Development and application of computational tools, processes and theories for automation, optimisation and machine learning in architectural design.
Computational methods and tools have increasingly been used by architects at every stage of the design process - from concept development to construction documentation – and are therefore informing, and gradually reshaping, the design process and the role of the designer.
Despite the overarching interest in the application of computational design tools, and the great deal of experimentation with recently developed techniques, especially pertaining Artificial Intelligence, there has been little effort to systematically explore the implications - in terms of design process and design thinking - of using such tools to address real-world design problems.
In this scenario, this research project aims to critically investigate the potential of state-of-the-art computational tools and techniques to expand on consolidated problem-solving approaches, such as automation and optimisation, and inform the early stages of the design process, including idea generation and problem-framing, via new forms of human-machine interaction enhanced by techniques based on Artificial Intelligence.
The project has a dual purpose: on the one hand, rediscovering and reinterpreting projects of the past to investigate how numerical tools can highlight the qualities and expand on the ambitions of the original design method and vision; on the other hand, developing new tools and processes for automation, optimisation and machine learning in design to finalise a range of exemplary applications in the fields of shell and spatial structures, in particular structural morphology and acoustic design.
The project is also linked to a number of teaching and learning activities of the Master of Architecture, such as the elective subject “Advanced Computational Design” and the Design Studio CDE: “How Virtual Becomes Real”.
Outputs:
Mirra, G. & Pugnale, A. (2021). Comparison between human-defined and AI-generated design spaces in the optimisation of shell structures [Manuscript submitted for publication].
Mirra, G. & Pugnale, A. (2021). Exploring a design space of shell and spatial structures generated by AI from historical precedents [Manuscript submitted for publication].
Pugnale, A. (2018). Integrating Form, Structure and Acoustics: A Computational Reinterpretation of Frei Otto’s Design Method and Vision. Journal of the International Association for Shell and Spatial Structures (Vol. 59, No. 1), pp. 75-86. DOI: 10.20898/j.iass.2018.195.901
Liuti, A., & Pugnale, A. (2014). Computational Morphogenesis applied to the Church of Longuelo: Reflections upon a possible parametric interpretation of the original design concepts, Conference: Across: Architectural Research through to Practice: 48th International Conference of the Architectural Science Association 2014, pp. 405-416, DOI: 10.13140/RG.2.2.28183.78243
Pugnale, A., Méndez Echenagucia, T., & Sassone, M. (2014). Computational Morphogenesis - Design of a free-form concrete shell. In S. Adriaenssens, P. Block, D. Veenendaal, & C. Williams (Eds.), Shells Structures for Architecture - Form finding and optimization (pp. 224-236). Routledge.
Project Contact:
Dr Alberto Pugnale (CI), Senior Lecturer in Architectural Design (www.albertopugnale.com)
Gabriele Mirra, PhD student (www.gabrielemirra.com)
Project Partners:
Dr Alessandro Liuti, ARUP Melbourne