach supports both structured conversational activities (e.g., story-telling, collaborative games) as well as more "free-flowing" engaging dialogue with variation and some unpredictability. BDI plans encode the knowledge required for the structured engagements, with the use of multiple plans for conversational goals providing variation in the interactions.