Concept sharing and adaptive coordination for collaborative design through interactive decision model construction

摘要

This paper discusses about the formulation of the collaborative design by multiple agents using the technique from machine learning in artificial intelligence and uncertainty reasoning from the decision theory. The fundamental issue for the collaborative design is to establish concept-sharing and seamless coordination among design participants (i.e., design agents). For this purpose, we introduce a learning technique for concept formation from prior examples (i.e., design precedents) as a method for constructing a design agent's own design-prototype hierarchy. Then, a design coordinator's activity is formulated decision-theoretically concerning withthe selection of design prototypes. The formulation is illustrated using the examples of designing girders of the bridge.