Publication | ACM Designing Interactive Systems (DIS) 2021
COVID-19 Facility Planning and Analysis
Designing a Multi-Agent Occupant Simulation System
The COVID-19 pandemic has made virus transmission a significant factor in designing buildings to ensure people’s safety. This paper proposed a system to help designers and facilities managers visualize the relationship between a built environment, human behavior, and risk of infection during the early stage of design.
Download publicationAbstract
Designing a Multi-Agent Occupant Simulation System to Support Facility Planning and Analysis for COVID-19
Bokyung Lee, Michael Lee, Jeremy Mogk, Rhys Goldstein, Jacky Bibliowicz, Frederik Brudy, Alexander Tessier
ACM Designing Interactive Systems (DIS) 2021 (Honorable Mention Award)
The COVID-19 pandemic changed our lives, forcing us to reconsider our built environment, architectural designs, and even behaviours. Multiple stakeholders, including designers, building facility managers, and policy makers, are making decisions to reduce SARS-CoV-2 virus transmission and make our environment safer; however, systems to effectively and interactively evaluate virus transmission in physical spaces are lacking. To help fill this gap, we propose OccSim, a system that automatically generates occupancy behaviours in a 3D model of a building and helps users analyze the potential effect of virus transmission from a large-scale and longitudinal perspective. Our participatory evaluation with four groups of stakeholders revealed that OccSim could enhance their decision making processes by identifying specific risks of virus transmission in advance, and illuminating how each risk relates to complex human-building interactions. We reflect on our design and discuss OccSim’s potential implications in the domains of design evaluation, generative design, and digital twins.
Related Resources
See what’s new.
2024
Reduced-order modeling of unsteady fluid flow using neural network ensemblesA framework to enhance the accuracy of time-series predictions in…
2024
A hyperreduced reduced basis element method for reduced-order modeling of component-based nonlinear systemsThis method balances accuracy and computational speed through adaptive…
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