Gramazio Kohler Research
News
Teaching
Research
Projects
Publications
About
Team
Open Positions
Contact
Compas XR
Compas FAB
Impact Printing
Compas Timber
AIXD: AI-eXtended Design
AI-Augmented Architectural Design
AR Timber Assemblies
Architectural Design with Conditional Autoencoders
Integrated 3D Printed Facade
Think Earth SP7
Robotic Plaster Spraying
Additive Manufactured Facade
Human-Machine Collaboration
Timber Assembly with Distributed Architectural Robotics
Eggshell Benches
Eggshell
CantiBox
Autonomous Dry Stone
RIBB3D
Data Driven Acoustic Design
Mesh Mould Prefabrication
Data Science Enabled Acoustic Design
Thin Folded Concrete Structures
FrameForm
Adaptive Detailing
Deep Timber
Robotic Fabrication Simulation for Spatial Structures
Jammed Architectural Structures
RobotSculptor
Digital Ceramics
On-site Robotic Construction
Mesh Mould Metal
Smart Dynamic Casting and Prefabrication
Spatial Timber Assemblies
Robotic Lightweight Structures
Mesh Mould and In situ Fabricator
Complex Timber Structures
Spatial Wire Cutting
Robotic Integral Attachment
Mobile Robotic Tiling
YOUR Software Environment
Aerial Construction
Smart Dynamic Casting
Topology Optimization
Mesh Mould
Acoustic Bricks
TailorCrete
BrickDesign
Echord
FlexBrick
Additive processes
Room acoustics
AIXD: AI-eXtended Design, 2021-2024
Software development project
AI-eXtended Design is open-source Python toolbox designed to revolutionize parametric design with the power of modern Machine Learning (ML) algorithms. AIXD is your go-to toolkit for design evaluation, generation, exploration, and optimization, seamlessly blending parametric modeling with AI capabilities.

Key Features:

  • Generative Power: AIXD empowers you to easily train generative AI models, such as Conditional Autoencoders. This enables the creation of designs that not only push the boundaries of creativity but also meet the specific performance constraints of your project, advancing design exploration.

  • Surrogate Modeling: Easily create surrogate models for parametric problems using feed-forward neural networks, enhancing efficiency in design evaluation and optimization.

  • Versatility: Initially developed for the Architecture, Engineering, and Construction (AEC) industry, AIXD is applicable to any parametric problem across diverse domains.

  • Project-Specific and Low-Code: Tailor AIXD to your project’s unique needs with its project-specific approach, all while enjoying the benefits of a low-code environment that accelerates your design workflow.


AIXD website including API reference, user guide, tutorials and source code.

Related projects:

AI-Augmented Architectural Design

Architectural Design with Conditional Autoencoders: Semiramis Case Study

Credits:
Gramazio Kohler Research, ETH Zurich
Prof. Matthias Kohler, Dr. Aleksandra Apolinarska, Gonzalo Casas, Dr. Romana Rust

Swiss Data Science Center (SDSC)
Dr. Luis Salamanca, Alessandro Maissen, Rafael Bischof, Dr. Konstantinos Tatsis, Prof. Fernando Perez-Cruz

kfm research, ETH Zurich
Prof. Walter Kaufmann, Dr. Michael Kraus, Sophia Kuhn
Copyright 2024, Gramazio Kohler Research, ETH Zurich, Switzerland
Gramazio Kohler Research
Chair of Architecture and Digital Fabrication
ETH Zürich HIB E 43
Stefano-Franscini Platz 1 / CH-8093 Zurich

+41 44 633 49 06
Follow us on:
Vimeo | Instagram