SEMIRAMIS
AI-augmented Architectural Design
Abstract
In this research project we aim to develop a toolkit for ML-based architectural design. Traditionally, architectural design involves combining and optimizing many criteria and constraints. For performance-driven design, architects and engineers create parametric design models to generate, simulate and evaluate many design instances, to gather performance feedback on design alterations. However, this is typically a hierarchical process, unable to deal with multiple concurrent objectives and only investigating a narrow spectrum of the design space. Here, instead of tuning input parameters until the result meets certain performance criteria, we envision that machine learned models of the design problem will allow us to find and explore design instances in the proximity of the specified performance goals.
We will develop and validate our AI-Augmented Architectural Design (AAAD) toolkit with a generic approach through case studies that are based on two different design categories. The first category concerns 2.5D surfaces, which are evaluated based on their fabricability (for 3D contour printing), as well as on environmental performance such as acoustics or sunlight protection, targeting architectural applications such as acoustic panels and façade panels. The second category are discrete element assemblies, which comprises load-bearing structures made of columns and beams. This category is evaluated based on structural or environmental performance goals.
The ultimate goal of this project is to augment the designer’s creative and analytical capabilities in the decision-making process by creating interactive design environments and thus revolutionize computational design methods in architecture.
People
Collaborators
Luis is originally from Spain, where he completed his bachelor's studies in Electrical engineering, and the Ms.C. on signal theory and communications, both at the University of Seville. During his Ph.D. he started focusing on machine learning methods, more specifically message passing techniques for channel coding, and Bayesian methods for channel equalization. He carried it out between the University of Seville and the University Carlos III in Madrid, also spending some time at the EPFL, Switzerland, and Bell Labs, USA, where he worked on advanced techniques for optical channel coding. When he completed his Ph.D. in 2013, he moved to the Luxembourg Center on Systems Biomedicine, where he switched his interest to neuroscience, neuroimaging, life sciences, etc., and the application of machine learning techniques to these fields. During his 4 and a half years there as a Postdoc, he worked on many different problems as a data scientist, encompassing topics such as microscopy image analysis, neuroimaging, single-cell gene expression analysis, etc. He joined the SDSC in April 2018. As Lead Data Scientist, Luis coordinates projects in various domains. Several projects focus on the application of natural language processing and knowledge graphs to the study of different phenomena in social and political sciences. In the domains of architecture and engineering, Luis is responsible for projects centered on the application of novel generative methods to parametric modeling. Finally, Luis also coordinates different projects in robotics, ranging from collaborative robotic construction to deformable object manipulation.
Before joining the SDSC as a Data Scientist in April 2023, Alessandro obtained his master’s degree in Computer Science with a focus on Machine Learning from ETH Zurich. In his master’s thesis, he worked on a joint project by the SDSC and the SLF Davos in which he automated the process of avalanche danger forecasting in the Swiss Alps using state-of-the-art machine learning techniques. In his free time, Alessandro loves alpine sports like ski-touring, climbing, and mountaineering.
Fernando Perez-Cruz received a PhD. in Electrical Engineering from the Technical University of Madrid. He is Titular Professor in the Computer Science Department at ETH Zurich and Head of Machine Learning Research and AI at Spiden. He has been a member of the technical staff at Bell Labs and a Machine Learning Research Scientist at Amazon. Fernando has been a visiting professor at Princeton University under a Marie Curie Fellowship and an associate professor at University Carlos III in Madrid. He held positions at the Gatsby Unit (London), Max Planck Institute for Biological Cybernetics (Tuebingen), and BioWulf Technologies (New York). Fernando Perez-Cruz has served as Chief Data Scientist at the SDSC from 2018 to 2023, and Deputy Executive Director of the SDSC from 2022 to 2023
PI | Partners:
ETH Zurich, Gramazio Kohler Research:
- Prof. Matthias Kohler
- Prof. Dr. Arno Schlüter
- Dr. Aleksandra Anna Apolinarska
- Dr. Romana Rust
description
Motivation
Design in Architecture, Engineering and Construction (AEC) can be described as an ill-defined (“wicked”) problem with many parameters, multiple constraints and contradicting objectives. Traditionally, only a very small number of possible solutions is considered, created based on human best-guess or they are limited to blanket solutions. Parametric design tools such as Grasshopper allowed the automated generation of large numbers of potential solutions, and the integration of performance measures. Still, parametric modelling only allows to carry out forward design, which still restrict the exploration capabilities of the designer, and a broader exploration of the solution space (Figure 1, “classic parametric modelling“).
