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 3430

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

_id	acadia19_392
id	acadia19_392
authors	Steinfeld, Kyle
year	2019
title	GAN Loci
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
doi	https://doi.org/10.52842/conf.acadia.2019.392
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	ecaade2023_125
id	ecaade2023_125
authors	Baºarir, Lale, Çiçek, Selen and Koç, Mustafa
year	2023
title	Demystifying the patterns of local knowledge: The implicit relation of local music and vernacular architecture
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 1, Graz, 20-22 September 2023, pp. 791–800
doi	https://doi.org/10.52842/conf.ecaade.2023.2.791
summary	As the zeitgeist suggests, the development of novel design output using Artificial Neural Networks (ANNs) is becoming an important milestone in the architectural design discourse. With the recent encounter of the computational design realm with the diffusion models, it becomes even easier to generate 2D and 3D design outputs. Yet, the utilization of machine learning tools within design computing domains is confined to generating or classifying visual and encoded data. However, it is critical to evaluate the untapped potentials of machine learning technologies in terms of illuminating the implicit correlations and links underlying distinct concepts and themes across a wide range of technical domains. With the ongoing research project named “Local Intelligence", we hypothesized that the local knowledge of a certain location might be conceptualized as a distributed network to connect different forms of local knowledge. As the first case of the project, we tried to reinstate a commonality between the local music and vernacular architecture, for which we trained generative adversarial network (GAN) models with the visual spectrograms translated from the audio data of the local songs and images of vernacular architectural instances from a defined geography. The two multi-modal GAN models differ in terms of the inherent convolutional layers and data pairing process. The outcomes demonstrated that both GAN models can learn how to depict vernacular architectural features from the rhythmic pattern of the songs in various patterns. Consequently, the implicit relations between music and architecture in the initial findings come one step closer to being demystified. Thus, the process and generative outcomes of the two models are compared and discussed in terms of the legibility of the architectural features, by taking the original vernacular architectural image dataset as the ground truth.
keywords	Local Intelligence, Machine Learning, Generative Adversarial Network (GAN), Local Music, Vernacular Architecture
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2022_114
id	caadria2022_114
authors	Dong, Zhiyong, Lin, Jinru, Wang, Siqi, Xu, Yijia, Xu, Jiaqi and Liu, Xiao
year	2022
title	Where Will Romance Occur, A New Prediction Method of Urban Love Map through Deep Learning
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 213-222
doi	https://doi.org/10.52842/conf.caadria.2022.1.213
summary	Romance awakens fond memories of the city. Finding out the relationship between romantic scene and urban morphology, and providing a prediction, can potentially facilitate the better urban design and urban life. Taking the Yangtze River Delta region of China as an example, this study aims to predict the distribution of romantic locations using deep learning based on multi-source data. Specifically, we use web crawlers to extract romance-related messages and geographic locations from social media platforms, and visualize them as romance heatmap. The urban environment and building features associated with romantic information are identified by Pearson correlation analysis and annotated in the city map. Then, both city labelled maps and romance heatmaps are fed into a Generative Adversarial Networks (GAN) as the training dataset to achieve final romance distribution predictions across regions for other cities. The ideal prediction results highlight the ability of deep learning techniques to quantify experience-based decision-making strategies that can be used in further research on urban design.
keywords	Romance Heatmap, Generative Adversarial Networks, Deep Learning, Big Data Analysis, Correlation Analysis, SDG 11
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	ijac202321208
id	ijac202321208
authors	Ennemoser, Benjamin; Mayrhofer-Hufnagl, Ingrid
year	2023
title	Design across multi-scale datasets by developing a novel approach to 3DGANs
source	International Journal of Architectural Computing 2023, Vol. 21 - no. 2, 358–373
summary	The development of Generative Adversarial Networks (GANs) has accelerated the research of Artificial Intelligence (AI) in architecture as a generative tool. However, since their initial invention, many versions have been developed that only focus on 2D image datasets for training and images as output. The current state of 3DGAN research has yielded promising results. However, these contributions focus primarily on building mass, extrusion of 2D plans, or the overall shape of objects. In comparison, our newly developed 3DGAN approach, using fully spatial building datasets, demonstrates that unprecedented interconnections across different scales are possible resulting in unconventional spatial configurations. Unlike a traditional design process, based on analyzing only a few precedents (typology) according to the task, by collaborating with the machine we can draw on a significantly wider variety of buildings across multiple typologies. In addition, the dataset was extended beyond the scale of complete buildings and involved building components that define space. Thus, our results achieve a high spatial diversity. A detailed analysis of the results also revealed new hybrid architectural elements illustrating that the machine continued the interconnections of scale since elements were not explicitly part of the dataset, becoming a true design collaborator.
keywords	3D Generative adversarial networks, architectural design, Spatial Interpolations
series	journal
last changed	2024/04/17 14:30

