A Context-aware Architecture for Mental Model Sharing through Semantic Movement in Intelligent Agents

Abstract

Recent studies in multi-agent systems are paying increasingly more attention to the paradigm of designing intelligent agents with human inspired concepts. One of the main cognitive concepts driving the core of many recent approaches in multi agent systems is shared mental models. In this paper, we propose an architecture for sharing mental models based on a new concept called semantic movement. This architecture has been inspired by a variety of mental models in humans and supports agents working in different simultaneous contexts and it uses semantic movement as a conflict resolution mechanism. Semantic movement is a kind of transition from the present mental states to some new states in order to resolve harming conflicts between mental models of participants. We formalized the semantic movement process in order to use it in our proposed architecture. Our test bed to evaluate this architecture is a set of complex scenarios which are likely impossible to be solved by individual agents without sharing. Our architecture exhibits better performance than other alternative methods that have sharing capabilities. We believe that the proposed architecture would be able to provide agents with the ability of generating more consistent behaviors between agents. Moreover, this architecture can become a suitable platform for the negotiation of self interested agents.