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 385

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

_id	ecaade2023_44
id	ecaade2023_44
authors	Mayrhofer-Hufnagl, Ingrid and Ennemoser, Benjamin
year	2023
title	From Linear to Manifold Interpolation: Exemplifying the paradigm shift through interpolation
doi	https://doi.org/10.52842/conf.ecaade.2023.2.419
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 2, Graz, 20-22 September 2023, pp. 419–429
summary	The advent of artificial intelligence, specifically neural networks, has marked a significant turning point in the field of computation. During such transformative times, we are often faced with a dearth of appropriate vocabulary, which forces us to rely on existing terms, regardless of their inadequacy. This paper argues that the term “interpolation,” typically used in deep learning (DL), is a prime example of this phenomenon. It is not uncommon for beginners to misunderstand its meaning, as DL pioneer Francois Chollet (2017) has noted. This misreading is especially true in the discipline of architecture, and this study aims to demonstrate how the meaning of “interpolation” has evolved in the second digital turn. We begin by illustrating, using 2D data, the difference between linear interpolation in the context of topological figures and its use in DL algorithms. We then demonstrate how 3DGANs can be employed to interpolate across different topologies in complex 3D space, highlighting the distinction between linear and manifold interpolation. In both 2D and 3D examples, our results indicate that the process does not involve continuous morphing but instead resembles the piecing together of a jigsaw puzzle to form many parts of a larger ambient space. Our study reveals how previous architectural research on DL has employed the term “interpolation” without clarifying the crucial differences from its use in the first digital turn. We demonstrate the new possibilities that manifold interpolation offers for architecture, which extend well beyond parametric variations of the same topology.
keywords	Interpolation, 3D Generative Adversarial Networks, Deep Learning, Hybrid Space
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2017_009
id	ecaade2017_009
authors	Takizawa, Atsushi and Furuta, Airi
year	2017
title	3D Spatial Analysis Method with First-Person Viewpoint by Deep Convolutional Neural Network with Omnidirectional RGB and Depth Images
doi	https://doi.org/10.52842/conf.ecaade.2017.2.693
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 693-702
summary	The fields of architecture and urban planning widely apply spatial analysis based on images. However, many features can influence the spatial conditions, not all of which can be explicitly defined. In this research, we propose a new deep learning framework for extracting spatial features without explicitly specifying them and use these features for spatial analysis and prediction. As a first step, we establish a deep convolution neural network (DCNN) learning problem with omnidirectional images that include depth images as well as ordinary RGB images. We then use these images as explanatory variables in a game engine to predict a subjects' preference regarding a virtual urban space. DCNNs learn the relationship between the evaluation result and the omnidirectional camera images and we confirm the prediction accuracy of the verification data.
keywords	Space evaluation; deep convolutional neural network; omnidirectional image; depth image; Unity; virtual reality
series	eCAADe
email
last changed	2022/06/07 07:56

_id	ecaade2017_041
id	ecaade2017_041
authors	Fukuda, Tomohiro, Kuwamuro, Yasuyuki and Yabuki, Nobuyoshi
year	2017
title	Optical Integrity of Diminished Reality Using Deep Learning
doi	https://doi.org/10.52842/conf.ecaade.2017.1.241
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 241-250
summary	A new method is proposed to improve diminished reality (DR) simulations to allow the demolition and removal of entire buildings in large-scale spaces. Our research goal was to obtain optical integrity by using a scientific and reliable simulation approach. Further, we tackled presumption of the texture of the background sky by applying deep learning. Our approach extracted the background sky using information from the actual sky obtained from a photographed image. This method comprised two steps: (1) detection of the sky area from the image through image segmentation and (2) creation of an image of the sky through image inpainting. The deep convolutional neural networks developed by us to train and predict images were evaluated to be feasible and effective.
keywords	Diminished Reality; Optical Integrity; Deep Learning; Augmented Reality; Landscape assessment
series	eCAADe
email
last changed	2022/06/07 07:50

