Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 20 of 529

Reformat results as: short short into frame detailed detailed into frame

_id	ecaadesigradi2019_605
id	ecaadesigradi2019_605
authors	Andrade Zandavali, Bárbara and Jiménez García, Manuel
year	2019
title	Automated Brick Pattern Generator for Robotic Assembly using Machine Learning and Images
doi	https://doi.org/10.52842/conf.ecaade.2019.3.217
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 3, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 217-226
summary	Brickwork is the oldest construction method still in use. Digital technologies, in turn, enabled new methods of representation and automation for bricklaying. While automation explored different approaches, representation was limited to declarative methods, as parametric filling algorithms. Alternatively, this work proposes a framework for automated brickwork using a machine learning model based on image-to-image translation (Conditional Generative Adversarial Networks). The framework consists of creating a dataset, training a model for each bond, and converting the output images into vectorial data for robotic assembly. Criteria such as: reaching wall boundary accuracy, avoidance of unsupported bricks, and brick's position accuracy were individually evaluated for each bond. The results demonstrate that the proposed framework fulfils boundary filling and respects overall bonding structural rules. Size accuracy demonstrated inferior performance for the scale tested. The association of this method with 'self-calibrating' robots could overcome this problem and be easily implemented for on-site.
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:54

_id	ecaadesigradi2019_514
id	ecaadesigradi2019_514
authors	de Miguel, Jaime, Villafa?e, Maria Eugenia, Piškorec, Luka and Sancho-Caparrini, Fernando
year	2019
title	Deep Form Finding - Using Variational Autoencoders for deep form finding of structural typologies
doi	https://doi.org/10.52842/conf.ecaade.2019.1.071
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 71-80
summary	In this paper, we are aiming to present a methodology for generation, manipulation and form finding of structural typologies using variational autoencoders, a machine learning model based on neural networks. We are giving a detailed description of the neural network architecture used as well as the data representation based on the concept of a 3D-canvas with voxelized wireframes. In this 3D-canvas, the input geometry of the building typologies is represented through their connectivity map and subsequently augmented to increase the size of the training set. Our variational autoencoder model then learns a continuous latent distribution of the input data from which we can sample to generate new geometry instances, essentially hybrids of the initial input geometries. Finally, we present the results of these computational experiments and lay out the conclusions as well as outlook for future research in this field.
keywords	artificial intelligence; deep neural networks; variational autoencoders; generative design; form finding; structural design
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:55

_id	acadia19_412
id	acadia19_412
authors	Del Campo, Matias; Manninger, Sandra; Carlson, Alexandra
year	2019
title	Imaginary Plans
doi	https://doi.org/10.52842/conf.acadia.2019.412
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 412-418
summary	Artificial Neural Networks (NN) have become ubiquitous across disciplines due to their high performance in modeling the real world to execute complex tasks in the wild. This paper presents a computational design approach that uses the internal representations of deep vision neural networks to generate and transfer stylistic form edits to both 2D floor plans and building sections. The main aim of this paper is to demonstrate and interrogate a design technique based on deep learning. The discussion includes aspects of machine learning, 2D to 2D style transfers, and generative adversarial processes. The paper examines the meaning of agency in a world where decision making processes are defined by human/machine collaborations (Figure 1), and their relationship to aspects of a Posthuman design ecology. Taking cues from the language used by experts in AI, such as Hallucinations, Dreaming, Style Transfer, and Vision, the paper strives to clarify the position and role of Artificial Intelligence in the discipline of Architecture.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:55

