The past two years of pandemic has significantly influenced our perception of life preference and working patterns. The prevalence of calling for flexible work method such work from home and better work-life balances is just a reflection of the change of tide in how people perceive the working and living style of the future.
This workshop discuss how this shift of subjective perception and human preference and its impact on urban space can be quantitively measured via diving into the depth of ‘big data’. Acknowledging the progress in open-source datasets that quantify the dynamic urban activities, such as Google street view, GIS, Airbnb .etc, instead of the common empirical method in urban analysis, our investigations and research about the grain and fabric of the city start with an effective approach to quantify subjective perception of preference in life style and streetscape with computer vision and machine learning.

During this workshop, we will examine the spatial formation, landscape elements composition, and landscape perception through data mining and data visualization of urban image data. The goal is to challenge the conventional perceptual study in the landscape and urban design process and inspire opportunities for novel quantitative analysis with an evidence-based approach to the design process to capture the shift in the public perception.

Workshop ID:
3

UN SDGs:
SDG3, SDG8, SDG11, SDG15

Format:
Online

Participant Pre-requisites:
Coding experience preffered but not necessary

Duration:
3 Days

Dates:
9/10/11 of April

Timezone:
10:00am to 6:00pm SYDNEY Time

Workshop Leaders:
Dan Luo, Lecturer, School of Architecture, University of Queensland
Waishan Qiu, Ph.D. in Regional Science, AAP, Cornell University
M.C.P. in City Design and Development, Department of Urban Studies and Planning, Massachusetts Institute of Technology
Wenjing Li, PhD Candidate, The University of Tokyo
Bachelor of Landscape architecture, Harbin Institute of Technology (HIT)

The workshop explores the agency of neural networks in the study of material stages within the context of life-cycle assessment in the circular economy. It primarily focuses on the use of GAN (generative adversarial networks), in Runway ML and Google Colab, to identify new cradle-to-cradle opportunities within latent walks from material life-cycle image datasets gathered from conventional linear economy industries’ take-make-waste processes. This workshop engages in the instrumentality of AI in recycling and closing life-cycle loops, not only in terms of proper post-Carbon waste management but also in potential manufacturing approaches. Generatively, the workshop seeks to prompt the use of 3D GAN techniques into animation and simulation industry-standard software – Cinema 4D –, through the translation of 2D GAN outputs as three-dimensionalized dynamic models to extract actual volumetric features of newly informed material stages, providing further opportunities for digital physicalization. Visualization-wise, the workshop covers methodologies to construct subtly animated novel ecologies with Cinema 4D and Quixel Bridge, as a platform for a participatory generative design that combines human-curated and crafted photo-realistic assets and datasets with AI volumetric processing of architectural artifacts. The resulting outputs are expected to lie within AI indeterminacy and human control while challenging and augmenting the designer’s agency.

Workshop ID:
4

UN SDGs:
SDG12

Format:
Online

Participant Pre-requisites:
Coding experience preffered but not necessary

Duration:
2 Days

Dates:
9/10 of April

Timezone:
10:00am to 6:00pm SYDNEY Time

Workshop Leaders:
Carlos Navarro, M. DesR SCI-Arc, 2015
Jiaoyue Zhao, M. Arch II SCI-Arc, 2020
https://mland.space/

In a “post carbon” reality, we no longer have the luxury to design and construct structures of the same calibre that we do today. The scarcity of building materials means that we need to look into new methods of adapting existing structures to suit changing needs as well as reusing building elements.

This workshop sets out to investigate how timber members from existing/demolished buildings as well as offcuts from industry could be repurposed to create new structures. It will encompass various stages from 3d scanning and documenting elements for reuse, through to the design and evaluation of in a parametric environment. Structures will be designed using aggregation techniques paired with structural optimisation to create new forms. Coupled within a mixed reality environment, it would be possible to manually manipulate and inform the design process that is driven by automated computational procedures.

The outcome of the workshop will be a series of digital workflows and design procedures that showcase the potential of using reclaimed timber for structures. We will develop and exhibit VR/AR environments and structures analyses tools as a proof of concept.

Workshop ID:
6

UN SDGs:
SDG11, SDG12, SDG13

Format:
In-Person or Online (Hybrid Mode)

Participant Pre-requisites:
Basic knowledge of Rhino and Grasshopper

Duration:
3 Days

Dates:
9/10/11 of April

Timezone:
10:00am to 6:00pm SYDNEY Time

Workshop Leaders:
Sascha Bohnenberger, Bollinger+Grohmann, Swinburne University of Technology
Ven Natarajan, Imersian
Matthew Tam, Bollinger+Grohmann, Karamba3D

The workshop will introduce an innovative structural-based form-finding method for architectural design with more freedom and creativity. Various methodologies have been developed to achieve the most optimized results in the structural field, which aim for light structures. Topology optimization creates the possibility of the strategy, which seeks to find the solution with the highest structural performance under certain material limitations by removing or adding materials elements step by step. The cutting-edge method founded and developed by Mike Xie and his team, Bi-directional Evolutionary Structural Optimisation (BESO), has been used and approved through lots of architecture projects and architecture design studios/workshops. Thus, this kind of new approach to generative architectural design will be introduced to this CAADRIA 2022 workshop. Students will be trained to develop their skills in architectural design through the application of topological optimization (BESO) software Ameba. The concept of topological optimization and the inspiration of natural morphological evolution will be run through architectural form-finding. Students will be required to complete a series of architecture/architectural components design and optimization individually or in pairs online.

