Design Modeling Symposium 2022

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

Fig. 1. Collapsing process of the WFC

Abstract

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

Lorenzo Villaggi, James Stoddart, Adam Gaier

Design Modeling Symposium 2022

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.

Download publication

Related Resources

Publication

2023

Multi-split configuration design for fluid-based thermal management systems

This work introduces a framework for automated exploration of optimal…

Publication

2019

Unsupervised Multi-Task Feature Learning on Point Clouds

We introduce an unsupervised multi-task model to jointly learn point…

Publication

2022

SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks

We present SkexGen, a novel autoregressive generative model for…

Project

2016

HIVE Exhibit

Hive is an innovative and interactive exhibit built through a unique…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us