Publication | Sustainable Cities and Society 2023
Generative design for COVID-19 and future pathogens using stochastic multi-agent simulation
Abstract
Generative design for COVID-19 and future pathogens using stochastic multi-agent simulation
Bokyung Lee, Damon Lau, Jeremy P.M. Mogk, Michael Lee, Jacobo Bibliowicz, Rhys Goldstein, Alexander Tessier
Sustainable Cities and Society 2023
We propose a generative design workflow that integrates a stochastic multi-agent simulation with the intent of helping building designers reduce the risk posed by COVID-19 and future pathogens. Our custom simulation randomly generates activities and movements of individual occupants, tracking the amount of virus transmitted through air and surfaces from contagious to susceptible agents. The stochastic nature of the simulation requires that many repetitions be performed to achieve statistically reliable results. Accordingly, a series of initial experiments identified parameter values that balanced the trade-off between computational cost and accuracy. Applying generative design to a case study based on an existing office space reduced the predicted transmission by around 10% to 20% compared with a baseline set of layouts. Additionally, a qualitative examination of the generated layouts revealed design patterns that may reduce transmission. Stochastic multi-agent simulation is a computationally expensive yet plausible way to generate safer building designs.
“How can generative design help building designers reduce the risk posed by COVID-19 and future pathogens? We created a custom multi-agent simulation that tracks the amount of virus transmitted via air and surfaces among occupants of an office. The simulation was used to generate office layouts that minimize the intake of virus particles.”
Related Resources
2023
DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable PhysicsInteractive programming system ensures users can refine generated code…
2022
UNIST: Unpaired Neural Implicit Shape Translation NetworkWe introduce UNIST, the first deep neural implicit modelfor…
2022
Assemble Them All: Physics-Based Planning for Generalizable Assembly by DisassemblyThis work proposes a novel method to efficiently plan physically…
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