_id	caadria2021_043
id	caadria2021_043
authors	Ng, Provides
year	2021
title	21E8: Coupling Generative Adversarial Neural Networks (GANS) with Blockchain Applications in Building Information Modelling (BIM) Systems
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 111-120
doi	https://doi.org/10.52842/conf.caadria.2021.2.111
summary	The ability of GANs to synthesize large sets of data is ideal for coupling with BIM to formulate a multi-access system that enables users to search and browse through a spectrum of articulated options, all personalised to design specificity - an 'Architecture Machine'. Nonetheless, due to challenges in proprietary incompatibility, BIM systems currently lack a secured yet transparent way of freely integrating with crowdsourced efforts. This research proposes to employ blockchain as a means to couple GANs and BIM, with e8 networking topology to facilitate communication and distribution. It consists of a literature review and a design research that proposes a tech stack design and UML (unified modeling language) use cases, and presents preliminary design results obtained using GANs and e8.
keywords	21e8; GANs; Blockchain; BIM; Architecture Machine
series	CAADRIA
email
last changed	2022/06/07 07:58

_id	cdrf2019_103
id	cdrf2019_103
authors	Runjia Tian
year	2020
title	Suggestive Site Planning with Conditional GAN and Urban GIS Data
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_10
summary	In architecture, landscape architecture, and urban design, site planning refers to the organizational process of site layout. A fundamental step for site planning is the design of building layout across the site. This process is hard to automate due to its multi-modal nature: it takes multiple constraints such as street block shape, orientation, program, density, and plantation. The paper proposes a prototypical and extensive framework to generate building footprints as masterplan references for architects, landscape architects, and urban designers by learning from the existing built environment with Artificial Neural Networks. Pix2PixHD Conditional Generative Adversarial Neural Network is used to learn the mapping from a site boundary geometry represented with a pixelized image to that of an image containing building footprint color-coded to various programs. A dataset containing necessary information is collected from open source GIS (Geographic Information System) portals from the city of Boston, wrangled with geospatial analysis libraries in python, trained with the TensorFlow framework. The result is visualized in Rhinoceros and Grasshopper, for generating site plans interactively.
series	cdrf
email
last changed	2022/09/29 07:51

_id	ecaade2020_007
id	ecaade2020_007
authors	Yu, De
year	2020
title	Reprogramming Urban Block by Machine Creativity - How to use neural networks as generative tools to design space
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 1, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 249-258
doi	https://doi.org/10.52842/conf.ecaade.2020.1.249
summary	The democratization of design requires balancing all sorts of factors in space design. However, the traditional way to organize spatial relationships cannot deal with such complex design objectives. Can one find another form of creativity rather the human brain to design space? As Margaret Boden mentioned, "computers and creativity make interesting partners with respect to two different projects." This paper addresses whether machine creativity in the form of neural networks could be considered as a powerful generative tool to reprogram urban block in order to meet multi-users' needs. It tested this theory in a specific block model called Agri-tecture, a new architectural form combing farming with the urban built environment. Specifically, the machine empowered by Generative Adversarial Network designed spatial layouts based on learning the existing cases. Nevertheless, since the machine can hardly avoid errors, architects need to intervene and verify the machine's work. Thus, a synergy between human creativity and machine creativity is called for.
keywords	machine creativity; Generative Adversarial Network; spatial layout; creativity combination; Agri-tecture
series	eCAADe
email
last changed	2022/06/07 07:57