_id	ecaadesigradi2019_648
id	ecaadesigradi2019_648
authors	Eisenstadt, Viktor, Langenhan, Christoph and Althoff, Klaus-Dieter
year	2019
title	Generation of Floor Plan Variations with Convolutional Neural Networks and Case-based Reasoning - An approach for transformative adaptation of room configurations within a framework for support of early conceptual design phases
doi	https://doi.org/10.52842/conf.ecaade.2019.2.079
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 79-84
summary	We present an approach for computer-aided generation of different variations of floor plans during the early phases of conceptual design in architecture. The early design phases are mostly characterized by the processes of inspiration gaining and search for contextual help in order to improve the building design at hand. The generation method described in this work uses the novel as well as established artificial intelligence methods, namely, generative adversarial nets and case-based reasoning, for creation of possible evolutions of the current design based on the most similar previous designs. The main goal of this approach is to provide the designer with information on how the current floor plan can evolve over time in order to influence the direction of the design process. The work described in this paper is part of the methodology FLEA (Find, Learn, Explain, Adapt) whose task is to provide a holistic structure for support of the early conceptual phases in architecture. The approach is implemented as the adaptation component of the framework MetisCBR that is based on FLEA.
keywords	room configuration; adaptation; case-based reasoning; convolutional neural networks; conceptual design
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:55

_id	acadia19_370
id	acadia19_370
authors	Mohammad, Ali; Beorkrem, Christopher; Ellinger, Jefferson
year	2019
title	Hybrid Elevations using GAN Networks
doi	https://doi.org/10.52842/conf.acadia.2019.370
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 370-379
summary	This project is an attempt to develop and test a method for generating one-sided hybrid exterior building elevations using designer’s base criteria and design rule sets as inputs in an advanced artificial intelligence network. Architects are using computational design to expedite the iteration process in an efficient manner. Optimization techniques utilizing genetic solvers allow designers to explore broad sets of iterations within a predefined subset. However, with the application of artificial intelligence networks these fields of exploration can be expanded upon to develop ranges of exploration which can explore iterations outside of typical ranges. This paper explores the use of Generative Adversarial Networks (GAN) to explore and demonstrate their possible capabilities to typical design problems. In this instance we are exploring their application in the development of architectural elevations.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:58

_id	ecaadesigradi2019_135
id	ecaadesigradi2019_135
authors	Newton, David
year	2019
title	Deep Generative Learning for the Generation and Analysis of Architectural Plans with Small Datasets
doi	https://doi.org/10.52842/conf.ecaade.2019.2.021
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 21-28
summary	The field of generative architectural design has explored a wide range of approaches in the automation of design production, but these approaches have demonstrated limited artificial intelligence. Generative Adversarial Networks (GANs) are a leading deep generative model that use deep neural networks (DNNs) to learn from a set of training examples in order to create new design instances with a degree of flexibility and fidelity that outperform competing generative approaches. Their application to generative tasks in architecture, however, has been limited. This research contributes new knowledge on the use of GANs for architectural plan generation and analysis in relation to the work of specific architects. Specifically, GANs are trained to synthesize architectural plans from the work of the architect Le Corbusier and are used to provide analytic insight. Experiments demonstrate the efficacy of different augmentation techniques that architects can use when working with small datasets.
keywords	generative design; deep learning; artificial intelligence; generative adversarial networks
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_id	lasg_whitepapers_2019_291
id	lasg_whitepapers_2019_291
authors	Sabin, Jenny
year	2019
title	Lumen
source	Living Architecture Systems Group White Papers 2019 [ISBN 978-1-988366-18-0] Riverside Architectural Press: Toronto, Canada 2019. pp.291 - 318
summary	This paper documents the computational design methods, digital fabrication strategies, and generative design process for [Lumen], winner of MoMA & MoMA PS1’s 2017 Young Architects Program. The project was installed in the courtyard at MoMA PS1 in Long Island City, New York, during the summer of 2017. Two lightweight 3D digitally knitted fabric canopy structures composed of responsive tubular and cellular components employ recycled textiles, photo-luminescent and solar active yarns that absorb and store UV energy, change color, and emit light. This environment offers spaces of respite, exchange, and engagement as a 150 x 75-foot misting system responds to visitors’ proximity, activating fabric stalactites that produce a refreshing micro-climate. Families of robotically prototyped and woven recycled spool chairs provide seating throughout the courtyard. The canopies are digitally fabricated with over 1,000,000 yards of high tech responsive yarn and are supported by three 40+ foot tensegrity towers and the surrounding matrix of courtyard walls. Material responses to sunlight as well as physical participation are integral parts of our exploratory approach to the 2017 YAP brief. The project is mathematically generated through form-finding simulations informed by the sun, site, materials, program, and the material morphology of knitted cellular components. Resisting a biomimetic approach, [Lumen] employs an analogic design process where complex material behavior and processes are integrated with personal engagement and diverse programs. The comprehensive installation was designed by Jenny Sabin Studio and fabricated by Shima Seiki WHOLEGARMENT, Jacobsson Carruthers, and Dazian with structural engineering by Arup and lighting by Focus Lighting.
keywords	living architecture systems group, organicism, intelligent systems, design methods, engineering and art, new media art, interactive art, dissipative systems, technology, cognition, responsiveness, biomaterials, artificial natures, 4DSOUND, materials, virtual projections,
email
last changed	2019/07/29 14:02