Proposed Approach / Solution
We have implemented a methodology for inverse design that leverages the parametric model. By using design instances generated using the parametric model, we can train a ML model to carry out two tasks. First, accelerate forward modelling by learning a surrogate model of the mapping from designs' parameters to performance measures. Second, perform inverse design, i.e. given a set of desired performance measures, the trained model will suggest designs satisfying those (Figure 1, “ML-based design“). Specifically, we have leveraged autoencoders, as in this architecture we can use the trained encoder as surrogate model, and the decoder as generator.
Impact
This methodology unleashes novel design possibilities by augmenting the designers with insights in solutions they would possibly not have imagined, excluding their unconscious bias, and allow to combine human synthetic thinking with the analytic power of computation. We have already utilized this methodology in several use-cases such as “Semiramis“ (see Figure 2), a vertical garden structure already built in Zug, Switzerland. In this particular case, the implemented methods helped the designer during the early exploration of feasible design.
Presentation
Gallery
a) the outline shapes of the planting platforms are generated from the design parameters (radii and constellations).
b) the design is subsequently assessed w.r.t. total area of the platforms, sun and rain occlusions.
c) the final design visualized in context and scale.
Annexe
Publications
- Salamanca, L., Apolinarska, A. A., Pérez-Cruz, F., & Kohler, M. (2022, September). Augmented intelligence for architectural design with conditional autoencoders: semiramis case study. In Design Modelling Symposium Berlin (pp. 108-121). Cham: Springer International Publishing. Augmented Intelligence for Architectural Design with Conditional Autoe
- Apolinarska, A. A., Casas, G., Salamanca, L., & Kohler, M. (September 2024). Grasshopper plugin for AI-augmented inverse design. Accepted for Design Modelling Symposium Kassel 2024
Additional resources
Bibliography
- Nauata, N., Chang, K. H., Cheng, C. Y., Mori, G., & Furukawa, Y. (2020). House-gan: Relational generative adversarial networks for graph-constrained house layout generation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16 (pp. 162-177). Springer International Publishing. House-GAN: Relational Generative Adversarial Networks for Graph-Constr
- Oh, S., Jung, Y., Kim, S., Lee, I., & Kang, N. (2019). Deep generative design: Integration of topology optimization and generative models. Journal of Mechanical Design, 141(11), 111405. https://doi.org/10.1115/1.4044229
- Brown, N. C., & Mueller, C. T. (2019). Design variable analysis and generation for performance-based parametric modeling in architecture. International Journal of Architectural Computing, 17(1), 36-52. https://doi.org/10.1177/147807711879949
- Sohn, K., Lee, H., & Yan, X. (2015). Learning structured output representation using deep conditional generative models. Advances in neural information processing systems, 28. Learning Structured Output Representation using Deep Conditional Generative Models
Publications
Related Pages
Some articles in the press:
- Weltneuheit an der ETH Zürich – Gärten aus Roboterhand
- ETH Zurich is building a 22.5-meter-tall, sculptural hanging garden with the help of robots
- Robots build new Hanging Gardens: ETH Zürich – e-architect
Official video of the press release:
ETH Zürich press release:
AIXD toolbox
More projects
ML-L3DNDT
BioDetect
IRMA
FLBI
News
Latest news
Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
The Promise of AI in Pharmaceutical Manufacturing
The Promise of AI in Pharmaceutical Manufacturing
Efficient and scalable graph generation through iterative local expansion
Efficient and scalable graph generation through iterative local expansion
Contact us
Let’s talk Data Science
Do you need our services or expertise?
Contact us for your next Data Science project!