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.

A Situational Awareness Approach to Intelligent Vehicle Agents

“…A similar approach has been employed to the control of non-player-characters in Second Life [22] • The normative framework component introduces the element of institutions [8] into the simulation, allowing obligations to be issued to simulation Fig. 1 Illustration of available BSF system components participants (e.g.…”

Social Coordination Frameworks for Social Technical Systems

“…-Regulated systems whose debugging or actual use involves a mixed population of human and software agents. For example, on-line multiplayer games [59], participatory simulation, and on-line dispute resolution [79]. -Coordination systems where, in spite of the need for a sharp specification of interactions, the precise flow of activity may be difficult to perceive in advance, or multiple variants of some activities may be necessary at some point during the system life-span.…”

“…Goal: Norm-influenced behaviour for agents controlling entities in virtual environments, with the aims of (i) enhanced plausibility when interacting with human-controlled avatars (e.g. Second Life) [59] (ii) provision of populations of non-player characters [58] and (iii) exploration of coordinating behaviour in complex situations (e.g. traffic simulation in SUMO) [15].…”

N-Jason: Run-Time Norm Compliance in AgentSpeak(L)

“…Lee et al [12] demonstrate a governance mechanism using this institutional model that shows how the normative consequences of particular actions can be delivered to agents' minds as percepts (to conventional Jason agents rather than the variety described here) either on request or by subscription, making them available for the agent reasoning process.…”

“…The belief base (B) is updated by P in the belief update process (belief-updatefunction (buf) more precisely) (see lines [6][7][8][9][10][11][12][13]. This belief update involves the creation of events in response to each new percept.…”