_id	artificial_intellicence2019_117
id	artificial_intellicence2019_117
authors	Stanislas Chaillou
year	2020
title	ArchiGAN: Artificial Intelligence x Architecture
doi	https://doi.org/https://doi.org/10.1007/978-981-15-6568-7_8
source	Architectural Intelligence Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2022)
summary	AI will soon massively empower architects in their day-to-day practice. This article provides a proof of concept. The framework used here offers a springboard for discussion, inviting architects to start engaging with AI, and data scientists to consider Architecture as a field of investigation. In this article, we summarize a part of our thesis, submitted at Harvard in May 2019, where Generative Adversarial Neural Networks (or GANs) get leveraged to design floor plans and entire buildings .
series	Architectural Intelligence
email
last changed	2022/09/29 07:28

_id	acadia19_392
id	acadia19_392
authors	Steinfeld, Kyle
year	2019
title	GAN Loci
doi	https://doi.org/10.52842/conf.acadia.2019.392
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 392-403
summary	This project applies techniques in machine learning, specifically generative adversarial networks (or GANs), to produce synthetic images intended to capture the predominant visual properties of urban places. We propose that imaging cities in this manner represents the first computational approach to documenting the Genius Loci of a city (Norberg-Schulz, 1980), which is understood to include those forms, textures, colors, and qualities of light that exemplify a particular urban location and that set it apart from similar places. Presented here are methods for the collection of urban image data, for the necessary processing and formatting of this data, and for the training of two known computational statistical models (StyleGAN (Karras et al., 2018) and Pix2Pix (Isola et al., 2016)) that identify visual patterns distinct to a given site and that reproduce these patterns to generate new images. These methods have been applied to image nine distinct urban contexts across six cities in the US and Europe, the results of which are presented here. While the product of this work is not a tool for the design of cities or building forms, but rather a method for the synthetic imaging of existing places, we nevertheless seek to situate the work in terms of computer-assisted design (CAD). In this regard, the project is demonstrative of a new approach to CAD tools. In contrast with existing tools that seek to capture the explicit intention of their user (Aish, Glynn, Sheil 2017), in applying computational statistical methods to the production of images that speak to the implicit qualities that constitute a place, this project demonstrates the unique advantages offered by such methods in capturing and expressing the tacit.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:56

_id	acadia19_168
id	acadia19_168
authors	Adilenidou, Yota; Ahmed, Zeeshan Yunus; Freek, Bos; Colletti, Marjan
year	2019
title	Unprintable Forms
doi	https://doi.org/10.52842/conf.acadia.2019.168
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp.168-177
summary	This paper presents a 3D Concrete Printing (3DCP) experiment at the full scale of virtualarchitectural bodies developed through a computational technique based on the use of Cellular Automata (CA). The theoretical concept behind this technique is the decoding of errors in form generation and the invention of a process that would recreate the errors as a response to optimization (Adilenidou 2015). The generative design process established a family of structural and formal elements whose proliferation is guided through sets of differential grids (multi-grids) leading to the build-up of large span structures and edifices, for example, a cathedral. This tooling system is capable of producing, with specific inputs, a large number of outcomes in different scales. However, the resulting virtual surfaces could be considered as "unprintable" either due to their need of extra support or due to the presence of many cavities in the surface topology. The above characteristics could be categorized as errors, malfunctions, or undesired details in the geometry of a form that would need to be eliminated to prepare it for printing. This research project attempts to transform these "fabrication imprecisions" through new 3DCP techniques into factors of robustness of the resulting structure. The process includes the elimination of the detail / "errors" of the surface and their later reinsertion as structural folds that would strengthen the assembly. Through this process, the tangible outputs achieved fulfill design and functional requirements without compromising their structural integrity due to the manufacturing constraints.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:54

_id	acadia19_596
id	acadia19_596
authors	Anton, Ana; Yoo, Angela; Bedarf, Patrick; Reiter, Lex; Wangler, Timothy; Dillenburger, Benjamin
year	2019
title	Vertical Modulations
doi	https://doi.org/10.52842/conf.acadia.2019.596
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 596-605
summary	The context of digital fabrication allows architects to reinvestigate material, process and the design decisions they entail to explore novel expression in architecture. This demands a new approach to design thinking, as well as the relevant tools to couple the form of artefacts with the process in which they are made. This paper presents a customised computational design tool developed for exploring the novel design space of Concrete Extrusion 3D Printing (CE3DP), enabling a reinterpretation of the concrete column building typology. This tool allows the designer to access generative engines such as trigonometric functions and mesh subdivision through an intuitive graphical user interface. Balancing process efficiency as understood by our industry with a strong design focus, we aim to articulate the unique architectural qualities inherent to CE3DP, energising much needed innovation in concrete technology.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:54

_id	caadria2019_369
id	caadria2019_369
authors	Hirschberg, Urs
year	2019
title	Harmonielehre for Architects - Exploring the relationship between music and architecture by scripting
doi	https://doi.org/10.52842/conf.caadria.2019.2.757
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 757-766
summary	This paper reports on an introductory scripting class that, whilst teaching the basics of algorithmic design to a large number of architecture students, also explored the commonalities between architecture and music. Historical and recent precedents as well as the theoretical and the practical aspect of the project and its pedagogical outcomes are discussed. The technical section includes a detailed description of the setup created for the students. The musical data format used was MIDI (Musical Instrument Digital Interface), which was read into the 3D computer graphics package MAYA and turned into 3D geometries using the scripting language MEL (Maya Embedded Language). The paper also discusses the resulting student works and in how far the musical nature of the data is visible in them.
keywords	Computational Design Education; Generative & Algorithmic Design; Scripting; Architecture and Music; MIDI
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	ecaadesigradi2019_138
id	ecaadesigradi2019_138
authors	Kim, Yujin
year	2019
title	Bioinspired Modularity in Evolutionary Computation and a Rule-Based Logic - Design Solutions for Shared Office Space
doi	https://doi.org/10.52842/conf.ecaade.2019.2.341
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 341-348
summary	Evolutionary computation is a population-based problem solver that is characterized by a stochastic optimization in order to solve both a single objective and multiple objectives. Previous evolutionary computational researches provided various design options and improved optimization through being evolved with fitness criteria, especially when multiple design objectives conflict with one another. In this paper, a rule-based algorithm was combined with the evolutionary computational process to propose an assembly logic of the modules and to improve an architectural building design in order to adapt to environmental changes. Two algorithms - a rule based and generative algorithm- proceeded simultaneously and provided various options as well as optimization in real time. For the experiment set-up, existing buildings were divided into each module; the modules were reinterpreted and reassembled with the logic driven by Evolutionary Developmental Biology. The conclusion is that when a rule based logic is combined with a developmental algorithm with a modular system, it is more efficient for the design process to be analyzed, evaluated, and optimized. The ultimate outcome provides various options in a short amount of time.
keywords	Evolutionary computation; rule-based algorithm; modularity; reassembly
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:52

_id	caadria2019_318
id	caadria2019_318
authors	Martinho, Helena, BelÃ©m, Catarina, LeitÃ£o, AntÃ³nio, Loonen, Roel and Gomes, M. GlÃ³ria
year	2019
title	Algorithmic Design and Performance Analysis of Adaptive FaÃ§ades
doi	https://doi.org/10.52842/conf.caadria.2019.1.685
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 1, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 685-694
summary	Building performance simulation tools have the potential for aiding the decision-making process in early design stages of an architectural project. As traditional simulation tools are based on a static design and adaptive faÃ§ades encompass an envisioned movement of construction elements, there is a lack of supporting tools and workflows that can correctly evaluate the performance of such building envelopes at an early stage. The presented ongoing research focuses on developing efficient parametric performance-based approaches for assessing the energy consumption in buildings with adaptive faÃ§ades, combining generative architectural design and performance analysis in a seamless workflow. To this end, we combine a new algorithmic design research tool with the well-established whole-building simulation engine EnergyPlus. The purpose of linking both tools lies in the possibility of generating and simulating models with adaptive faÃ§ade mechanisms through a single script, evaluating and using the simulation results to adjust the model's parameters and develop optimized control strategies.
keywords	Building performance simulation; Adaptive faÃ§ades; Algorithmic design; Energy analysis
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	ecaadesigradi2019_389
id	ecaadesigradi2019_389
authors	Mohite, Ashish, Kochneva, Mariia and Kotnik, Toni
year	2019
title	Speed of Deposition - Vehicle for structural and aesthetic expression in CAM
doi	https://doi.org/10.52842/conf.ecaade.2019.1.729
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 729-738
summary	This paper presents intermediate results of an experimental research directed towards development of a method that uses additive manufacturing technology as a generative agent in architectural design process. The primary technique is to variate speed of material deposition of a 3D printer in order to produce undetermined textural effects. These effects demonstrate local variation of material distribution, which is treated as a consequence of interaction between machining parameters and material properties. Current stage of inquiry is concerned with studying the impact of these textural artefacts on structure. Experiments demonstrate that manipulating distribution of matter locally results in more optimal structural performance, it solves printability issues of overhanging geometry without the need for additional supports and provides variation to the surface. The research suggests aesthetic and structural benefits of applying the developed method for mass-customized fabrication. It questions the linear thinking that is predominant in the field of 3D printing and provides an approach that articulates interaction between digital and material logics as it directs the formation of an object that is informed by both.
keywords	digital fabrication; digital craft; texture; ceramic 3D printing
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_id	ecaadesigradi2019_177
id	ecaadesigradi2019_177
authors	Ostrowska-Wawryniuk, Karolina
year	2019
title	BIM-Aided Prefabrication for Minimum Waste DIY Timber Houses
doi	https://doi.org/10.52842/conf.ecaade.2019.1.251
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 251-258
summary	The continuous housing shortage demands efficient ways of design and construction. In the context of rising construction standards and shrinking manpower, one of the possible answers to the problem is prefabrication oriented towards do-it-yourself (DIY) construction methods, which could contribute to the low and middle income housing supply in the market. The article covers the process of developing an experimental tool for aiding single-family housing design with the use of small-element solid timber prefabrication, suitable for DIY assembly. The presented tool uses the potential of BIM technology adapting a traditionally-designed house to the needs of prefabrication and optimizing it in terms of waste generated in the assembly process. The presented experiment was realized in the Autodesk Revit environment and incorporates custom generative scripts developed in Dynamo-for-Revit. The prototype analyzed an input model and converted it into a prefabricated alternative based on the user- and technology-specified boundary conditions. The prototype was tested on the example design of a two-story single-family house. The results compare the automated optimized model conversion with manual adaptation approach. The implemented algorithm allowed for reducing the construction waste by more than 50%.
keywords	do-it-yourself construction; do-it-yourself house; generative BIM; BIM-aided prefabrication; small-panel timber prefabrication; self-help housing
series	eCAADeSIGraDi
email
last changed	2022/06/07 08:00

_id	caadria2021_053
id	caadria2021_053
authors	Rhee, Jinmo and Veloso, Pedro
year	2021
title	Generative Design of Urban Fabrics Using Deep Learning
doi	https://doi.org/10.52842/conf.caadria.2021.1.031
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 31-40
summary	This paper describes the Urban Structure Synthesizer (USS), a research prototype based on deep learning that generates diagrams of morphologically consistent urban fabrics from context-rich urban datasets. This work is part of a larger research on computational analysis of the relationship between urban context and morphology. USS relies on a data collection method that extracts GIS data and converts it to diagrams with context information (Rhee et al., 2019). The resulting dataset with context-rich diagrams is used to train a Wasserstein GAN (WGAN) model, which learns how to synthesize novel urban fabric diagrams with the morphological and contextual qualities present in the dataset. The model is also trained with a random vector in the input, which is later used to enable parametric control and variation for the urban fabric diagram. Finally, the resulting diagrams are translated to 3D geometric entities using computer vision techniques and geometric modeling. The diagrams generated by USS suggest that a learning-based method can be an alternative to methods that rely on experts to build rule sets or parametric models to grasp the morphological qualities of the urban fabric.
keywords	Deep Learning; Urban Fabric; Generative Design; Artificial Intelligence; Urban Morphology
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	ecaadesigradi2019_602
id	ecaadesigradi2019_602
authors	Toulkeridou, Varvara
year	2019
title	Steps towards AI augmented parametric modeling systems for supporting design exploration
doi	https://doi.org/10.52842/conf.ecaade.2019.1.081
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 81-90
summary	Dataflow parametric modeling environments have become popular as exploratory tools due to them allowing the variational exploration of a design by controlling the parameters of its parametric model schema. However, the nature of these systems requires designers to prematurely commit to a structure and hierarchy of geometric relationships, which makes them inflexible when it comes to design exploration that requires topological changes to the parametric modeling graph. This paper is a first step towards augmenting parametric modeling systems via the use of machine learning for assisting the user towards topological exploration. In particular, this paper describes an approach where Long Short-Term Memory recurrent neural networks, trained on a data set of parametric modeling graphs, are used as generative systems for suggesting alternative dataflow graph paths to the parametric model under development.
keywords	design exploration; visual programming; machine learning
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_id	caadria2019_100
id	caadria2019_100
authors	Xu, Jianan and Li, Biao
year	2019
title	Searching on Residential Architecture Design based on Integer Programming
doi	https://doi.org/10.52842/conf.caadria.2019.1.263
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 1, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 263-270
summary	This paper describes an approach to using integer programming algorithms for computer-aided architecture design, taking residential buildings as an example. The research realized the dense arrangement of multiple shape templates in a certain domain of orthogonal grids. In addition, combined with the topological relationship of building functions, a single-story residential building layout is generated. The architectural design problems at different levels are solved by changing the objective function and restrictions in the integer programming algorithm. The algorithm can be expanded and employed to other fields of architecture, and may provide new architectural methodologies.
keywords	Generative Design; Architectural layout planning; Integer Programming; Topology
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	ecaadesigradi2019_034
id	ecaadesigradi2019_034
authors	Chen, Dechen, Luo, Dan, Xu, Weiguo, Luo, Chen, Shen, Liren, Yan, Xia and Wang, Tianjun
year	2019
title	Re-perceive 3D printing with Artificial Intelligence
doi	https://doi.org/10.52842/conf.ecaade.2019.1.443
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 443-450
summary	How can machine learning be combined with intelligent construction, material testing and other related topics to develop a new method of fabrication? This paper presents a set of experiments on the dynamic control of the heat deflection of thermoplastics in searching for a new 3D printing method with the dynamic behaviour of PLA and with a comprehensive workflow utilizing mechanic automation, computer vision, and artificial intelligence. Additionally, this paper will discuss in-depth the performance of different types of neural networks used in the research and conclude with solid data on the potential connection between the structure of neural networks and the dynamic, complex material performance we are attempting to capture.
keywords	3D printing; AI; automation; material; fabrication
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:55

For more results click below: