Extended BDI framework for modelling human decision-making in complex automated manufacturing systems

This paper presents a novel software agent model to replace the partial decision-making function of a human. The proposed model, employing the belief, desire, intention (BDI) agent framework, is capable of (1) generating plans in real time, (2) supporting both the reactive and the proactive decision-making, (3) maintaining situation awareness in human language such as logic, and (4) changing the commitment strategy adaptive to historical performance. In this paper, the proposed model has been developed in the context of the human operator who is responsible for error detection and recovery in a complex automated manufacturing system. A distributed computing platform has been used to integrate an agent (implemented in JACK), real human, and the environment (Arena simulation software).