Prototype Discovery using Quality-Diversity
This work addresses the challenge of aiding engineers in design ideation by integrating user feedback into an automated search process, though it appears incremental as it builds on existing quality-diversity methods.
The paper tackles the problem of computer-aided ideation by introducing an iterative procedure that uses quality-diversity algorithms to search for diverse, high-performing solutions, clustering them into classes represented by prototypes for user selection, with results demonstrated on 2D airfoil and 3D side view mirror domains to enhance engineers' intuition.
An iterative computer-aided ideation procedure is introduced, building on recent quality-diversity algorithms, which search for diverse as well as high-performing solutions. Dimensionality reduction is used to define a similarity space, in which solutions are clustered into classes. These classes are represented by prototypes, which are presented to the user for selection. In the next iteration, quality-diversity focuses on searching within the selected class. A quantitative analysis is performed on a 2D airfoil, and a more complex 3D side view mirror domain shows how computer-aided ideation can help to enhance engineers' intuition while allowing their design decisions to influence the design process.