_id	acadia17_474
id	acadia17_474
authors	Peng, Wenzhe; Zhang, Fan; Nagakura, Takehiko
year	2017
title	Machines’ Perception of Space: Employing 3D Isovist Methods and a Convolutional Neural Network in Architectural Space Classification
doi	https://doi.org/10.52842/conf.acadia.2017.474
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 474- 481
summary	Simple and common architectural elements can be combined to create complex spaces. Different spatial compositions of elements define different spatial boundaries, and each produces a unique local spatial experience to observers inside the space. Therefore an architectural style brings about a distinct spatial experience. While multiple representation methods are practiced in the field of architecture, there lacks a compelling way to capture and identify spatial experiences. Describing an observer’s spatial experiences quantitatively and efficiently is a challenge. In this paper, we propose a method that employs 3D isovist methods and a convolutional neural network (CNN) to achieve recognition of local spatial compositions. The case studies conducted validate that this methodology works well in capturing and identifying local spatial conditions, illustrates the pattern and frequency of their appearance in designs, and indicates peculiar spatial experiences embedded in an architectural style. The case study used small designs by Mies van der Rohe and Aldo van Eyck. The contribution of this paper is threefold. First, it introduces a sampling method based on 3D Isovist that generates a 2D image that can be used to represent a 3D space from a specific observation point. Second, it employs a CNN model to extract features from the sampled images, then classifies their corresponding space. Third, it demonstrates a few case studies where this space classification method is applied to different architectural styles.
keywords	design methods; information processing; AI; machine learning; computer vision; representation
series	ACADIA
email
last changed	2022/06/07 08:00

_id	acadia17_552
id	acadia17_552
authors	Sjoberg, Christian; Beorkrem, Christopher; Ellinger, Jefferson
year	2017
title	Emergent Syntax: Machine Learning for the Curation of Design Solution Space
doi	https://doi.org/10.52842/conf.acadia.2017.552
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 552- 561
summary	The expanding role of computational models in the process of design is producing exponential growth in parameter spaces. As designers, we must create and implement new methods for searching these parameter spaces, considering not only quantitative optimization metrics but also qualitative features. This paper proposes a methodology that leverages the pattern modeling properties of artificial neural networks to capture designers' inexplicit selection criteria and create user-selection-based fitness functions for a genetic solver. Through emulation of learned selection patterns, fitness functions based on trained networks provide a method for qualitative evaluation of designs in the context of a given population. The application of genetic solvers for the generation of new populations based on the trained network selections creates emergent high-density clusters in the parameter space, allowing for the identification of solutions that satisfy the designer’s inexplicit criteria. The results of an initial user study show that even with small numbers of training objects, a search tool with this configuration can begin to emulate the design criteria of the user who trained it.
keywords	design methods; information processing; AI; machine learning; generative system
series	ACADIA
email
last changed	2022/06/07 07:56

_id	ecaade2017_271
id	ecaade2017_271
authors	Narahara, Taro
year	2017
title	Collective Construction Modeling and Machine Learning: Potential for Architectural Design
doi	https://doi.org/10.52842/conf.ecaade.2017.2.341
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 341-348
summary	Recently, there are significant developments in artificial intelligence using advanced machine learning algorithms such as deep neural networks. These new methods can defeat human expert players in strategy-based board games such as Go and video games such as Breakout. This paper suggests a way to incorporate such advanced computing methods into architectural design through introducing a simple conceptual design project inspired by computational interpretations of wasps' collective constructions. At this stage, the paper's intent is not to introduce a practical and fully finished tool directly useful for architectural design. Instead, the paper proposes an example of a program that can potentially become a conceptual framework for incorporating such advanced methods into architectural design.
keywords	Design tools; Stigmergy; Machine learning
series	eCAADe
email
last changed	2022/06/07 07:58

