Architectures multi-agents génériques à base de réseaux de Pétri colorés temporisés pour la fusion multimodale en entrée

Abstract

The multimodal featuring fusion for natural human-computer interaction involves complex intelligent architectures to face unexpected errors and mistakes made by users. These architectures should react to events that occur simultaneously with eventual redundancy from different input media. In this paper, agent based generic architectures for multimedia multimodal dialog protocols are proposed. Global agents are decomposed into relevant components. Each element is modeled separately. The elementary models are then linked together into timed colored Petri nets to obtain the full architecture. Hence, maintainability, understandability and modification of the architecture are facilitated. For validation purpose, the proposed multi-agent architectures are applied on a practical example.