Developing multiagent systems for design activity analysis

Engineering design is a complex socio-technical activity characterized by co-evolution of problem and solution. However, the actual design theories are not well-suited to represent and model the complexity of design activity, the co-evolution and its dynamics. Therefore, there is a need to develop design activity reasoning theories and tools, which can theorize and simulate the model of co-evolution and its dynamics. Multiagent systems have the capacity to play an important role in developing and analyzing models and theories of interactivity in socio-technical societies, particularly in design. This paper first addresses a theory for design activity reasoning. Then, it will present a multiagent system, called ADEA (Agents-based DEsign activity Analysis), in order to model, simulate and analyze this theory. The agents of the ADEA platform formalize the necessary design roles, characterizing the design activity as well as the relationship between design parameters in the design space. ADEA's platform shows that cognitive limitation of role agents has been overcome, considering their relationship with the design space modeled as a network of design parameter agents.