Harnessing Game-Inspired Content Creation for Intuitive Generative Design and Optimization

摘要: A generalizable and example-based model for multi-scale generative design is presented. The model adapts the Wave Function Collapse (WFC) algorithm, a procedural approach popularized in game development, to a quality-diversity (QD) framework, a state-of-the-art multi-solution optimization approach. QD enables the search of high-performing solutions not only against objectives, but along a set of qualitative features -- explicitly ensuring diversity within the solutions. We demonstrate the challenges and opportunities in applying these novel methodologies to AEC-focused problems through a real-world residential complex case study.