Workshop ID:
7

UN SDGs:
SDG9, SDG13

Format:
In-Person or Online (Hybrid Mode)

Participant Pre-requisites:
Knowledge of Rhino and Grasshopper

Duration:
2 Days

Dates:
9/10 of April

Timezone:
10:00am to 6:00pm SYDNEY Time

Workshop Leaders:
Nic Bao, RMIT University
Xin Yan, Tsinghua University
Yuan Yao, Ameba Institute of Engineering Structure Optimisation

This workshop explores the intersection of game and AI as a novel way to approach architectural participatory generative design. The recent rapid advancement of machine learning and AI in architectural industries is operating with limitation to allow a wider audience. Allowing a wider spectrum of evaluation will be vital in the design process for a more sustainable built environment. Inspired by machine learning (ML) application in Unity3D as game design elements, there are potentials to promote the active participation of architects, artists and even the public in the design generation processes by gamification. In this workshop, we will explore novel generative design methodology driven by Reinforcement Learning combined with player active interaction, focusing on the actor-aware generation of logics, environmental factors and complex human behaviour. How can a machine think creatively according to non-linear human behaviour and complex environmental effects? What may be the possible form generated from the active collaboration between AI and different agents? These questions approach the goals of AI that help designers through the novel augmentation of machine vision and automation. In the workshop, participants will work with a given set of reinforcement-learning-based frameworks and package in Unity3D to explore design ideas and potentials of human-machine interaction for a more sustainable community design strategy. 

Workshop ID:
8

UN SDGs:
SDG17

Format:
Online

Participant Pre-requisites:
Basic C#/Python, Basic 3D modelling skills

Duration:
3 Days

Dates:
9/10/11 of April

Timezone:
10:00am to 6:00pm SYDNEY Time

Workshop Leaders:
Chien-hua Huang, China Academy of Art
Hao Wu, University of Applied Arts Vienna

As a result of climate change, the average global temperature is on the rise, leading us to question how we need to design and build housing and shelter for extreme heat. Research into vernacular architecture in hot arid climates offers design and material strategies to deal with extreme heat. Opportunities include building with earth materials and the use of cooling towers such as those used in Iran’s traditional architecture. Similar passive design strategies of building in earth materials, while cooling via venturi effect can be seen in nature in the clay nests of termites.  3D printing this workshop aims to combine knowledge of vernacular architecture in arid climates, with biomimicry principles and 3D printing processes to design and develop housing to meet the challenges of climate change. This workshop takes the first step to establish preliminary 3D printing experiments for wall structures to gain building approvals by Australian building authorities required for potenital housing projects for the Narara Ecovillage. 

Workshop ID:
10

UN SDGs:
SDG9, SDG11

Format:
In-Person

Participant Pre-requisites:
Knowledge of Rhino and Grasshopper

Duration:
3 Days

Dates:
9/10/11 of April

Timezone:
10:00am to 6:00pm SYDNEY Time

Workshop Leaders:
Alex Tohidi, UNSW  
Dr Mohammed Gomaa, RMIT
Richard Blackwell, UNSW
Kate Dunn, UNSW

Workshop Sponsored By:

Narara Ecovillage


Mudtec

The workshop demonstrates the potential of AI in helping designers identify architectural solutions and place them within the most relevant architectural canons. In this workshop, we will present a novel workflow that uses graph-based machine learning to automatically classify buildings based on their 3D topological graph rather than their 2D visual depiction. The system takes advantage of two main technologies: The first is Topologic which is a library that enhances the representation of 3D models through non-manifold topology and embedded semantic information. The second is DGCNN which is an end-to-end deep graph neural network that can be directly applied to graphs with arbitrary topology without the requirement to perform manual feature engineering. The workflow in this workshop will consist of two stages: In the first sage, we will introduce the participants to a generative simulation system which creates a large synthetic dataset with several topological variations. These geometrical models will then be converted into semantically rich topological dual graphs. In the second stage, the graphs will be imported to the DGCNN model for graph classification. We will discuss with the participants the principles of graph machine learning on topological models and the optimisation of hyperparameters needed to achieve high performance.

