Towards polite virtual agents using social reasoning techniques

J. Lee, Tingting Li, J. Padget

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The use of polite agents is a new approach in order to improve efficiency and naturalism in navigation for player characters in crowded virtual worlds. This paper aims to model the politeness of virtual humans using logic-based approaches, subject to theory of politeness decomposed of conventional and interpersonal politeness. To do so, we propose a high-level agent architecture combined with normative framework to model and reason about 'polite' behaviours in social situations. With this architecture, we demonstrate (i) specifying polite behaviours as a form of social norms; (ii) generating polite behaviours using social reasoning technique; (iii) deliberation with such norms in belief-desire-intention agents; and (iv) realising physical actions based on the decision. Implementation for social reasoning is achieved by InstAL, based on the semantics of answer set programming. Using experiments with simple collision avoidance model, we show the effectiveness of polite behaviour in navigation designed by such architecture, as well as the adequacy of this architecture for modelling theory of politeness in all circumstances.
Original languageEnglish
Pages (from-to)335-343
Number of pages9
JournalComputer Animation and Virtual Worlds
Volume24
Issue number3-4
Early online date15 May 2013
DOIs
Publication statusPublished - May 2013

Fingerprint

Navigation
Collision avoidance
Computer programming
Semantics
Experiments

Cite this

Towards polite virtual agents using social reasoning techniques. / Lee, J.; Li, Tingting; Padget, J.

In: Computer Animation and Virtual Worlds, Vol. 24, No. 3-4, 05.2013, p. 335-343.

Research output: Contribution to journalArticle

@article{5a294ebddeac46658f2872596f28bd80,
title = "Towards polite virtual agents using social reasoning techniques",
abstract = "The use of polite agents is a new approach in order to improve efficiency and naturalism in navigation for player characters in crowded virtual worlds. This paper aims to model the politeness of virtual humans using logic-based approaches, subject to theory of politeness decomposed of conventional and interpersonal politeness. To do so, we propose a high-level agent architecture combined with normative framework to model and reason about 'polite' behaviours in social situations. With this architecture, we demonstrate (i) specifying polite behaviours as a form of social norms; (ii) generating polite behaviours using social reasoning technique; (iii) deliberation with such norms in belief-desire-intention agents; and (iv) realising physical actions based on the decision. Implementation for social reasoning is achieved by InstAL, based on the semantics of answer set programming. Using experiments with simple collision avoidance model, we show the effectiveness of polite behaviour in navigation designed by such architecture, as well as the adequacy of this architecture for modelling theory of politeness in all circumstances.",
author = "J. Lee and Tingting Li and J. Padget",
year = "2013",
month = "5",
doi = "10.1002/cav.1517",
language = "English",
volume = "24",
pages = "335--343",
journal = "Computer Animation and Virtual Worlds",
issn = "1546-4261",
publisher = "John Wiley and Sons Inc.",
number = "3-4",

}

TY - JOUR

T1 - Towards polite virtual agents using social reasoning techniques

AU - Lee, J.

AU - Li, Tingting

AU - Padget, J.

PY - 2013/5

Y1 - 2013/5

N2 - The use of polite agents is a new approach in order to improve efficiency and naturalism in navigation for player characters in crowded virtual worlds. This paper aims to model the politeness of virtual humans using logic-based approaches, subject to theory of politeness decomposed of conventional and interpersonal politeness. To do so, we propose a high-level agent architecture combined with normative framework to model and reason about 'polite' behaviours in social situations. With this architecture, we demonstrate (i) specifying polite behaviours as a form of social norms; (ii) generating polite behaviours using social reasoning technique; (iii) deliberation with such norms in belief-desire-intention agents; and (iv) realising physical actions based on the decision. Implementation for social reasoning is achieved by InstAL, based on the semantics of answer set programming. Using experiments with simple collision avoidance model, we show the effectiveness of polite behaviour in navigation designed by such architecture, as well as the adequacy of this architecture for modelling theory of politeness in all circumstances.

AB - The use of polite agents is a new approach in order to improve efficiency and naturalism in navigation for player characters in crowded virtual worlds. This paper aims to model the politeness of virtual humans using logic-based approaches, subject to theory of politeness decomposed of conventional and interpersonal politeness. To do so, we propose a high-level agent architecture combined with normative framework to model and reason about 'polite' behaviours in social situations. With this architecture, we demonstrate (i) specifying polite behaviours as a form of social norms; (ii) generating polite behaviours using social reasoning technique; (iii) deliberation with such norms in belief-desire-intention agents; and (iv) realising physical actions based on the decision. Implementation for social reasoning is achieved by InstAL, based on the semantics of answer set programming. Using experiments with simple collision avoidance model, we show the effectiveness of polite behaviour in navigation designed by such architecture, as well as the adequacy of this architecture for modelling theory of politeness in all circumstances.

UR - http://www.scopus.com/inward/record.url?scp=84877872522&partnerID=8YFLogxK

UR - http://dx.doi.org/10.1002/cav.1517

U2 - 10.1002/cav.1517

DO - 10.1002/cav.1517

M3 - Article

VL - 24

SP - 335

EP - 343

JO - Computer Animation and Virtual Worlds

JF - Computer Animation and Virtual Worlds

SN - 1546-4261

IS - 3-4

ER -