This research is a manifestation of architectural co-creation between agent simulation based machine learning and an architect’s tacit knowledge. Instead of applying machine learning brains to agents, the author reversed the idea and applied machine learning to buildings. The project used agent simulation as a database, and trained the space to reconfigure itself based on its distance to the nearest agents. To overcome the limitations of machine learning model’s simplified solutions to complicated architectural environments, the author introduced a co-creation method, where an architect uses tacit knowledge to overwatch and have real-time control over the space reconfiguration process. This research combines both the strength of machine learning’s data-processing ability and an architect’s tacit knowledge. Through exploration of emerging technologies such as machine learning and agent simulation, the author highlights limitations in design automation. By combining an architect’s tacit knowledge with a new generation design method of agent simulation based machine learning, the author hopes to explore a new way for architects to co-create with machines.
Co-creation: Space Reconfiguration by Architect and Agent Simulation Based Machine Learning
Computational Design and Robotic Fabrication
The International Conference on Computational Design and Robotic Fabrication ; 2022 June 27, 2022 - July 05, 2022
2023-04-04
10 pages
Article/Chapter (Book)
Electronic Resource
English
British Library Conference Proceedings | 1997
|GALINA BALASHOVA: THE FIRST SPACE ARCHITECT
TIBKAT | 2022
|GALINA BALASHOVA: THE FIRST SPACE ARCHITECT
TIBKAT | 2020
|National Security Space Architect (NSSA) Space Weather Architecture Study
British Library Conference Proceedings | 1999
|