Workshop ID:
11

UN SDGs:
SDG9, SDG11, SDG12

Format:
Online

Participant Pre-requisites:
Basic Knowledge of Rhino and Grasshopper

Duration:
2 Days

Dates:
9/10 of April

Timezone:
10:00am to 6:00pm PARIS Time

Workshop Leaders:
Professor Wassim jabi, Chair of Computational Methods in Architecture, Welsh School of Architecture, Cardiff University
Twitter: @wassimj
Arch. Abdulrahman Alymani, PhD Candidate at Welsh School of Architecture, Cardiff University
Twitter: @dodescape1

This workshop will introduce a new method – Deeplsomer – that uses autoregressive deep neural network to implicitly generate isomers (variants) of 3D forms. The goal is to understand and employ Al driven automated design iteration with hands-on demonstration and exercise. Participants will be introduced to the methodology of Deeplsomer to learn the spatial features of 3D digital models to generate new variants that reflect the original learnt spatial features to varying degrees. The computational workflow has three key components – (i) image representation of 3D digital model(s), (ii) auto-regression of the image(s) using neural network to generate variants, and (iii) decoding the output variant image(s) into 3D digital model(s).

With any given training data (discrete digital model), Deeplsomer is capable of generating new data (variant discrete digital model) from and of the same distribution. Its capability of producing legible output with limited data set sets it apart from data-hungry GANs. Deeplsomer establishes a new paradigm of automated 3D form iteration that steers away from the currently prevalent method of explicitly scripting the (parametric) geometric rules.

Workshop ID:
12

UN SDGs:
SDG9

Format:
Online

Participant Pre-requisites:
Knowledge of Rhino and Grasshopper

Duration:
1 Day

Dates:
9 of April

Timezone:
10:00am to 6:00pm PARIS Time

Workshop Leaders:
Joy Mondal, Design Head, Wesearch Lab, Visiting Faculty, SPA (Delhi)

Do you wonder how merging traditional craft with advanced digital fabrication processes can lead to more sustainable building techniques? Are you interested in how computational design tools can enhance cooperation and knowledge exchanges between architects and engineers? Are you curious about robotic assembly, CNC fabrication, parametric modeling, or CAD-to-CAE workflows? Then don’t miss this unique opportunity to join our one-day online workshop at CAADRIA 2022! In the first part of this workshop, the manipulation of both standard and bespoke timber plate structures will be introduced. This includes the presentation of various case studies and design parameters, i.e. joints types, assembly sequences and connection compatibilities. Then, integrated digital fabrication processes, i.e. CNC machining constraints and robotic assembly considerations will be presented. For the engineering design and simulation part, COMPAS_FEA, an extension of the COMPAS framework, will be employed. COMPAS is a state-of-the-art computational platform that enables a trans-disciplinary collaboration between architects, engineers, and contractors. Engineering design requirements, i.e. elements required to define a valid structural model for plate structures will notably be explained. Finally, participants will have the chance to apply what they have learned by designing their own timber plate structure using the provided framework. 

Workshop ID:
13

UN SDGs:
SDG9, SDG11, SDG12

Format:
Online

Participant Pre-requisites:
Basic Knowledge of Rhino and Grasshopper

Duration:
1 Day

Dates:
9 of April

Timezone:
10:00am to 6:00pm PARIS Time

Workshop Leaders:
Nicolas Rogeau, Ecole Polytechnique Fédérale de Lausanne
Dr. Aryan Rezaei Rad, Ecole Polytechnique Fédérale de Lausanne

The workshop will explore engaging with Genetic Algorithms (GAs) as an exploratory and an optimisation process using Snowflake – a newly developed interactive plugin, and apply the developed method to design high-rise morphologies in an urban context in Sydney CBD. It aims to create a dialogue between human creativity and intuition and the genetic algorithms quantitative process to enable a varied and richer space of viable design solutions.

The workshop will introduce participants to the working principles of engaging with GAs to solve multi-objective optimisation problems first, then moving into a more advanced level of interacting with the algorithm to influence the evolution to reflect participants’ intuition or preference. Participants will first learn how to formulate the design problem for an optimisation or exploration process. Later, they will learn how to engage with the different levels of interactions facilitated by the new plugin. The new interactive process will then be applied in design experiments of high-rise morphologies on an urban site. The outcome of these experiments will be a population of solutions combing the architect’s subjectivity and intuition with the genetic algorithms quantitative performance-based objectives.

Workshop ID:
14

UN SDGs:
SDG9, SDG11

Format:
Online

Participant Pre-requisites:
Intermediate Knowledge of Rhino and Grasshopper

Duration:
3 Days

Dates:
9/10/11 of April

Timezone:
10:00am to 6:00pm PARIS Time

Workshop Leaders:
Zayad Motlib, Associate Professor, XJTLU. Founder, Amorphoustudio
Heba Eiz, Computational Designer, MSc Bartlett School of Architecture

This workshop will investigate the relationship between architecture and distributed ledger technologies(DLTs), within the broader context of architecture and urban processes.
 
We will explore frameworks for decentralised design problem solving as well as decentralised production systems in the context of the fourth industrial revolution. We will look closer into Blockchain infrastructure as a means for creating new operational models for architectural design, through project governance, scaling collaboration, and shifting trust to the infrastructure rather than the actors involved.
 
Blockchain and DLTs are seen as alternative systems of trust, which provide the technological backbone needed to combine aspects of the Circular Economy, Internet of Things (IoT), Smart Cities, and Building Information Modelling (BIM) by adding an infrastructural layer for tamper-proof exchange of value and information.
 
We will explore ways in which blockchain and DLTs in general may impact the ways we produce, reproduce, and think about architectural design across different scales, around five main thematic areas: Modularity/Stigmergic Assembly, Metaverse, Cryptoeconomics in Construction, Collaborative Design/Fabrication, Digital-Twins/Mapping. The participants however are encouraged to explore the nexus between architecture and peer-to peer economies that blockchains can forge.
 
Our main objectives are to introduce participants to decentralised computational methodologies as infrastructure for architectural design, explore the relevance of Cryptoeconomics for architectural & computational designers and train more computational designers into writing smart contracts. Basic tuition into writing smart contracts in solidity will be provided.

Workshop ID:
15

UN SDGs:
SDG4, SDG7, SDG8, SDG9, SDG11, SDG12

Format:
Online

Participant Pre-requisites:
None

Duration:
2 Days

Dates:
9/10 of April

Timezone:
10:00am to 6:00pm PARIS Time

Workshop Leaders:
Dr Theo Dounas, RGU Aberdeen 
Yorgos Berdos, University of Edinburgh, University of Dundee

The workshop will look at the “ecological footprint” of cities from a spatial perspective, analyzing the impact that cities have on the surrounding territory and beyond.

Breaking down the ecological footprint method into components through which the ecological footprint of a city is measured, the participants will be asked to explore these aspects separately, and then bring them together to create their own ecological index and visualize it, according to their analysis. Participants will be given a different city to explore, and are expected to base their analysis on local conditions, resulting in different ecological footprint indexes for each of the cities analyzed, following different environmental narratives.

The workshop will introduce students to geospatial data mining through Google Earth Engine in Grasshopper 3D.  It aims at providing students with a pipeline, in CPython, to dynamically access and manipulate petabytes of online georeferenced data and visualize them. This offers designers an extraordinary opportunity to work with environmental phenomena, using design tools.

Workshop ID:
17

UN SDGs:
SDG11, SDG12, SDG13

Format:
Online

Participant Pre-requisites:
Basic Knowledge of Rhino and Grasshopper

Duration:
1 Day

Dates:
9 of April

Timezone:
10:00am to 6:00pm PARIS Time

Workshop Leaders:
Erzë Dinarama, Interdisciplinary Designer
Iacopo Neri, Computational Designer

In a post Carbon world, we will collaborate internationally on both design and fabrication, without travel by airplane or automobile. KUKA|crc Cloud Remote Control allows users to program robots in international locations from the comfort and safety of their home or office. This allows for a digitalization of fabrication, where robots as a service brings the ability to control giant machines within reach of your Monday morning Zoom meetings.
 
We invite you to join Robots in Architecture Research and the Chair for Individualized Production in this exciting CAADRIA 2022 workshop.
Learn to collaborate with robots from anywhere using KUKA|crc Cloud Remote Control!
 
Participants will collaborate on the design, optimization and fabrication of a steel structure made from rebar. Each international participant will program the robot to pick and place steel elements that will be welded in place by a local fabricator. The location of the elements will be digitally communicated to all international participants allowing you to build on the structure that others have created. In this way, from countries all around the world, we will build an impromptu structure spanning the gap between two tables a meter apart, while at the same time building a bridge between you and robotic fabrication. 

Workshop ID:
18

UN SDGs:
SDG4, SDG9, SDG17

Format:
Online

Participant Pre-requisites:
Intermediate Knowledge of Rhino and Grasshopper

Duration:
3 Days

Dates:
9/10/11 of April

Timezone:
10:00am to 6:00pm PARIS Time

Workshop Leaders:
Ethan Kerber, Researcher
Chair for Individualized Construction Production – RWTH Aachen University
Robots in Architecture Research
Dr.-Ing. Sven Stumm, Senior Researcher Computer Science
Chair for Individualized Construction Production – RWTH Aachen University
Robots in Architecture Research
Dr Techn., University Professor Sigrid Brell-Cokcan
Chair for Individualized Construction Production – RWTH Aachen University
Association for Robots in Architecture