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 79

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

_id	caadria2018_056
id	caadria2018_056
authors	Chirkin, Artem, Pishniy, Maxim and Sender, Arina
year	2018
title	Generilized Visibility-Based Design Evaluation Using GPU
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 483-492
doi	https://doi.org/10.52842/conf.caadria.2018.2.483
summary	Visibility plays an important role in perception and use of an urban design, and thus often becomes a target of design analysis. This work presents a fast method of evaluating various visibility-based design characteristics, such as isovists or insolation exploiting the GPU rendering pipeline and compute shaders. The proposed method employs a two-stage algorithm on each point of interest. First, it projects the visible space around a vantage point onto an equirectangular map. Second, it folds the map using a flexibly defined function into a single value that is associated with the vantage point. Being executed on a grid of points in a 3D scene, it can be visualized as a heat map or utilized by another algorithm for further design analysis. The developed system provides nearly real-time analysis tools for an early-stage design process to a broad audience via web services.
keywords	design analysis; design evaluation; GPU; isovist; insolation
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	ecaade2018_145
id	ecaade2018_145
authors	Fukuda, Tomohiro, Zhu, Yuehan and Yabuki, Nobuyoshi
year	2018
title	Point Cloud Stream on Spatial Mixed Reality - Toward Telepresence in Architectural Field
source	Kepczynska-Walczak, A, Bialkowski, S (eds.), Computing for a better tomorrow - Proceedings of the 36th eCAADe Conference - Volume 2, Lodz University of Technology, Lodz, Poland, 19-21 September 2018, pp. 727-734
doi	https://doi.org/10.52842/conf.ecaade.2018.2.727
summary	In remote meetings that involve the study of buildings and cities, sharing three-dimensional (3D) virtual spatial of buildings and cities is just as necessary as sharing the appearances and voices of meeting participants. Because of this, system development and pilot projects have attempted to share 3D virtual models via the internet in real-time but is still insufficient compared with face-to-face meeting. Therefore, this research explores the applicability of a spatial mixed reality (MR) system that displays point cloud streams to realize 3D remote meeting in architecture and urban fields. MR is a new technology that enables 3D presentations of various information, combining the physical and virtual worlds. One MR method is telepresence, which is expected to give people a way to communicate remotely as if face to face in a realistic way. We first developed a MR system named PcsMR (Point cloud stream on mixed reality) to display point cloud streams. The PcsMR system's operation consists of generating and transferring a point cloud stream and then rendering a point cloud stream using MR. The PcsMR acquired the point cloud stream in real-time using Kinect for Windows v2 and transferred it to Microsoft HoloLens, which uses optical see-through MR. Then we constructed two prototypes based on PcsMR and carried out pilot projects. Through observing the experiments, application possibilities for architecture and urban fields are found in meetings and communications that share real-time 3D objects and include the movement of remote participants and objects. The proposed method was evaluated feasible and effective.
keywords	Telepresence; Mixed reality; Point cloud stream; Remote meeting; Real time
series	eCAADe
email
last changed	2022/06/07 07:50

_id	acadia18_366
id	acadia18_366
authors	Baseta, Efilena; Bollinger, Klaus
year	2018
title	Construction System for Reversible Self-Formation of Grid Shells. Correspondence between physical and digital form
source	ACADIA // 2018: Recalibration. On imprecisionand infidelity. [Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-17729-7] Mexico City, Mexico 18-20 October, 2018, pp. 366-375
doi	https://doi.org/10.52842/conf.acadia.2018.366
summary	This paper presents a construction system which offers an efficient materialization method for double-curved gridshells. This results in an active-bending system of controlled deflections. The latter system embeds its construction manual into the geometry of its components. Thus it can be used as a self-formation process. The two presented gridshell structures are composed of geometry-induced, variable stiffness elements. The latter elements are able to form programmed shapes passively when gravitational loads are applied. Each element consists of two layers and a slip zone between them. The slip allows the element to be flexible when it is straight and increasingly stiffer while its curvature increases. The amplitude of the slip defines the final deformation of the element. As a result, non-uniform deformations can be obtained with uniform cross sections and loads. When the latter elements are used in grid configurations, self-formation of initially planar surfaces emerges. The presented system eliminates the need for electromechanical equipment since it relies on material properties and hierarchical geometrical configurations. Wood, as a flexible and strong material, has been used for the construction of the prototypes. The fabrication of the timber laths has been done via CNC industrial milling processes. The comparison between the initial digital design and the resulting geometry of the physical prototypes is reviewed in this paper. The aim is to inform the design and fabrication process with performance data extracted from the prototypes. Finally, the scalability of the system shows its potential for large-scale applications, such as transformable structures.
keywords	full paper, material & adaptive systems, flexible structures, digital fabrication, self-formation
series	ACADIA
type	paper
email
last changed	2022/06/07 07:54