_id	caadria2020_234
id	caadria2020_234
authors	Zhang, Hang and Blasetti, Ezio
year	2020
title	3D Architectural Form Style Transfer through Machine Learning
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 2, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 659-668
doi	https://doi.org/10.52842/conf.caadria.2020.2.659
summary	In recent years, a tremendous amount of progress is being made in the field of machine learning, but it is still very hard to directly apply 3D Machine Learning on the architectural design due to the practical constraints on model resolution and training time. Based on the past several years' development of GAN (Generative Adversarial Network), also the method of spatial sequence rules, the authors mainly introduces 3D architectural form style transfer on 2 levels of scale (overall and detailed) through multiple methods of machine learning algorithms which are trained with 2 types of 2D training data set (serial stack and multi-view) at a relatively decent resolution. By exploring how styles interact and influence the original content in neural networks on the 2D level, it is possible for designers to manually control the expected output of 2D images, result in creating the new style 3D architectural model with a clear designing approach.
keywords	3D; Form Finding; Style Transfer; Machine Learning; Architectural Design
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	ascaad2016_007
id	ascaad2016_007
authors	Elsayed, Mohamed; Osama Tolba and Ahmed Elantably
year	2016
title	Architectural Space Planning Using Parametric Modeling - Egyptian National Housing Project
source	Parametricism Vs. Materialism: Evolution of Digital Technologies for Development [8th ASCAAD Conference Proceedings ISBN 978-0-9955691-0-2] London (United Kingdom) 7-8 November 2016, pp. 45-54
summary	The Egyptian government resorts to prototype housing for low-income citizens to meet the growing demand of the housing market. The problem with the prototype is that it does not meet specific needs. Consequently, users make modifications to the prototype without professional intervention because of the high cost. This paper discusses an automatic multi-stories space planning tool that helps low-income citizens to modify their prototype housing provided by the government. Social, spatial and functional design aspects were set in the original design prototype by an architect. The proposed tool simulates spaces spatial locations in the original design by simulating the analogy of mechanical springs through an interactive simulation of a parametric model. The authors developed the used algorithm in the generative design tool Grasshopper and the live physics engine Kangaroo, both working within the Rhino 3D environment. The algorithm has two versions, one-floor level version and two floors version targeting the wealthier users. Results indicate that this tool integrates with the exploratory nature of the design process even for non-professional users. The authors designed a tool that will help the users to study the effect of the desired modifications against the originally provided prototype, it also makes it easier for users to express their requirements to a professional designer, conserving time and financial cost.
series	ASCAAD
email
last changed	2017/05/25 13:13

_id	ecaade2016_224
id	ecaade2016_224
authors	Gerber, David and Pantazis, Evangelos
year	2016
title	Design Exploring Complexity in Architectural Shells - Interactive form finding of reciprocal frames through a multi-agent system
source	Herneoja, Aulikki; Toni Österlund and Piia Markkanen (eds.), Complexity & Simplicity - Proceedings of the 34th eCAADe Conference - Volume 1, University of Oulu, Oulu, Finland, 22-26 August 2016, pp. 455-464
doi	https://doi.org/10.52842/conf.ecaade.2016.1.455
wos	WOS:000402063700050
summary	This paper presents an integrated workflow for interactive design of shell structures, which couples structural and environmental analysis through a multi-agent systems (MAS) for design. The work lies at the intersection of architecture, engineering and computer science research, incorporating generative design with analytical techniques. A brief review on architectural shell structures and the structural logic of reciprocal frames is described. Through the morphological study of reciprocal frames locally we seek to inform the behavior of a MAS, which integrates form-finding techniques, with daylight factor analysis (DFA) and finite element analysis (FEA) on a global configuration. An experimental design is developed in order to explore the solution space of large span free form shells with varying topologies and boundary conditions, as well as identify the relationships between local design parameters of the reciprocal frames (i.e. number of elements, profile) and the analyses (i.e. stress distribution, solar radiation) for enabling the generation of different global design alternatives. The research improves upon design decision-making latency and certainty through harnessing geometric complexity and structural form finding for early stage design. Additionally, the research improves upon design outcomes by establishing a feedback loop between design generation, analysis and performance.
keywords	Generative design; computational design; multi-agent systems; shell structures; reciprocal frames; form finding; parametric design
series	eCAADe
email
last changed	2022/06/07 07:51

_id	acadia16_12
id	acadia16_12
authors	Gerber, David Jason; Pantazis, Evangelos
year	2016
title	A Multi-Agent System for Facade Design: A design methodology for Design Exploration, Analysis and Simulated Robotic Fabrication
source	ACADIA // 2016: POSTHUMAN FRONTIERS: Data, Designers, and Cognitive Machines [Proceedings of the 36th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-77095-5] Ann Arbor 27-29 October, 2016, pp. 12-23
doi	https://doi.org/10.52842/conf.acadia.2016.012
summary	For contemporary design practices, there still remains a disconnect between design tools used for early stage design exploration and performance analysis, and those used for fabrication and construction of complex tectonic architectural systems. The research brings forward downstream fabrication constraints into the up-stream design exploration and design decision making. This paper addresses the issues of developing an integrated digital design work-flow and details a research framework for the incorporation of environmental performance into a robotic fabrication for early stage design exploration and generation of intricate and complex alternative façade designs. The method allows the user to import a design surface, define design parameters, set a number of environmental performance objectives, and then simulate and select a robotic construction strategy. Based on these inputs, design alternatives are generated and evaluated in terms of their performance criteria in consideration of their robotically simulated constructability. In order to validate the proposed framework, an experimental case study of office building façade designs that are generatively created from a multi-agent system for design methodology is design explored and evaluated. Initial results define a heuristic function for improving simulated robotic constructability and illustrate the functionality of our prototype. Project limitations and future research steps are then discussed.
keywords	generative design, multi-objective design optimization, robotic fabrication, simulation, design performance, design decision making
series	ACADIA
type	paper
email
last changed	2022/06/07 07:51

_id	acadia16_318
id	acadia16_318
authors	Huang, Alvin
year	2016
title	From Bones to Bricks: Design the 3D Printed Durotaxis Chair and La Burbuja Lamp
source	ACADIA // 2016: POSTHUMAN FRONTIERS: Data, Designers, and Cognitive Machines [Proceedings of the 36th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-77095-5] Ann Arbor 27-29 October, 2016, pp. 318-325
doi	https://doi.org/10.52842/conf.acadia.2016.318
summary	Drawing inspiration from the variable density structures of bones and the self-supported cantilvers of corbelled brick arches, the Durotaxis Chair and the La Burbuja lamp explore a material-based design process by responding to the challenge of designing a 3D print, rather than 3D printing a design. As such, the fabrication method and materiality of 3D printing define the generative design constraints that inform the geometry of each. Both projects are seen as experiments in the design of 3D printed three-dimensional space packing structures that have been designed specifically for the machines by which they are manufactured. The geometry of each project has been carefully calibrated to capitalize on a selection of specific design opportunities enabled by the capabilities and constraints of additive manufacturing. The Durotaxis Chair is a half-scale prototype of a fully 3D printed multi-material rocking chair that is defined by a densely packed, variable density three-dimensional wire mesh that gradates in size, scale, density, color, and rigidity. Inspired by the variable density structure of bones, the design utilizes principal stress analysis, asymptotic stability, and ergonomics to drive the logics of the various gradient conditions. The La Burbuja Lamp is a full scale prototype for a zero-waste fully 3D printed pendant lamp. The geometric articulation of the project is defined by a cellular 3D space packing structure that is constrained to the angles of repose and back-spans required to produce un-supported 3D printing.
keywords	parametic design, digital fabrication, structural analysis, additive manufacturing, 3d printing
series	ACADIA
type	paper
email
last changed	2022/06/07 07:50

_id	ecaade2016_217
id	ecaade2016_217
authors	Klerk, Rui de and Beir?o, José
year	2016
title	Ontologies and Shape Grammars - A Relational Overview Towards Semantic Design Systems
source	Herneoja, Aulikki; Toni Österlund and Piia Markkanen (eds.), Complexity & Simplicity - Proceedings of the 34th eCAADe Conference - Volume 2, University of Oulu, Oulu, Finland, 22-26 August 2016, pp. 305-314
doi	https://doi.org/10.52842/conf.ecaade.2016.2.305
wos	WOS:000402064400030
summary	This paper provides an overview on the relation between computational ontologies and shape grammars regarding the development and production of multi-purpose Semantic Design Systems. The objective of the author's ongoing research is to assist the creation of generative design systems, applicable to design processes in general. Shape grammar rules and ontologies in these systems will be focusing on abstract, generic rules and generic descriptions. When combined through contextually specified relations, these assume semantic expressions and should be able to produce meaningful results.We collect here a short state of the art of the research developed in the fields of architecture, urbanism and computer science in the past ten years regarding the use of knowledge bases (ontologies) combined with generative design systems (with a particular focus on shape grammars). We expect to provide both insight about architectural and urban typologies and the production of meaningful designs using automated generative design systems.
keywords	Ontologies; Shape Grammars; Semantic Design Systems; Architectural Design; Urban Planning
series	eCAADe
email
last changed	2022/06/07 07:51

_id	acadia16_174
id	acadia16_174
authors	Moorman, Andrew; Liu, Jingyang; Sabin, Jenny E.
year	2016
title	RoboSense: Context-Dependent Robotic Design Protocols and Tools
source	ACADIA // 2016: POSTHUMAN FRONTIERS: Data, Designers, and Cognitive Machines [Proceedings of the 36th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-77095-5] Ann Arbor 27-29 October, 2016, pp. 174-183
doi	https://doi.org/10.52842/conf.acadia.2016.174
summary	While nonlinear concepts are widely applied in analysis and generative design in architecture, they have not yet convincingly translated into the material realm of fabrication and construction. As the gap between digital design model, shop drawing, and fabricated result continues to diminish, we seek to learn from fabrication models and natural systems that do not separate code, geometry, pattern, material compliance, communication, and form, but rather operate within dynamic loops of feedback, reciprocity, and generative fabrication. Three distinct, but connected problems: 1) Robotic ink drawing; 2) Robotic wine pouring and object detection; and 3) Dynamically Adjusted Extrusion; were addressed to develop a toolkit including software, custom digital design tools, and hardware for robotic fabrication and user interaction in cyber-physical contexts. Our primary aim is to simplify and consolidate the multiple platforms necessary to construct feedback networks for robotic fabrication into a central and intuitive programming environment for both the advanced to novice user. Our experimentation in prototyping feedback networks for use with robotics in design practice suggests that the application of this knowledge often follows a remarkably consistent profile. By exploiting these redundancies, we developed a support toolkit of data structures and routines that provide simple integrated software for the user-friendly programming of commonly used roles and functionalities in dynamic robotic fabrication, thus promoting a methodology of feedback-oriented design processes.
keywords	online programming, cyber-physical systems, computational design, robotic fabrication, human-robot interaction
series	ACADIA
type	paper
email
last changed	2022/06/07 07:58

_id	acadia16_140
id	acadia16_140
authors	Nejur, Andrei; Steinfeld, Kyle
year	2016
title	Ivy: Bringing a Weighted-Mesh Representations to Bear on Generative Architectural Design Applications
source	ACADIA // 2016: POSTHUMAN FRONTIERS: Data, Designers, and Cognitive Machines [Proceedings of the 36th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-77095-5] Ann Arbor 27-29 October, 2016, pp. 140-151
doi	https://doi.org/10.52842/conf.acadia.2016.140
summary	Mesh segmentation has become an important and well-researched topic in computational geometry in recent years (Agathos et al. 2008). As a result, a number of new approaches have been developed that have led to innovations in a diverse set of problems in computer graphics (CG) (Sharmir 2008). Specifically, a range of effective methods for the division of a mesh have recently been proposed, including by K-means (Shlafman et al. 2002), graph cuts (Golovinskiy and Funkhouser 2008; Katz and Tal 2003), hierarchical clustering (Garland et al. 2001; Gelfand and Guibas 2004; Golovinskiy and Funkhouser 2008), primitive fitting (Athene et al. 2004), random walks (Lai et al.), core extraction (Katz et al.) tubular multi-scale analysis (Mortara et al. 2004), spectral clustering (Liu and Zhang 2004), and critical point analysis (Lin et al. 20070, all of which depend upon a weighted graph representation, typically the dual of a given mesh (Sharmir 2008). While these approaches have been proven effective within the narrowly defined domains of application for which they have been developed (Chen 2009), they have not been brought to bear on wider classes of problems in fields outside of CG, specifically on problems relevant to generative architectural design. Given the widespread use of meshes and the utility of segmentation in GAD, by surveying the relevant and recently matured approaches to mesh segmentation in CG that share a common representation of the mesh dual, this paper identifies and takes steps to address a heretofore unrealized transfer of technology that would resolve a missed opportunity for both subject areas. Meshes are often employed by architectural designers for purposes that are distinct from and present a unique set of requirements in relation to similar applications that have enjoyed more focused study in computer science. This paper presents a survey of similar applications, including thin-sheet fabrication (Mitani and Suzuki 2004), rendering optimization (Garland et al. 2001), 3D mesh compression (Taubin et al. 1998), morphin (Shapira et al. 2008) and mesh simplification (Kalvin and Taylor 1996), and distinguish the requirements of these applications from those presented by GAD, including non-refinement in advance of the constraining of mesh geometry to planar-quad faces, and the ability to address a diversity of mesh features that may or may not be preserved. Following this survey of existing approaches and unmet needs, the authors assert that if a generalized framework for working with graph representations of meshes is developed, allowing for the interactive adjustment of edge weights, then the recent developments in mesh segmentation may be better brought to bear on GAD problems. This paper presents work toward the development of just such a framework, implemented as a plug-in for the visual programming environment Grasshopper.
keywords	tool-building, design simulation, fabrication, computation, megalith
series	ACADIA
type	paper
email
last changed	2022/06/07 07:58

_id	acadia20_668
id	acadia20_668
authors	Pasquero, Claudia; Poletto, Marco
year	2020
title	Deep Green
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 668-677.
doi	https://doi.org/10.52842/conf.acadia.2020.1.668
summary	Ubiquitous computing enables us to decipher the biosphere’s anthropogenic dimension, what we call the Urbansphere (Pasquero and Poletto 2020). This machinic perspective unveils a new postanthropocentric reality, where the impact of artificial systems on the natural biosphere is indeed global, but their agency is no longer entirely human. This paper explores a protocol to design the Urbansphere, or what we may call the urbanization of the nonhuman, titled DeepGreen. With the development of DeepGreen, we are testing the potential to bring the interdependence of digital and biological intelligence to the core of architectural and urban design research. This is achieved by developing a new biocomputational design workflow that enables the pairing of what is algorithmically drawn with what is biologically grown (Pasquero and Poletto 2016). In other words, and more in detail, the paper will illustrate how generative adversarial network (GAN) algorithms (Radford, Metz, and Soumith 2015) can be trained to “behave” like a Physarum polycephalum, a unicellular organism endowed with surprising computational abilities and self-organizing behaviors that have made it popular among scientist and engineers alike (Adamatzky 2010) (Fig. 1). The trained GAN_Physarum is deployed as an urban design technique to test the potential of polycephalum intelligence in solving problems of urban remetabolization and in computing scenarios of urban morphogenesis within a nonhuman conceptual framework.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	acadia16_236
id	acadia16_236
authors	Pineda, Sergio; Arora, Mallika; Williams, P. Andrew; Kariuki, Benson M.; Harris, Kenneth D. M.
year	2016
title	The Grammar of Crystallographic Expression
source	ACADIA // 2016: POSTHUMAN FRONTIERS: Data, Designers, and Cognitive Machines [Proceedings of the 36th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-77095-5] Ann Arbor 27-29 October, 2016, pp. 236-243
doi	https://doi.org/10.52842/conf.acadia.2016.236
summary	This paper stems from a research collaboration which brings together two disciplines at different ends of the scale spectrum: crystallography and architecture. The science of crystallography demonstrates that the properties of crystalline materials are a function of atomic/molecular interactions and arrangements at the atomic level—i.e., functions of the form and structure of the material. Some of these nano-geometries are frameworks with special characteristics, such as uni-directional porosity, multi-directional porosity, and varied combinations of flexibility and strength. This paper posits that the symmetry operations implicit in these materials can be regarded as a spatial grammar in the design of objects, spaces, and environments. The aim is to allow designers and architects to access the wealth of structural information that is now accumulated in crystallographic databases as well as the spatial symmetry logics utilized in crystallography to describe molecular arrangements. To enable this process, a bespoke software application has been developed as a tool-path to allow for interoperability between crystallographic datasets and CAD-based modelling systems. The application embeds the descriptive logic and generative principles of crystallographic symmetry. Using this software, the project, inter alia, produces results related to a class of geometrical surfaces called Triply Periodic Minimal (TPM) surfaces. In addition to digital iterations, a physical prototype of one such surface called the gyroid was constructed to test potential applications in design. The paper describes the development of these results and the conclusions derived from the first stage of user testing.
keywords	interdisciplinarity, physical prototyping, triply periodic minimal surfaces, computational workflow, bespoke software, crystallographic space groups, nano-scale symmetry, nano-scale periodicity, molecular geometry, crystallographic expression
series	ACADIA
type	paper
email
last changed	2022/06/07 08:00

_id	caadria2016_209
id	caadria2016_209
authors	Wang, Likai; Zilong Tan and Guohua Ji
year	2016
title	Toward the wind-related building performative design
source	Living Systems and Micro-Utopias: Towards Continuous Designing, Proceedings of the 21st International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2016) / Melbourne 30 March–2 April 2016, pp. 109-218
doi	https://doi.org/10.52842/conf.caadria.2016.109
summary	The integration of optimization algorithms and building performance simulation tools make it possible to carry out performa- tive design or performance-driven design, which aims to guide the de- sign synthesis process of the simulation results to continuously im- prove the design. However, the associated research work of wind- related building performance is still deficient, resulting from lack of applicable interface and the time consumption. Meanwhile, in the in- dustrial design realm, the aero-dynamics or fluid-dynamics behaviour of the production under development has been vastly analysed and op- timized based on the multi-discipline optimization (MDO) techniques. Owing to offering numerous built-in interface and integrated optimi- zation algorithm, MDO application software has begun to be used in building optimization design with the complex relationship between various objectives. With the advantage of MDO tools and aimed to provide an efficient optimization approach from the perspective of ar- chitect, this paper proposes a wind-related building performance op- timization design system integrating Rhinoceros and Fluent based on iSIGHT - a MDO application software. In addition, the lighting per- formance is considered in this research as well for implementing the multi-objective optimization. Two case studies of tall building optimi- zation design based on varied generative approaches are introduced to investigate the effect and efficiency of this system.
keywords	Performative design; wind-related building performance; MDO; parametric generating design
series	CAADRIA
email
last changed	2022/06/07 07:58

_id	ascaad2016_017
id	ascaad2016_017
authors	Yazici, Sevil; David J. Gerber
year	2016
title	Prototyping Generative Architecture - Experiments on Multi-Agent Systems, Environmental Performance and 3D Printing
source	Parametricism Vs. Materialism: Evolution of Digital Technologies for Development [8th ASCAAD Conference Proceedings ISBN 978-0-9955691-0-2] London (United Kingdom) 7-8 November 2016, pp. 145-154
summary	Computational design was developed to solve complex problems in architecture and to enable the establishment of systems with complex properties in a holistic manner. With the enhanced capabilities of computational design, there are possibilities to develop integrated approaches to adapt to multi-faceted design problems. Swarm-based multi-agent systems (MAS) are already used as generative bottom-up methods in various design operations, including form-finding and optimization. This study presents a systematic approach, in which multi-agent systems are informed by the environmental performance assessment data where the output is directly linked to the 3D printing process. The intent is to increase efficiency within the design and prototyping process by integrating performance and fabrication into the early stages of the design process. The proposed method has been applied as a case study to a diverse group of students and professionals. The results have proven that applying this systematic approach enabled the designers to achieve highly sophisticated, formal and organizational outputs, with enhanced spatial and geometric qualities.
series	ASCAAD
email
last changed	2017/05/25 13:31

_id	acadia20_238
id	acadia20_238
authors	Zhang, Hang
year	2020
title	Text-to-Form
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 238-247.
doi	https://doi.org/10.52842/conf.acadia.2020.1.238
summary	Traditionally, architects express their thoughts on the design of 3D architectural forms via perspective renderings and standardized 2D drawings. However, as architectural design is always multidimensional and intricate, it is difficult to make others understand the design intention, concrete form, and even spatial layout through simple language descriptions. Benefiting from the fast development of machine learning, especially natural language processing and convolutional neural networks, this paper proposes a Linguistics-based Architectural Form Generative Model (LAFGM) that could be trained to make 3D architectural form predictions based simply on language input. Several related works exist that focus on learning text-to-image generation, while others have taken a further step by generating simple shapes from the descriptions. However, the text parsing and output of these works still remain either at the 2D stage or confined to a single geometry. On the basis of these works, this paper used both Stanford Scene Graph Parser (Sebastian et al. 2015) and graph convolutional networks (Kipf and Welling 2016) to compile the analytic semantic structure for the input texts, then generated the 3D architectural form expressed by the language descriptions, which is also aided by several optimization algorithms. To a certain extent, the training results approached the 3D form intended in the textual description, not only indicating the tremendous potential of LAFGM from linguistic input to 3D architectural form, but also innovating design expression and communication regarding 3D spatial information.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

For more results click below: