Abstract
Creative problems are ill-defined, and thus experimentation, evaluation, and iteration are key elements of creative problem solving. We present a computational theory of evaluation in creative design. Our technique evaluates a design concept by analogically comparing it with alternative articulations of the concept. We operationalize this theory of analogical comparison in the context of biologically inspired design that uses biological analogies for conceptual design of technological systems. Our technique of analogical comparison supports evaluation of prior technological designs, biological source cases, as well as candidate conceptual designs through analogical mapping between alternative functional models of these design concepts. Given a functional model of a design concept and an alternative functional model of the same design concept, analogical comparison leverages a novel hierarchically organized analogical mapping technique to align the two models and identify the differences between them. Our technique is implemented in an operational artificial intelligence agent called Design Evaluation through Simulation and Comparison (DESC). We evaluate DESC through computational experimentation across several models to illustrate its strengths and limits and to highlight areas for future research.
