Arbitration of Autonomous Multimedia Objects with a Multi-Agent System

In interactive multimedia applications, the objects composing the scene are increasingly considered as autonomous agents. Although autonomy brings flexibility and realism in the animation, objects´ autonomy needs to be controlled. In this purpose we must be able to specify the rights and duties of objects. In this paper, we present the Moise^Inst meta-model aiming at specifying normative organisations of agents according to four points of view: structural, functional, contextual and normative. We show how this model is used within an application of interactive TV game show where avatars are based on agents