_id	cf2017_567
id	cf2017_567
authors	Kim, Ikhwan; Lee, Injung; Lee, Ji-Hyun
year	2017
title	The Expansion of Virtual Landscape in Digital Games: Classification of Virtual Landscapes Through Five principles
source	Gülen Çagdas, Mine Özkar, Leman F. Gül and Ethem Gürer (Eds.) Future Trajectories of Computation in Design [17th International Conference, CAAD Futures 2017, Proceedings / ISBN 978-975-561-482-3] Istanbul, Turkey, July 12-14, 2017, pp. 567-584.
summary	This research established classification system which contains five principles and variables to classify the types of the virtual landscape in digital games. The principles of the classification are Story, Space Shape, Space and Action Dimension, User Complexity and Interaction Level. With this classification system, our research group found the most representative types of virtual landscape in the digital game market through 1996 to 2016. Although mathematically there can be 288 types of virtual landscape, only 68 types have been used in the game market in recent twenty years. Among the 68 types, we defined 3 types of virtual landscape as the most representative types based on the growth curve and a number of cases. Those three representative types of virtual landscapes are Generating / Face / 3D-3D / Single / Partial, Providing / Chain / 3D-3D / Single / Partial and Providing / Linear / 2D-2D / Single / Partial. With the result, the researchers will be able to establish the virtual landscape design framework for the future research.
keywords	Digital Game, Virtual Landscape, Game Design, Game Classification
series	CAAD Futures
email
last changed	2017/12/01 14:38

_id	ecaade2017_007
id	ecaade2017_007
authors	Wurzer, Gabriel, Lorenz, Wolfgang E., Cerovsek, Tomo and Martens, Bob
year	2017
title	Contrasting Publications in Design and Scientific Research
doi	https://doi.org/10.52842/conf.ecaade.2017.1.385
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 385-394
summary	This paper explores the differences between 'design' and 'science' papers published at eCAADe conferences through use of automatic classification. The latter is conducted using a set of differentiating criteria (e.g. number of figures determines a paper to be either 'design' or 'science') which are calibrated with the help of a manual selection of papers from eCAADe 2015 as ground truth. Results show that we predict 83% of the papers correctly; experiments using data from eCAADe 2014 until eCAADe 2016 furthermore show the stability of our results. However, we are not so much after the development this automatic classification but rather want to characterize the two research cultures of design and science. This is achieved by taking a close look at the differentiating criteria, which can inform tools such as ProceeDings over possible future directions and adaptation needs.
keywords	Differentiation; Design; Science; ProceeDings; CumInCAD
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2021_203
id	ecaade2021_203
authors	Arora, Hardik, Bielski, Jessica, Eisenstadt, Viktor, Langenhan, Christoph, Ziegler, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas
year	2021
title	Consistency Checker - An automatic constraint-based evaluator for housing spatial configurations
doi	https://doi.org/10.52842/conf.ecaade.2021.2.351
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 2, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 351-358
summary	The gradual rise of artificial intelligence (AI) and its increasing visibility among many research disciplines affected Computer-Aided Architectural Design (CAAD). Architectural deep learning (DL) approaches are being developed and published on a regular basis, such as retrieval (Sharma et al. 2017) or design style manipulation (Newton 2019; Silvestre et al. 2016). However, there seems to be no method to evaluate highly constrained spatial configurations for specific architectural domains (such as housing or office buildings) based on basic architectural principles and everyday practices. This paper introduces an automatic constraint-based consistency checker to evaluate the coherency of semantic spatial configurations of housing construction using a small set of design principles to evaluate our DL approaches. The consistency checker informs about the overall performance of a spatial configuration followed by whether it is open/closed and the constraints it didn't satisfy. This paper deals with the relation of spaces processed as mathematically formalized graphs contrary to existing model checking software like Solibri.
keywords	model checking, building information modeling, deep learning, data quality
series	eCAADe
email
last changed	2022/06/07 07:54

_id	ecaade2017_101
id	ecaade2017_101
authors	Ayoub, Mohammed and Wissa, Magdi
year	2017
title	Daylight Optimization - A Parametric Study of Urban Façades Design within Hybrid Settlements in Hot-Desert Climate
doi	https://doi.org/10.52842/conf.ecaade.2017.2.193
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 193-202
summary	Unprecedented growth of hybrid settlements causes deterioration to the indoor environmental quality. Due to their narrow street-networks and fully packed urban fabric, lower floors are subjected to severe overshadow condition, which has adverse effects on the health of the inhabitants. This paper aims to investigate techniques to mitigate the under-lit indoor environment for a group of buildings with variable heights and orientations, with regard to the urban façades parameters. It reflects an intervention in an existing hybrid settlements, within hot-desert climate, to alter façades configurations for daylight optimization, and ultimately recover the lost indoor quality of users in such contexts.
keywords	Daylight Optimization; Urban Façade; Simulation; Hybrid Settlements ; Parametric Design
series	eCAADe
email
last changed	2022/06/07 07:54

_id	ecaade2017_234
id	ecaade2017_234
authors	Benetti, Alberto, Favargiotti, Sara and Ricci, Mos?
year	2017
title	RE.S.U.ME. - REsilient and Smart Urban MEtabolism
doi	https://doi.org/10.52842/conf.ecaade.2017.1.1113
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 1113-1120
summary	New technologies and uncontrolled open-data policies lead public to a new way of approaching the built environment. To enlarge the competences of the professionals that work within the cities, we believe that providing a deep and dynamic knowledge on the heritage and urban built environment is the more effective solution to offer a unique support to the needs. By providing a boosted geographical database with detailed information about the status of each building, we aim to support the professional by providing a neat vision about vacant buildings available citywide. We think this knowledge is an important asset in covering every kind of public requests: from flat to rent to an abandoned building to restore or to drive better investors. The city of Trento will be the pilot project to test these statements.We studied the phenomenon of pushing new constructions rather investing on the reuse of abandoned buildings with the consequences of unsustainable land use. To address the work we adopted a comprehensive approach across the fields of urbanism, ICT engineering and social sciences. We believe that sharing knowledge and know-hows with municipalities, agencies, and citizens is the way to support better market strategies as well as urban transformation policies.
keywords	Information Technology; Urban Metabolism; Re-cycle; Urban Reserves; Policy Decision-Making; Data-driven Analysis
series	eCAADe
email
last changed	2022/06/07 07:54

_id	acadia17_164
id	acadia17_164
authors	Brugnaro, Giulio; Hanna, Sean
year	2017
title	Adaptive Robotic Training Methods for Subtractive Manufacturing
doi	https://doi.org/10.52842/conf.acadia.2017.164
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 164-169
summary	This paper presents the initial developments of a method to train an adaptive robotic system for subtractive manufacturing with timber, based on sensor feedback, machine-learning procedures and material explorations. The methods were evaluated in a series of tests where the trained networks were successfully used to predict fabrication parameters for simple cutting operations with chisels and gouges. The results suggest potential benefits for non-standard fabrication methods and a more effective use of material affordances.
keywords	design methods; information processing; construction; robotics; ai & machine learning; digital craft; manual craft
series	ACADIA
email
last changed	2022/06/07 07:52

_id	acadia20_382
id	acadia20_382
authors	Hosmer, Tyson; Tigas, Panagiotis; Reeves, David; He, Ziming
year	2020
title	Spatial Assembly with Self-Play Reinforcement Learning
doi	https://doi.org/10.52842/conf.acadia.2020.1.382
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. 382-393.
summary	We present a framework to generate intelligent spatial assemblies from sets of digitally encoded spatial parts designed by the architect with embedded principles of prefabrication, assembly awareness, and reconfigurability. The methodology includes a bespoke constraint-solving algorithm for autonomously assembling 3D geometries into larger spatial compositions for the built environment. A series of graph-based analysis methods are applied to each assembly to extract performance metrics related to architectural space-making goals, including structural stability, material density, spatial segmentation, connectivity, and spatial distribution. Together with the constraint-based assembly algorithm and analysis methods, we have integrated a novel application of deep reinforcement (RL) learning for training the models to improve at matching the multiperformance goals established by the user through self-play. RL is applied to improve the selection and sequencing of parts while considering local and global objectives. The user’s design intent is embedded through the design of partial units of 3D space with embedded fabrication principles and their relational constraints over how they connect to each other and the quantifiable goals to drive the distribution of effective features. The methodology has been developed over three years through three case study projects called ArchiGo (2017–2018), NoMAS (2018–2019), and IRSILA (2019-2020). Each demonstrates the potential for buildings with reconfigurable and adaptive life cycles.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	caadria2021_354
id	caadria2021_354
authors	Huang, Chenyu, Gong, Pixin, Ding, Rui, Qu, Shuyu and Yang, Xin
year	2021
title	Comprehensive analysis of the vitality of urban central activities zone based on multi-source data - Case studies of Lujiazui and other sub-districts in Shanghai CAZ
doi	https://doi.org/10.52842/conf.caadria.2021.2.549
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. 549-558
summary	With the use of the concept Central Activities Zone in the Shanghai City Master Plan (2017-2035) to replace the traditional concept of Central Business District, core areas such as Shanghai Lujiazui will be given more connotations in the future construction and development. In the context of todays continuous urbanization and high-speed capital flow, how to identify the development status and vitality characteristics is a prerequisite for creating a high-quality Central Activities Zone. Taking Shanghai Lujiazui sub-district etc. as an example, the vitality value of weekday and weekend as well as 19 indexes including density of functional facilities and building morphology is quantified by obtaining multi-source big data. Meanwhile, the correlation between various indexes and the vitality characteristics of the Central Activities Zone are tried to summarize in this paper. Finally, a neural network regression model is built to bridge the design scheme and vitality values to realize the prediction of the vitality of the Central Activities Zone. The data analysis method proposed in this paper is versatile and efficient, and can be well integrated into the urban big data platform and the City Information Modeling, and provides reliable reference suggestions for the real-time evaluation of future urban construction.
keywords	multi-source big data; Central Activities Zone; Vitality; Lujiazui
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	ijac201715102
id	ijac201715102
authors	Klemmt, Christoph and Klaus Bollinger
year	2017
title	Angiogenesis as a model for the generation of load-bearing networks
source	International Journal of Architectural Computing vol. 15 - no. 1, 18-36
summary	This research suggests an algorithm to generate structural networks based on discreet elements for given locations of support points and point loads. Previous research attempted to achieve this by using a computational growth simulation of venation systems, which form the structure of leaves. However, such networks always start from a single point and therefore cannot be used to form arches or beams. In order to generate networks that are based on two or three support points, an algorithm has been developed that is inspired instead by angiogenesis, the process by which vascular systems develop. The algorithm is based on a spring system with a variable network graph that connects the support points and is pulled upwards and split sideways into multiple veins by a given set of load points. The algorithm has been used to grow architectural structures. Different networks have been tested using finite element analysis and compared with both venation and column-and-beam structures. The angiogenesis networks as well as the venation network are shown to perform well and may be suitable as architectural structural systems.
keywords	Architecture, angiogenesis, structure, network, growth
series	other
type	normal paper
email
last changed	2019/08/02 08:25

_id	ijac201715105
id	ijac201715105
authors	Nahmad Vazque, Alicia and Wassim Jabi
year	2017
title	Investigations in robotic-assisted design: Strategies for symbiotic agencies in material-directed generative design processes
source	International Journal of Architectural Computing vol. 15 - no. 1, 70-86
summary	The research described in this article utilises a phase-changing material, three-dimensional scanning technologies and a six-axis industrial robotic arms as vehicles to enable a novel framework where robotic technology is utilised as an ‘amplifier’ of the design process to realise geometries that derive from both constructive visions and architectural visions through iterative feedback loops between them. The robot in this scenario is not a fabrication tool but the enabler of an environment where the material, robotic and human agencies interact. This article describes the exploratory research for the development of a dialogic design process, sets the framework for its implementation, carries out an evaluation based on designer use and concludes with a set of observations. One of the main findings of this article is that a deeper collaboration that acknowledges the potential of these tools, in a learning-by-design method, can lead to new choreographies for architectural design and fabrication.
keywords	Robotic fabrication, human-machine networks, digital design, agency
series	other
type	normal paper
email
last changed	2019/08/02 08:28

_id	acadia17_572
id	acadia17_572
authors	Sparrman, Bjorn; Matthews, Chris; Kernizan, Schendy; Chadwick, Aran; Thomas, Neil; Laucks, Jared; Tibbits, Skylar
year	2017
title	Large-Scale Lightweight Transformable Structures
doi	https://doi.org/10.52842/conf.acadia.2017.572
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 572- 581
summary	This paper presents strategies for the creation of large-scale transformable structures. In particular we work to leverage material properties and novel construction techniques to induce transformation. We employ flexible biaxial braided geometries to create interconnected large-scale textile surfaces. These braided networks distribute load forces via their internal friction, allowing for uniform structural transformation without the need for complicated mechanical linkages or electromechanical actuation. The ultimate range of these structures has been simulated with computational tools and correlated with physical load testing. We present various applications and configurations of these transforming structures that demonstrate their utility and a new attitude toward the creation of lightweight morphable structures.
keywords	material and construction; simulation & optimization; fabrication; form finding
series	ACADIA
email
last changed	2022/06/07 07:56

_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	ecaade2017_202
id	ecaade2017_202
authors	Sollazzo, Aldo, Trento, Armando and Baseta, Efilena
year	2017
title	Machinic Agency - Implementing aerial robotics and machine learning to map public space
doi	https://doi.org/10.52842/conf.ecaade.2017.2.611
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 611-618
summary	The research presented in this paper is focused on proposing a new digital workflow, involving unmanned aerial vehicles (UAV) and machines learning systems, in order to detect and map citizen's behaviors in the context of public spaces.Novel machinic abilities can be implemented in the understanding of the human context, decoding, through computer visions and machine learning, complex systems into intelligible outputs (Olson, 2008), mapping the relationships of our reality. In this framework, robotic and computational strategies can be implemented in order to offer a new description of public spaces, bringing to light the hidden forces and multiple layers constituting the urban habitat. The presented study focuses on the development of a methodology turning video frames collected from cameras installed on drones into large datasets used to train convolutional networks and enable machines learning systems to detect and map pedestrians in public spaces.
keywords	mapping; drones; machine learning; computer vision; city
series	eCAADe
email
last changed	2022/06/07 07:56

_id	caadria2017_105
id	caadria2017_105
authors	Janssen, Patrick
year	2017
title	Evolutionary Urbanism - Exploring Form-based Codes Using Neuroevolution Algorithms
doi	https://doi.org/10.52842/conf.caadria.2017.303
source	P. Janssen, P. Loh, A. Raonic, M. A. Schnabel (eds.), Protocols, Flows, and Glitches - Proceedings of the 22nd CAADRIA Conference, Xi'an Jiaotong-Liverpool University, Suzhou, China, 5-8 April 2017, pp. 303-312
summary	Form-Based Codes are legal regulations adopted by local government that allow specific urban forms to be achieved. Such codes have a significant impact on the performative potential of the urban environment. This paper explores the possibility of using a neuroevolution algorithm to elucidate the complex relationship between Form-based Codes and their performative potential. More specifically, Compositional Pattern Producing Networks (CPPN) are used to generate parameter fields, which then drive the generation of varied urban models. For evolving the CPPN networks, a neuroevolution algorithm is used, called Neuroevolution of Augmenting Topologies (NEAT). In order to test the feasibility of the proposed approach, an abstract experiment is described in which a population of urban models are evolved, optimising a set of performance criteria related to the vista and location of the residential units.
keywords	Form-based codes; evolutionary design; neural networks; neuroevolution; urban planning
series	CAADRIA
email
last changed	2022/06/07 07:52

For more results click below: