Worskhop01

AI in+form: Bio-inspired Solar Designs in Architecture

Description:

Biological systems are efficient within Earth’s energy chain not only because of their individual performance, but also their collective emergence. This research argues that architectural design should emphasize options over optimal-solutions, channeling this to diversify solar designs that can be aggregated for diverse building topologies and user demands. Instead of generating one design to be used for every solar problem, this research focuses on AI informed workflows that generate families of designs which are adaptive to each other, performing aggregation that aims at pertaining to Geoffrey West’s ‘quartered law of nonlinear power scaling’, which can be fabricated in similar methods using the same mathematical conception. How to enable variational designs that win over diverse solar vectors in a complex environment through variational aggregation? Through both theoretical and technical means, this paper hopes to prompt discussions around the relationship between nature/human/machine and the future roles of architects as designers.
This research frames design as an iterative decision-making strategy that feedback between input/output of human-machine, which demands a studying of tasks within a design process and how they can be distributed between designers/algorithms that are each better at different tasks. This workshop empowers participants with an understanding of readily available digital design tools: 1) problem identification/mapping (from socio-economic to climatic); 2) translating bio-inspirations into parametric-enabled visual algorithms; 3) the practise of iterative negotiation between designer intuition and algorithmic generation, more specifically, this workshop will study AI as rule-based systems (i.e. CA, GA) and Machine Learning (ML), which helps to automate the translation between voxel-pixel data input/output. Through both theoretical and technical means, this workshop hopes to prompt discussions around the relationship between nature/human/machine and the future roles of architects as designers.


Max Participants:
10
Keywords:

artificial intelligence, form-finding, bio-design, renewables, human-machine interaction

Requirements (Hardware/Software):
  1. The participants require a computer which can run Rhinoceros 3D and Grasshopper.
  2. Basic Knowledge of Grasshopper

Apply here!

Schedule:

  • Timezone: London Time (UTC/GMT+1)

  • Worksession duration: 1:00 PM - 5:00 PM BST (5:00 AM - 9:00 AM PST)

  • Day 1 / July 11th

    1. Introductory presentation
    2. Tutorial of the workflow (Rhino & Google Colab)

  • Day 2 / July 12th

    1. Digital model preparation
    2. Discretization, autoregression and decoding discrete output of digital models


  • Day 3 / July 13th

    1. Charrette
    2. 3D variation production

  • Day 4 / July 14th

    1. Charrette
    2. 3D variation production

  • Day 5 / July 15th

    1. Project documentation
    2. Discussion on outcomes
Tutors:
Alberto Fernandez
Provides Ng
Baha Odaibat
David Doria
Nikoletta Karastathi
Bio:

AI in+form is an architect and researcher collective that focuses on building the relationship between rationalising energy circularity and human-machine interaction. More specifically, AI in-form stands at the convergence of artificial intelligence, information feedback, form-finding, and socio-economic inclusivity. In the search for tools that fall between the established fields of expertise, the collective collaborates with professionals across cultural and disciplinary boundaries, from natural to social sciences. The core members are Alberto Fernandez Architect UCH, PhD candidate at The Bartlett School of Architecture (UCL), Academic at UCH-FAU and RIBA Chartered Architect; Provides Ng teaching at the Bartlett School of Architecture (UCL), where she also received her distinction in MRes Digital Theory and Architecture; Baha Odaibat Architecture studies at GJU science and Trier university of applied science; and David Doria bachelor’s degree in Architecture and Urbanism from the Federal University of Sergipe and MArch from The Bartlett School of Architecture (UCL).


Max Participants:
15
Keywords:

artificial intelligence, form finding, bio-inspired

Requirements (Hardware/Software):
  1. Software: Rhino v 7, Grasshopper Plugin: lady bug, wasp, rabbit (Cellular Automata CA / Genetic Algorithm GA) Virtual communication
  2. Mapping: Zoom, Miro
  3. Not compulsory: Python (Machine Learning ML)
  4. Beginner - intermediate grasshopper / modeling
  5. Basic theoretical understanding on Artificial Intelligence
  6. Interest in energy problems / design communication / multi-stakeholder exchange

Workshop02

Augmented Objects 2.0

Description:

This workshop will be divided into two sessions. First will focus on creation of the object(modelling + animation) and second will be devoted to AR deployment.For the object modelling we will use Zbrush or Cinema4d(depending on interest), where we will go through main modelling/simulation techniques and going though import/export processes.For the AR part, we will go though main setups of SparkAR, and how create materials and animations, and how to deploy experience to a smartphone.


Max Participants:
20
Keywords:

Augmented Reality, Virtual Reality, Mixed Reality, Architecture

Requirements (Hardware/Software):
  1. Unity
  2. Cinema4d/zbrush/or any other 3D programme of your choice
  3. Wikitude AR package for Unity

  4. Pc or laptop
  5. Smartphone or tablet(for AR deployment)

Apply here!

Schedule:

  • Timezone: Los Angeles Time

  • Day 1 3h / 11am - 2pm PT (11th July)

    1. Lecture on AR in architecture and potential outcomes
    2. Miro discussion
    3. Intro to Wikitude in Unity and image tracking setup

  • Day 2 -3h / 11am - 2pm PT (12th July)

    1. Short presentations on AR concepts
    2. AR content prep
    3. Keyframe animations in unity
    4. Scripts and shaders overview
    5. Technical help

  • Day 3 - 3h / 11am - 2pm PT (13th July)

    1. Showing work in progress
    2. Technical helpn

  • Day 4 / July 14th

    1. Finals
Tutors:
Shaun McCallum
Sasha Belitskaja
Bio:

Shaun McCallum is a Scottish architectural designer and digital artist whose work investigates the impact of new technologies upon socio-political cultures through ephemeral architectural objects and installations. He received his Bachelor of Architecture, with Distinction, from the University of Dundee before studying at the (Sci-Arc) Southern Institute of Architecture in Los Angeles and Die Angewandte in Studio Greg Lynn. His projects which explore the accessibility and integration of digital technologies within existing physical structures have received a variety of awards and have been published internationally. As a researcher, Shaun has served as a travel fellow in China investigating the interplay of mystical historical ruins juxtaposed with new consumer lead architectural objects and under occupied mega cities. With his interests in hybridised realities Shaun has taught workshops on augmented reality and virtual reality through experimental workflows.

Sasha Belitskaja is an Estonian architectural designer and game developer whose work centres on novel interactive design models and the interplay of new emergent aesthetics. Her projects focus on utilizing computer graphics and game engine technology to explore new forms of connectivity between audience, architect and community. Her experimental work and proposals have been published internationally. Sasha has taught workshops on building dynamic spatial conditions through custom built game design environments and experimental 3D modelling softwares. She received her Bachelor of Architecture from the University of Dundee, graduating with distinction, before continuing her masters studies at Die Angewandte in Studio Greg Lynn. Throughout her professional architecture career, Aleksandra has worked for award winning internationally-known innovative offices in Stuttgart, Vienna and Los Angeles.


workshop03

DeepIsomer: Implicit 3D Variation of Design with Autoregressive Neural Network

Description:

Artificial intelligence (AI) and machine learning (ML) have been integrated in the workflow and the creative processes of many industries in the recent years. The open-source nature of the development of the tools has presented an opportunity to the architecture community to not only borrow already developed techniques, but also to reinterpret them to supplement our tacit knowledge. This workshop will introduce a new method – DeepIsomer – that uses autoregressive deep neural network to implicitly generate isomers (variants) of 3D forms. The goal is to understand and employ AI driven automated design iteration with hands-on demonstration and a design charrette.

Participants will be introduced to the theory of neural network and autoregression to provide the conceptual framework needed for the workshop design charrette. Subsequently, DeepIsomer shall be used 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 mentioned as following -

  • 1.Discretisation of 3D digital model(s)
  • 2.Autoregression of the discrete representation(s) using neural network to generate variants
  • 3.Decoding the variant output discrete representation(s) into 3D digital model(s)

Participants shall be using Grasshopper to encode discrete 3D forms and decode the output discrete representations into 3D forms. Google Colab shall be used to train and run the neural network. Participants shall be taught how to set up a Colab notebook with code snippets in order to execute deep learning. Form day 3, participants will work in teams of two or three to generate and document variations of 3D forms modeled by themselves. Participants will be encouraged to explore different geometrical typologies, e.g., orthogonal, circular, composite, and free-form.
DeepIsomer establishes a new paradigm of implicit design iteration that steers away from the currently prevalent method of explicitly scripting the (parametric) geometric rules. These investigations provoke deliberations over the role of the machine as the “doer”, the “thinker” or the “creative companion”; and the authorship of the final output.


Keywords:

Deep learning, Neural network, 3D variation, Autoregression

Requirements (Hardware/Software):

-Basic 3d software knowledge, smartphone, laptop, Zbrush or Cinema4d, SparkAR
-Augmented and animated object on students smartphone


Max Participants:
20

Apply here!

Schedule:

  • Timezone: Los Angeles (UTC/GMT – 05:00)


  • Session Duration: 9 am – 12 noon CT


  • Day 1

    1. Introductory presentation
    2. Tutorial of the workflow (Rhino & Google Colab)


  • Day 2
    1. Digital model preparation
    2. Discretization, autoregression
    3. Decoding discrete output of digital models


  • Day 3

    1. Charrette
    2. 3D variation production

  • Day 4

    1. Charrette
    2. 3D variation production

  • Day 5

    1. Project documentation
    2. Open discussion
Tutors:

Joy Mondal
Bio:

Joy Mondal leads WEsearch lab which offers design computation consultancy to architecture practices in Southeast Asia. He has released Grasshopper plugins to automate column-beam placement (Eelish) and to generate Piet Mondrian inspired 2D composition and 3D massing (Chingree). He was the recipient of the inaugural Saint-Gobain research scholarship. Earlier, he worked with the Sutainability Group at AECOM to setup POT (Parametric Optimisation Technology), which offered parametric performance optimisation solutions to architects for the first time in India.
Joy is a TEDx fellow, presenting ways of democratising architecture for everyone by using graph theory and shape grammar to automate residential design generation, thereby making design service more affordable. His research has been published in various CAAD conference proceedings. He has tutored multiple international workshops including at Rethinking The Future workshop series, Digital FUTURES 2020, ASCAAD 2021 and CAADRIA 2021.


workshop04

Experiences & Heritage in south European cities: Digital tools and practices

Description:

The seminar will be addressing questions regarding contemporary relevance of historic cities, including resilience and sustainability of multicultural metropolises; urbanization, etc. Urban studies require computationally-enabled techniques for incorporating data that reveal the details of everyday life, as well as data at nested scales (neighbourhoods, districts, and the city as a whole). The proposed seminar will:

Offer opportunities for participants to exchange ideas, knowledge, good practices and tools of co-creation about the study of public space in historic cities through an exemplar case of a south European city with very rich built heritage that is challenged by economic conditions, climate change, and which hosts to a great extent migrant communities (Palermo).

Introduce seminar participants to examples of online tools and innovative mobile applications of co-creation which support policy-making related to heritage and urban development, specifically the application of a new software tool DARIAH app, developed by DEUSTO Tech (University of Deusto, Bilbao, Spain) for the needs of the working group on ‘Digital Practices for the study of Urban Heritage’ that the applicant is chairing at the European digital infrastructure network of the Arts and Humanities DARIAH ERIC.

Keywords:

Digital tools, co-creation, public space, built heritage, crowdsourcing, data management

Requirements (Hardware/Software):
  1. Mobile phone (manufactured after 2017-18)
  2. DARIAH app:
  3. This is a great opportunity to discuss in the context of the conference the role and impact of digital tools for co-creation and the practical outcomes of a physical workshop about a real world spatial challenge, supported financially by the DARIAH ERIC, involving local stakeholders and interdisciplinary teams of participants, more at: https://udigish.hypotheses.org/

Max Participants:
30

Apply here!

The workshop is cancelled. Interested parties can floow this link https://udigish.hypotheses.org/176 for a followup workshop on the same topic

Schedule:


Timezone: Athens (CET) (UTC/GMT +3),
Start time :09:30 AM CET, 12:30 AM PS
Worksession duration: 6h

  • Day 1 / July 15th
    1. A-Introduction
    2. B-Round table
    3. C-Discussion
    4. D-Testing
    5. E-Exchange of ideas
    6. F-Wrap up
Tutors:

Georgios Artopoulos
Fabio M Montagnino
Carlos Smaniotto Costa
Gaia Redaelli
Alfonso Bahillo
Jürgen F. Weishaupl
Colter Wehmeier
Bio:

Georgios Artopoulos works on immersive and virtual environments, urban modeling and digital simulation for the study of built heritage and the creative exploration of historical narratives. The social aspects of historic space and the cross-disciplinary nature of the pressing challenges facing our historic cities are explored through the externally funded projects he is coordinating (under H2020, ENI-CBC-MED, and RIF), his role as a Head of Virtual Competency Centre e-Infrastructure of the DARIAH ERIC, and as a Member of the Scientific Advisory Board of JPI Urban Europe.

Fabio M Montagnino in 2001 designed a multidisciplinary environment for innovation and technology transfer, which have been effectively initiated at the University Campus of Palermo, where he has been Managing Director from 2011 to 2019. He promoted a broad network of infrastructure for innovation ranging from the academic hub to a dedicated node for creativity and cultural ventures, to fab-labs, living labs and coworking spaces. He has been coordinator and partner of a large number of R&I and international cooperation activities, with a specific focus on sustainable development solutions. He is expert evaluator of the EIC Acceleration program.

Carlos Smaniotto Costa holds a diploma in landscape architecture and environmental planning and a PhD in urban and landscape planning from the Leibniz University Hannover/Germany. He is professor at Lusófona University in Lisbon, lecturing landscape/urban design and urban ecology in the master’s and PhD programmes, and member of the Interdisciplinary Research Centre for Education and Development (CeiED), where he leads the research area on citizen science in urban studies. He coordinates and participates in several collaborative training programmes with German, British, Brazilian and Iranian universities. He is the editor of the book series Culture & Territory of University Lusófona.

Gaia Redaelli From 2003 to 2012, she directed the Cordoba Foundation for Contemporary Architecture, a non-profit structure that studies urban and architectural transformations as they happen. From 2012 to 2015, she was Director General for Renewal of the Cityscape, of Buildings and of Architecture at the Ministry for Public Infrastructure and Civic Construction with the Regional Government of Andalusia. She has been a partner at Redaelli Speranza Architetti Associati since 2007.

Alfonso Bahillo From 2017 to 2020 he was the Director of DeustoTech, the University of Deusto’s research institute for the ICT. He collaborates as a visiting professor in the Masters in Telecommunications of the Faculty of Electronics and Telecommunications of the Universidad del Cauca (Colombia) and the Faculty of Engineering of the University of Deusto. He has worked (leading some of them) in more than 30 projects and research contracts in all areas, regional, national and international. He is coauthor of 36 JCR articles, 9 book chapters, more than 35 papers at international conferences, and 4 national patents.

Jürgen F. Weishaeupl Director of the artprojects collective. Jürgen has long experience in art curation, acting as cultural conceptionist and producer for governmental organisations, cities, cultural institutions working in Austria, Italy, and other European countries.

Colter Wehmeier received a Master of Architecture from the University of Illinois in 2019, with a focus on situated media, virtuality, and urbanization. In the Fall of 2020, he entered a joint-PhD between UIUC’s Informatics program with a concentration in Art & Culture, and The Cyprus Institute’s program for Science & Technology in Cultural Heritage. His research interest is the influence of the public commons on community health and behavior. This work hopes to bridge theories of material architecture/urbanity with the field of social computing.


Project01

Bioinspired Connections: Nature, Sensors, and Design

Description:

This workshop investigates the role technology and neuroscience play in aiding the design process and making meaningful connections between people and nature. It introduces advanced technologies and quantified self practices (QS) that allow participants to use neural data and pattern recognition as feedback for the design process. The objective is to find clues to natural elements of human perception that can inform the design to meet goals for well-being. A pattern network of geometric shapes that achieve a higher level of monitored meditation levels and point toward a positive emotional valence is proposed. By referencing biological forms found in nature, the workshop utilizes an algorithmic process that explores how nature can influence architecture. To measure the impact, the team uses FaceOSC for capture and an Artificial Neural Network for micro-expression recognition, and a MindWave sensor manufactured by NeuroSky, which documents the human response further. By referencing biological forms found in nature, the workshop utilizes an algorithmic process that explores how nature can influence architecture and design. To measure the impact, the team uses interfaces designed for this purpose based on low-coast technology and open-source software, such as FaceOSC and Processing, which document the human response further. The participants start by creating geometries inspired by nature through algorithmic modeling; this allows specific parameters to be enforced. The projects that are most aligned with the biophilic design are compiled into a seven-minute presentation, which each participant watches while recorded a video-selfie.

An inter-individual analysis is made to classify the emotional valences provoked by each instance. The participants' facial expressions are then analyzed and ranked using FaceOSC and an Artificial Neural Network (ANN) for gesture recognition. This process is trained to correlate with micro-expressions using Geneva Affective Picture and Database. In parallel, an intra-individual analysis is used, and the designs are tested with commercial electroencephalography (EEG) sensor. The same designs are then observed one more time to estimate brain modulations in the observer's attention and meditation levels (AT, MT). These datasets are used to rethink the initial drawings based upon the degree of positive emotional valence. Upon review of the drawings as evidence, the low-cost interface (FaceOSC and Max MSP) and NeuroSky MindWave sensor allow us to establish a boundary logic, ranking geometric shapes that point to positive emotions and a higher level of monitored meditation levels. The results suggest a deeper level of understanding relative to geometric shapes in design. They indicate a new way to predict how well-being factors can clarify and rationalize a more intuitive design process inspired by nature. Also, they allow expanding the designer's perception, awareness, and sensitivity about the built environment.

This workshop is structured in four different stages. In the first, teachers and guests will introduce principles of biophilic design, evolutionary biology, neuroscience, and cognitive science. In the second, the instructors will provide training on algorithmic modeling of NURBS, meshing, and geometric transformations related to bioinspired design, using Rhino, Grasshopper, and other plug-ins. In the third, the proposals will be evaluated with MindWave to measure neurophysiological values and FaceOSC in Max MSP to recognize emotional states. Finally, the content will be presented to the group with high-resolution images and commented on by the final panel.

Keywords:

Bioinspired design, Algorithmic modeling, Neurophysiological sensing, Emotional states, Design sensibility

Requirements (Hardware/Software):
  1. Basic knowledge on geometry and/or modeling.
  2. Rhino 6 or 7 and Grasshopper

Max Participants:
15

Min Participants:
8

Apply here!

Schedule:

  • Timezone:
    Los Angeles Time (GMT -7)

  • Worksession Duration:
    9:00 AM – 4:00 PM (Including lunch break)

  • Day 1 (6h)

    1. Introduction of Biophilia, Biomimetics, Aesthetic principles
    2. Introduction of Neuroscience and Psychology principles


  • Day 2 (6h)

    1. Worksession with participants

  • Day 3 (3h)

    1. Worksession with participants

  • Day 4 (3h)

    1. Worksession with participants

  • Day 5 (6h)

    1. Final Presentations
Tutors:

Andrea Macruz
Ernesto Bueno
Gustavo Sol
Jaime Vega
Ricardo Palmieri
Bio:

Andrea Macruz holds a B.A. in Architecture from Universidade Presbiteriana Mackenzie in Sao Paulo, a Masters in Biodigital Architecture from Universitat Internacional de Catalunya in Barcelona, and a Masters in Contemporary Furniture Design from Istituto Marangoni in Milan. Andrea has exhibited in venues such as the Salone Satellite at the Milan Furniture Fair, London Design Week, etc. Currently, she is part of the DigitalFUTURES Ph.D. program at Tongji University in Shanghai and teaches Biomimicry at Centro Universitário Belas Artes.

Ernesto Bueno holds a degree in Architecture and Urbanism at UCV, in Caracas, a Masters in Biodigital Architecture at ESARQ-UIC, in Barcelona, and a Master in Design from UFRGS. He is part of the Ph.D. program in Architecture and Urbanism at Mackenzie. Ernesto has published in journals such as IJAC and has exhibited works in events such as CAAD Futures 2015. He was a tutor in AA Visiting School programs in Rio and SP and LAMO-UFRJ workshops. He is a researcher on parametric/algorithmic design, professor at UniBrasil Centro Universitário.

Gustavo Sol is an actor and director specialized in performativity neurocomputing. Postdoctoral fellow in the Neuroscience and Cognition Program (UFABC) holds a Ph.D. in Arts from ECA / USP (2017), with a Sandwich Doctorate at Paul-Valery III University (France). He holds a Masters in Communication and Semiotics from PUC / SP (2008) and a Bachelor's Degree in Performing Arts from UNICAMP (2000). Gustavo contributes to the Robotics and Rehabilitation Research Laboratory - LABORE / IF. He is a professor at the Centro Universitário Belas Artes and a collaborator of Digital Dramaturgy Lab Squared from the University of Toronto, Canada.

Jaime Vega is an architect and holds a Masters from IPT / SP. He is a professor in undergraduate and postgraduate courses at Centro Universitário Belas Artes and postgraduate courses at Universidade Anhembi Morumbi/Capes where he is also a doctoral student in design. He has his own studio called Vega Brasil, where he develops design works using VR / AR immersion technologies, parametric and gamification. He contributed to setting up the Lab IMEX at Belas Artes and participates in the postgraduate group at the Media Lab at Anhembi Morumbi.

Ricardo Palmieri is an architect and owner of Noisetupi. He is a Master student in Engineering and Innovation Management, at UFABC, a specialist in the development of interactive and immersive environments and multimedia producer. He participated in the implementation of Multimedia Kits by Cultura Viva Program of MinC. He was a professor at PUC-SP, UNIP, SENAC and IED-SP, and organized workshops in several cultural institutions in Brazil and abroad. In 2009 he won the Locative Media award at the Vivo ArteMov Festival and received honorable mentions at the Prix Ars Electronica in 2010 and 2013. Since 2011 he has been carrying out interactive audiovisual art projects.


workshop06

KUKA|crc Cloud Remote Control Modeling Tools

Description:

This workshop is a technical workshop that aims to introduce a workflow to produce sets of synthetic architectural data using visual programming tools. The workflow consists of a path from scratch to a complete point cloud data-set ready to be used in a deep neural network. We shaped the workflow over the idea of segmentation of historical dome systems of Anatolian Seljuk buildings.

The work that we propose starts with a parametric definition of the parts of an architectural system selected by the participants. The relation of the parts and how they come together will be defined. The addition of details for unique elements is optional after this step. We continue with the definition of layers and a naming system. The export of the data-set is the final step of the data creation process. The workshop will conclude with a presentation and demonstration on the use of data-set for a machine learning experiment.

KUKA|crc Cloud Remote Control allows users from anywhere in the world to control robots in international locations. During the CAADfutures workshop participants will learn how to design for parametric robotic fabrication, simulate and optimize robotic path planning, remotely book robots and send code for automated production. Ww will provide workshop licenses to the software and remote access to the robots. Participants will monitor the robotic process through digital twins and multiple web stream views of the robotic cell. We will use Zoom as a platform for online collaboration. We will use Rhino/Grashopper/KUKA|crc to collaborate with the robots.

Keywords:

Parametric, Robotics, Automation, Remote Control

Requirements (Hardware/Software):
  1. a Windows computer
  2. high speed internet connection
  3. Latest version of Rhinoceros 3d & GH.
  4. Small scale prototyping tools - wood sticks & glue gun

Max Participants:
12

Apply here!

Schedule:

  • Timezone:
    Berlin (UTC/GMT +2)

  • Work sessions:
    Daily from 14:00 – 19:00 Cest (Central European Summer Time)

  • Day 1 / July 11

    1. Intro to Automation
    2. Software installation, remote connection and basic robot motions

  • Day 2 / July 12

    1. Collaborative building strategies with bricks
    2. Introduction to pick & place strategies
    3. Early design decision assistance tools – Physics simulations

  • Day 3 / July 13

    1. Design strategy discussion: Collaborative building strategies with steel
    2. Strategy A: Plane creation for path planning
    3. Strategy A: Early design decision assistance tools – Structure & path optimization

  • Day 4 / July 14

    1. Collaborative building with steel
    2. Visualizations, Animations, and AR
    3. Prototyping

  • Day 5 / July 15

    1. Collaborative building with steel
    2. Prototyping
Tutors:

Sigrid Brell-Cokcan, Ethan Kerber, Dr. Sven Stumm
Bio:

Univ.-Prof. Dr. techn. Sigrid Brell-Cokcan founded the Chair of Individualized Production (IP) in 2015. She is a founding partner of II Architects, and founding partner/president of the Association for Robots in Architecture.,

Ethan Kerber is a computational designer with experience in digital fabrication including public sculptures in Washington DC and Virginia. Ethan is a researcher at IP and Managing Editor for the Journal on Construction Robotics.,

Dr. Sven Stumm is the lead developer of KUKA|crc, which integrates automated technology into online collaboration enabling remote users to collaborate closely with robotic production processes, integrating Industry 4.0 principles to create decentralized production networks.


workshop07

Synthesizing Training Data Using Parametric Modeling Tools

Description:

This workshop focuses on data set synthesis using parametric definitions of architectural elements in cultural heritage sites. If you are dealing with semantic segmentation problems in scan-2-BIM workflow and you lack data to train your deep neural network, it's a workshop for you!

It is a technical workshop that aims to introduce a workflow to produce sets of synthetic architectural data using visual programming tools. The workflow consists of a path from scratch to a complete point cloud data-set ready to be used in a deep neural network. We shaped the workflow over the idea of segmentation of historical dome systems of Anatolian Seljuk buildings.

Initially, the work that we propose starts with a parametric definition of the parts of an architectural system selected by the participants. The relation of the parts and how they come together will be defined. The addition of details for unique elements is optional after this step. We continue with the definition of layers and a naming system. The export of the data-set is the final step of the data creation process. The workshop will conclude with a presentation and demonstration on the use of data-set for a machine learning experiment.

Each participant will have been introduced to a method of synthesizing data for deep learning training in architectural heritage. The applicants will be focusing on different details of the structures, and all the data-set will be combined at the end of the workshop. Each participant will also walk away with a prepared data set for such procedures. We ask the participants to open the right of use to workshop organizers for research purposes.

The “Synthesizing Training Data Using Parametric Modeling Tools” workshop is part of a project supported by TÜBİTAK under the number 119K896.This workshop is a technical workshop that aims to introduce a workflow to produce sets of synthetic architectural data using visual programming tools. The workflow consists of a path from scratch to a complete point cloud data-set ready to be used in a deep neural network. We shaped the workflow over the idea of segmentation of historical dome systems of Anatolian Seljuk buildings.

Keywords:

Training Data Generation, Synthetic Data, Point Cloud, Cultural Heritage

Requirements (Hardware/Software):
  1. The participants require a computer which can run Rhinoceros 3D and Grasshopper.
  2. An intermediate level of modeling and visual programming is required. Participants can follow the workshop using any modeling environment in which they are advanced at but the instructor will be giving all the definitions, and support in Rhinoceros 3D and Grasshopper. Models will be converted into point clouds using Cloud Compare, no prior knowledge required.

Max Participants:
8

Apply here!

Schedule:

  • Timezone:
    Istanbul (UTC/GMT +3)
  • Session Duration: 04:00 - 08:00 (EST), 10:00 - 14:00 (CET), 16:00 - 20:00 (China)

  • Day 1 / July 11th
    1. Intoductory Meeting
    2. Introduction to the topic, installation of the required plugins and applications.
    3. How could it be used? | A small introduction to Neural Network training.
    4. Parametric modeling | Selection of the subject
    5. Definition of a simple set geometry | Definition of a simple set geometry
    6. Semi-supervised work session through Slack

  • Day 2 / July 12th

    1. Detailing
    2. Redefinition of the geometry with more details.
    3. Definition of layers with Elefront.
    4. Naming convention. Exporting.
    5. Writing a C# code to bake and export the created mesh geometries as obj files.
    6. Convert obj Files into point clouds using CloudCompare.
    7. Semi-supervised work session through Slack


  • Day 3 / July 13th

    1. Conclusion of the works. Final Presentations and discussion on the results.
Tutors:

M. Cem Güneş, Sevgi Altun, Berkay Öztürk, Alican Mertan, Yusuf H. Şahin
Bio:

Cem Güneş is an architect with a background in computer science and a graduate student in the Architectural Design Computing program at Istanbul Technical University. He is currently working on data enrichment for deep learning in documentation tasks and semi-automatic reconstruction of historical architectural elements using visual programming tools.

Sevgi Altun is an architect with a background in electrical - electronics engineering. She is a research assistant and a graduate student in the Architectural Design Computing program at Istanbul Technical University. Her research focuses on the correlation of the material construction of brick structures with the design geometry.

Berkay Öztürk is an architect who has graduated from İzmir Institute of Technology in 2019 and a graduate student in the Architectural Design Computing program at İstanbul Technical University. He worked as a junior architect for a year in an architectural design office and during this time he lectured about BIM and Revit at the local chamber of architects and started the transition process of the office to the BIM system. He is currently working on heritage building information modeling (HBIM).

Alican Mertan is a Ph.D. student at the Computer Engineering program and a member of the Vision Lab at Istanbul Technical University. His research so far focused on 3D Vision problems. He develops and analyzes deep learning-based solutions for 3D vision problems such as depth estimation and point cloud processing. Currently, he is working on a research project, where he tries to develop deep learning-based solutions to automatically process the data of historic buildings. The project involves dealing with limited and noisy real-world data.

Yusuf H. Sahin is a research assistant and Ph.D. candidate in Computer Engineering, ITU. Currently, he is working on computer vision (including 3D vision and especially point clouds), deep learning, and machine learning. He is a part of the ITU Vision Lab and working with Prof. Gozde Unal.


workshop08

Beyond generative Computer Aided-Architectural Design (CAAD)

Description:

This lobby will discuss CAAD in the age of digital ubiquity and rapid development of Artificial Intelligence (AI) capabilities and its historical linkages with generative algorithms (procedural models today), but also with digitization of traditional architectural and urban design practices. We intend to create a themed three 1-2h sessions on Artificial Intelligence (AI) , procedural modelling and CIM (linking to aspects of traditional architectural and urban design practices). We will open the workshop with a provocative 10min presentation and maybe have a 10min presentation by a pioneer on AI, procedural modelling and CIM (to be confirmed). Then we will have a symposium like lobby where I as moderator will guide a discussion asking difficult questions about intersection of CAAD trends (automation, incorporation of AI, proceduralization and interfaces for architect-computer interactions) and professional architectural and urban design practices. All the participants (we plan for 20-30 participants) will later engage with the debate. I intend to invite pioneers in procedural modelling (e.g. Gustavo Patow who created skylineEngine, and also programmers/computer engineers from Avalanche studios who do procedural modeling in Houdini), urban morphologists (Ivor Samuels, Paul Sanders, Jenni Partanen) who work with urban design and we cooperate with us on the development of the CIM software

1. What is really the difference between CAAD and BIM? What are the historical precedents of CAAD? How much of the CAAD history is linked with automation (CAD-CAM) and generative algorithms (e.g. William Mitchell's advocacy who wrote a book on CAAD in the 1977)? How does CAAD (as generative algorithms) and current BIM apps fit the traditional architectural and urban design practices? Can we call ArchiCAD and Revit (the dominant BIM software) CAAD apps (software used by architects)? Why are BIM apps so popular among architects and not among construction engineers or project leaders at construction sites?

2. How digitization and new AI development would influence CAAD? What is the role of AI in the traditional architectural and urban design practices? Why there is no AI in ArchiCAD and Revit (the dominant BIM software)? How can we integrate AI in these apps (visionary question)? Would AI change the role of the digital architect and urban designer? Much of the CAAD advocacy is on CAD-CAM (automating architectural design and construction), but do we really want to live in automatic buildings and cities? Is automatic architecture preferable? The literature on CAAD and CIM emphasizes information models and city generative algorithms. AI is conceived as design machine, but we can think of AI as aid to designers (conversational or analytical). How can AI help in the creation of design worlds and toolboxes (architects work with unique design toolboxes and analytical tools) and automatically produce deliverables such as drawings, notations, analyses and so on.

3. While architects have BIM software that includes architectural design elements (and parametric models), planners and urban designers use Geographic Information Systems (GIS) that does not fit their practices. They usually print out maps and draw urban designs on paper. GIS as digital twin offers a very poor support for urban designers. What is the current and future role of digital twins and AI in morphological analyzes and urban design? What kind of software is needed? What are the CAAD and BIM influences on urban design? How AI can help?

Keywords:

Generative design, procedural modeling, urban design, urban morphology, City Information Modeling (CIM)

Requirements (Hardware/Software):
  1. No requirements (just Zoom).


Max Participants:
20

Apply here!

Schedule:

  • Timezone:
    Stockholm (UTC/GMT +2)

  • Worksessions:
    15:00pm - 21:00pm (6:00am-12:00pm PST)

  • Day 1 / June 13th

    1. 15:00-15:30 Welcome 1 (generative algorithms as CAAD leitmotif and proceduralism as new paradigms)
    2. 15:30-16:30 City procedural modelling (Gustavo Patow presenting SkylineEngine for 30min plus discussions)
    3. 16:30-17:00 Mingle
    4. 17:00-17:30 Welcome 2 (generative algorithms and designer practices)
    5. 17:30-18:30 Generative design for professionals (Kean Walmsley presenting Autodesk's generative design efforts for 15min plus discussions/panel possibly)
    6. 18:30-19:00 Mingle
    7. 19:00-19:30 Welcome 3 (CAAD/CAUD, BIM/CIM, designer practices and automated architects/urban designers)
    8. 19:30-20:30 Digitizing architects and urban designers (where does proceduralism and AI fit in architectural, urban design and planning practices?). Preview of the new CIM software.
    9. 20:30-21:00 Mingle
Tutors:
Todor Stojanovski, Hui Zhang
Bio:

I am a postdoc at the Embodied Social Agents Lab (ESAL), the division for Computational Science and Technology (CST) at KTH Royal Institute of Technology in Stockholm Sweden where I work with digitizing urban design and City Information Modelling (CIM). I am originally an architect and I am engaged with urban morphology and the morphology of various digital twins incl. Geographic Information Systems (GIS), procedural models and city generative algorithms. The current literature on CIM emphasizes information models and city generative algorithms similarly as in Computer Aided-Architectural Design (CAAD). In my CIM approach I advocate to create Urban Morphological Artificial Intelligence (UMAI) as "invisible" digital morphologist and aid to designers. UMAI help in the creation of design worlds and toolboxes, design defaults, links to big data, and automatically produce urban design deliverables such as drawings, notations, analyses and so on (depending on the style of the architect and urban designers.


workshop9

The Horta Component Library: Using Space Groups in Grasshopper to Create Novel Honeycombs

Description:

The Space Groups are a mathematical system for the description of the symmetries in 3d lattices. They can be applied to architectural computation to create rigorous yet novel honeycombs for visualization and fabrication. Professor Duane McLemore of Mississippi State University has developed Horta, a component library for Grasshopper for the implementation of the Space Groups. This will be used to fabricate real-world objects, and this workshop will be the first public use of these components.The Workshop will have two components, a 2 day Software Tutorial and Collaborative Design Hackathon which will be available in person or online, and a 3 day Fabrication Workshop in which together we will construct a full-scale Installation designed collaboratively using the Space Group Symmetries. (Note that the final design will be generated during the Workshop. All included representations are a similar design idea which meets the same criteria.

Keywords:

Space Groups, Grasshopper, Lattice, Installation, Fabrication

Requirements (Hardware/Software):
  1. A laptop computer capable of running Rhino 6 or 7 and Grasshopper.
  2. Rhino 6 or 7 and Grasshopper.The Horta Component Library will be distributed at the beginning of, or before, the start of the Workshop

Max Participants:
50

Apply here!

Schedule:

  • Timezone:
    Los Angeles Time (GMT -7) - 9:00 AM – 4:00 PM (Including lunch break)
  • Worksessions(Local time): 9:00 AM – 4:00 PM (Including lunch break)

  • Day 1 / July 11th

    1. Workshop on the Space Groups
    2. Exploration of Space Groups for architecture and Design
    3. Software tutorial on the Horta Component Library

  • Day 2 / July 12th

    1. Design Hackathon, wherein the participants and I collaborate on a final design for the installation we are creating.
    2. Production of the cut files for the Installation
    3. Remote participants who complete Days 1 and 2 will receive the Certificate of Completion

  • Day 3 / July 13th

    1. Material preparation and cutting.
    2. Coaching of any interested parties in any smaller-scale fabrication projects they are doing on their own.

  • Day 4 / July 14th

    1. Post-processing of geometry
    2. Beginning the assembly process.
    3. Coaching of any interested parties in any smaller-scale fabrication projects they are doing on their own.

  • Day 5 / July 15th

    1. Assembly of final piece
    2. Final Discussion
Tutors:
Duane McLemore
Bio:

Duane McLemore is an Assistant Professor at the School of Architecture at Mississippi State University. He is the co-founder of X Over Zero, an architecture and design firm best known for their 3d printed jewelry. His research focuses on 1. the use of computation in contemporary fabrication methods. 2. The application of mathematics – specifically the Space Groups - in computational design. 3. The application of geometry in architectural design, fabrication, and education. Duane is a graduate of the University of Southern California (BArch 2003) and the Bartlett School of Architecture at University College London (MArch 2010). He is a licensed Architect in the State of California.


workshop10

Timber Tectonics

Description:

Architectural Geometry (AG) focuses on the synthesis of shapes that guarantee structural and fabrication optimality. It is also closely aligned with and complementary to the development of robotic and digital fabrication (RDF) technologies and design methods. The workshop will explore the relevance of this state-of-the-art design and construction paradigm in the realm of complex, multi-objective, precision manufactured, computational geometry projects. Specifically, the workshop is a collaborative design exercise exploring the design space of topologies that seeks synergies of tacit mesh modeling with computational formfinding, digital timber and RDF.

The workshop will thus provide a hands-on, introductory experience to prepare for both the imminent future of architectural design and construction and architectural practise; The content and tool-chains of the workshop are representative of the state-of-the-art in the AEC industry as it shifts from Building Information Modelling (BIM) for documentation to Design for Manufacturing and Assembly (DfMA)/ industrialised construction (IC) paradigm.

Keywords:

Architectural Geometry, Digital Timber, Computational Formfinding, Design for Manufacturing

Requirements (Hardware/Software):
  1. Intermediate Mesh Modeling in Rhino, Maya ; Knowledge of programming/ Grasshopper beneficial
  2. McNeel Rhinoceros 7.0, Grasshopper, Autodesk Maya 2018; Fast internet connection

Max Participants:
12

Apply here!

Schedule:

  • Timezone:
    London (UTC/GMT +1)

  • Work session duration: 6 hours a day starting at 16:30 London time


  • Day 1 / July 12th

    1. 2 hours tutor led session
    2. 5-6 hours of self led work in teams

  • Day 2 / July 13th

    1. 2 hours tutor led session
    2. 5-6 hours of self led work in teams

  • Day 3 / July 14th

    1. 2 hours tutor led session
    2. 5-6 hours of self led work in teams

  • Day 4 / July 15th

    1. 2 hours tutor led session
    2. 5-6 hours of self led work in teams
    3. wrap up results
Tutors:
Zaha Hadid Architects, Computation & Design Group , London, UK
University of Calgary SAPL, Calgary , Canada
Bio:

Vishu Bhooshan is a Lead Designer at Zaha Hadid Architects, Computation and Design Research group (ZHA CODE) in London. He also teaches at Architectural Computation & Architectural Design, Bartlett post-graduate programs (BPro), University College of London.

He leads the design research on computational geometries, with specific interest on structure and fabrication aware tectonics and the development of software agnostic computational frameworks to explore it. He has taught and presented at several institutes, international workshops and professional CAD conferences.

Henry David Louth is a computational designer and design lead with the Computation and Design Research Group (ZHCODE).

He joined ZHA in 2014, and now leads the residential efforts and special projects within ZHACODE. HE has over 13 years of professional experience in the AEC industry on various project types, scales, and sectors. He is a registered US architect and LEED accredited professional. Prior to ZHA, Henry worked in the US overseeing fast track deliveries, and facilitating retailer rollouts.

During his time at ZHA, Henry has contributed to several projects including a student housing project in Hong Kong, Volu prefabricate dining pavilion, Thallus Experimental Structure, The Winston Gallery, Morpheus Hotel at City of Dreams Macau, Venice retrospective exhibition Palazzo Franchetti, MUAC UNAM exhibition: Design as Second Nature and Xi'an International football centre.

Most recently as lead designer, he led the design team and coordination for Roatan Prospera developing a digital platform and systems design for ecologically and economically sustainable island housing developments on hillside coastal terrain.

Henry has conducted workshops and short courses on various topics ranging from applied research to geometry and construction for each Architectural Association Visiting School (AAVS)'14, the association for Computer Aided Architectural Design in Asia (CAADRIA)'18, and Digital Futures '20. He is a published researcher in the international Journal Rapid Manufacture and conference paper contributor to SIMAUD'15, Fabricate '17 and Design Modelling Symposium 19.

Alicia Nahmad Vazquez is the founder of Architecture Extrapolated (R-Ex) and works as assistant professor of robotics and AI in architecture at the University of Calgary. She is also co-director of the Laboratory for Integrative Design. For the last 5 years, Alicia worked as studio master co-leading the Nahmad-Bhooshan studio at the Architectural Association DRL master’s program.

As a research-based practising architect, Alicia explores materials and digital design and fabrication technologies along with the digitization of building trades and the wisdom of traditional building cultures. Her projects include the construction of award-winning ‘Knit-Candela’ and diverse collaborations with practice and academic institutions on the development and on-site construction of shell structures.

She holds a PhD in human-robot collaborative (HRC) design from Cardiff University and a MArch from the AADRL. Alicia previously worked developing design tools for practices like Populous and Zaha Hadid architects. Alicia has also been an Artist-In-Residence at Autodesk Pier 9, and has taught and lectured extensively in Latin America and Europe. Her research has been widely published internationally in journals and conference proceedings



workshop11

From Aalto to Darwin: Genetic optimization of modernism's classics

Description:

The goal of the workshop is to demonstrate a workflow for computational optimization. Starting from a selection of architectural symbols, students will be guided to define a design as a set of computational rules thereby expanding the existing building to it's global solution space. Attendees will then learn how to setup an optimization algorithm that tests the solution space and returns the most optimal design. Finally, the original and the AI optimized designs will be critically evaluated side by side, and will be discussed in an open session by a panel of experts in AI and architecture

Keywords:

Generative optimization, Multi-objective generative algorithms, artificial intelligence, Generative Space Planning, Evolutionary Solver

Requirements (Hardware/Software):
  1. Softwear: Rhino7, Grasshopper, Wallacei and Ladybug tools + additional plugins list will be given to participants prior to the workshop.
  2. Level of participants: Prior knowledge and use of grasshopper is a requisite.

Max Participants: 20

Apply here!

Schedule:

  • Timezone:
    Barcelona CEST (UTC/GMT +2)

  • Worksession Duration: 4 - 8 pm (UTC+2) / 7:00 am-11:00 am (PST)


  • Day 1 / July 11th / 7:00 am-11:00 am (PST)

    1. Introduction + Session 1
    2. Participants will split in groups of 4

  • Day 2 / July 12th / 7:00 am-11:00 am (PST)

    1. Presentation & Tutorial Session 2
    2. Working in groups of 4

  • Day 3 / July 13th / 7:00 am-11:00 am (PST)

    1. Tutorial Session 3 & Work
    2. Working in groups of 4

  • Day 4 / July 14th / 7:00 am-11:00 am (PST)

    1. Tutorial Session 4 & Work
    2. Wrap up
Tutors:
Oana Taut, IAAC
Bio:

Oana Taut is a Romanian architect specializing in AI in Architecture. She obtained her first master degree in architecture at UAUIM in Bucharest, Romania and completed the two-year Master in Advanced Architecture at the Institute for Advanced Architecture of Catalonia (IAAC) in Barcelona, Spain.Oana’s professional aim is to design space from objective data, and materialize it in a sustainable way. Her interests include computation, genetic optimization, digital fabrication and immersive visualization technologies.

Her master thesis project developed in IaaC is a research on the topic of artificial intelligence as enabler of a renewed architectural process. During the last two years she has been active in the acdemic world as Studio Faculty Assistant and Academic Coordinator of Master of Advanced Computation for Architecture and Design in IAAC. Before Oana has worked as an architect in Ireland, involved in education projects locally and hospitality projects in the Middle East.



workshop11

Workshop Presentations and Discussion

Description:

Presentation feom the workshop tutors on the work completed during the week of the workshops. The presentation will be followed by a short discussion