Jonathan Dortheimer: Towards the Architecture Machine – Challenges and opportunities for integrating artificial intelligence in architectural design
architectural design is highly dependent on interaction and collaboration with project owners, stakeholders, and professionals. In my previous research, I developed an architectural-design crowdsourcing design process, framework, and software. The research demonstrated that architectural design could be collaboratively generated using an algorithmic process based on professional architects and non-specialists (Dortheimer et al., 2020).
Together with AI methods, the algorithmic design process has the potential of improving and automating architectural design. In this context, generative Machine Learning methods like Generative Adversarial Networks (GAN) demonstrated the ability to produce a new kind of machine creativity (Leach, 2020). This ability raises new questions about the place of the human in an AI-based design process (Picon, 2020). In this context, the presented ongoing project seeks to discover new knowledge in human-computer interaction by exploring and developing the interface between humans and AI in architectural design processes.
Dortheimer, Jonathan, Eran Neuman, and Tova Milo. 2020. “A Novel Crowdsourcing-Based Approach for Collaborative Architectural Design.” In Anthropologic: Architecture and Fabrication in the Cognitive Age – Proceedings of the 38th ECAADe Conference, 2:155–64. Berlin, Germany,. http://papers.cumincad.org/data/works/att/ecaade2020_037.pdf.
Leach, Neil. 2020. “Do Robots Dream of Digital Buildings?” In Architectural Intelligence, 59–73. Springer Singapore. https://doi.org/10.1007/978-981-15-6568-7.
Picon, Antoine. 2020. “What About Humans? Artificial Intelligence in Architecture.” In Architectural Intelligence, 15–29. Springer Singapore. https://doi.org/10.1007/978-981-15-6568-7.