Publication | Journal of Building Performance Simulation 2017
Simulating Use Scenarios in Hospitals using Multi-Agent Narratives
Abstract
Simulating Use Scenarios in Hospitals using Multi-Agent Narratives
Davide Schaumann, Simon Breslav, Rhys Goldstein, Azam Khan, Yehuda E. Kalay
Journal of Building Performance Simulation 2017
Anticipating building-related complexities ensuing from occupants’ behaviour is a major challenge in architectural design. Conventional building performance simulation tools model occupancy in a highly aggregated form, abstracting away the impact of dynamic spatial and social factors on occupant behaviour. To address this issue, we propose a multi-agent system that accounts for these aspects in process-driven facilities, such as hospitals. The approach involves modelling ‘narratives’, rule-based scripts that direct occupants’ movement and shared activities. A scheduling mechanism employs Operations Research techniques to dynamically coordinate the narratives’ execution. We demonstrate the method by simulating day-to-day operations in a typical hospital setting, involving scheduled procedures and unscheduled adaptations due to dynamic social and environmental conditions. The process involved collecting data using field observations and interviews with experts, modelling narratives, and simulating them to produce use scenarios that can be visualized and analysed by designstakeholders.LINK
Associated Autodesk Researchers
Related Resources
2023
Multi-split configuration design for fluid-based thermal management systems
This work introduces a framework for automated exploration of optimal…
2023
BOP-Elites: A Bayesian Optimisation Approach to Quality Diversity Search with Black-Box descriptor functions
An algorithm that efficiently tackles expensive black-box optimization…
2019
An Empirical Study of how Socio-Spatial Formations are influenced by Interior Elements and Displays in an Office Context
The design of a workplace can have a profound impact on the…
2018
A Symmetric Formalism for Discrete Event Simulation with Agents
In designing a general modeling formalism for domain experts, a key…
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