AI-Driven Design and Generative Architecture

Project Discover: An application of generative design for architectural space planning

Danil Nagy, Damon Lau, John Locke, James Stoddart, Lorenzo Villaggi, Ray Wang, Dale Zhao, David Benjamin

Published 2017

Thumbnail for Project Discover: An application of generative design for architectural space planning
📄 Paper🌐 Project
This paper describes a flexible workflow for generative design applied to architectural space planning. We describe this workflow through an application for the design of a new office space. First, we describe a computational design model that can create a variety of office layouts including locating all necessary programs and people using a small set of input parameters. We then describe six unique objectives that evaluate each layout based on architectural performance as well as worker-specific preferences. Finally, we show the use of a multi-objective genetic algorithm (MOGA) to search through the high-dimensional space of all possible designs, and describe several visualization tools that can help a designer to navigate through this design space and choose good designs. We conclude by discussing the future of such computational workflows in design and architecture. Our hope is that they go beyond basic automation to create an expanded role for the human designer and a more dynamic and collaborative interaction between computer design software and human designers in the future.

Abstract

This paper describes a flexible workflow for generative design applied to architectural space planning. We describe this workflow through an application for the design of a new office space. First, we describe a computational design model that can create a variety of office layouts including locating all necessary programs and people using a small set of input parameters. We then describe six unique objectives that evaluate each layout based on architectural performance as well as worker-specific preferences. Finally, we show the use of a multi-objective genetic algorithm (MOGA) to search through the high-dimensional space of all possible designs, and describe several visualization tools that can help a designer to navigate through this design space and choose good designs. We conclude by discussing the future of such computational workflows in design and architecture. Our hope is that they go beyond basic automation to create an expanded role for the human designer and a more dynamic and collaborative interaction between computer design software and human designers in the future.

Topics

Form FindingGenerative Design and Design Space ExplorationParametric, Computational and Algorithmic Designconditional generationdesign automationdesign space optimizationgeometry generationmulti-objective optimization

Cite this paper

@inproceedings{8c0c5464,
address={Toronto, Canada}, title={Project Discover: An Application of Generative Design for Architectural Space Planning}, ISBN={9781510870185}, url={https://dl.acm.org/citation.cfm?id=3289794}, DOI={10.22360/SimAUD.2017.SimAUD.007}, booktitle={Proceedings of the 2017 Symposium on Simulation for Architecture and Urban Design (SimAUD 2017)}, publisher={Society for Modeling and Simulation International (SCS)}, author={Danil , Nagy and Damon , Lau and John , Locke and  Jim , Stoddart and Lorenzo,  Villaggi and Ray , Wang and Dale , Zhao and David , Benjamin}, year={2017}, pages = {} }