_id	ecaade2018_162
id	ecaade2018_162
authors	Alkadri, Miktha, Turrin, Michela and Sariyildiz, Sevil
year	2018
title	Toward an Environmental Database - Exploring the material properties from the point cloud data of the existing environment
source	Kepczynska-Walczak, A, Bialkowski, S (eds.), Computing for a better tomorrow - Proceedings of the 36th eCAADe Conference - Volume 2, Lodz University of Technology, Lodz, Poland, 19-21 September 2018, pp. 263-270
doi	https://doi.org/10.52842/conf.ecaade.2018.2.263
summary	The utilization of point cloud as a 3D laser scanning product has reached across multi-disciplines in terms of data processing, data visualization, and data analysis. This study particularly investigates further the use of typical attributes of raw point cloud data consisting of XYZ (position information), RGB (colour information) and I (intensity information). By exploring the optical and thermal properties of the given point cloud data, it aims at compensating the material and texture information that is usually remained behind by architects during the conceptual design stage. Calculation of the albedo, emissivity and the reflectance values from the existing context specifically direct the architects to predict the type of materials for the proposed design in order to keep the balance of the surrounding Urban Heat Island (UHI) effect. Therefore, architects can have a comprehensive analysis of the existing context to deal with the microclimate condition before a design decision phase.
keywords	point cloud data; material characteristics; albedo; emissivity; reflectance value
series	eCAADe
email
last changed	2022/06/07 07:54

_id	sigradi2018_1580
id	sigradi2018_1580
authors	Bomfim de Araujo, Alana; Groetelaars , Natalie Johanna; Leão de Amorim, Arivaldo
year	2018
title	Use of Dense Stereo Matching for Existing Building Documentation: Comparative Analysis of Tools
source	SIGraDi 2018 [Proceedings of the 22nd Conference of the Iberoamerican Society of Digital Graphics - ISSN: 2318-6968] Brazil, São Carlos 7 - 9 November 2018, pp. 874-879
summary	This paper presents a comparative study of Dense Stereo Matching (DSM) tools to generate point cloud from digital photogrammetric restitution. The capability of four different state-of-the-art software systems as Photoscan (Agisoft), 3DF Zephyr Free (3Dflow), Remake (Autodesk) and Recap 360 (Autodesk) is examined to document a historical object. The main aspects compared are: processing time, export file formats, file size, quality and density of point clouds obtained from tools standard parameters. From the literature review, the analysis and the experiments, it is possible to evaluate the potential of DSM technique for the existing building documentation.
keywords	Dense Stereo Matching (DSM); Digital photogrammetry; DSM tools; Point cloud; Triangular irregular network (TIN)
series	SIGRADI
email
last changed	2021/03/28 19:58

_id	sigradi2018_1473
id	sigradi2018_1473
authors	Kimi Cogima, Camila; V. V. de Paiva, Pedro; Dezen-Kempter, Eloisa; G. De Carvalho, Marco Antonio
year	2018
title	Digital scanning and BIM modeling for modern architecture preservation: the Oscar Niemeyer’s Church of Saint Francis of Assisi
source	SIGraDi 2018 [Proceedings of the 22nd Conference of the Iberoamerican Society of Digital Graphics - ISSN: 2318-6968] Brazil, São Carlos 7 - 9 November 2018, pp. 457-462
summary	The Building Information Modelling (BIM) technology enabled improvement in the design, construction and maintenance stages highly. In the field of existing buildings, including historical assets, this technology has not yet had the same impact. This paper presents a methodology to create an intelligent digital model for an outstanding building from modern architecture in Brazil using multiple reality-based technologies. The fusion of the different point cloud raw data generated a high-resolution Dense Surface Model (DSM), the base of an accurate and detailed parametric Model. This study demonstrated the potential of digital surveying, including low-cost sensors, and BIM for built heritage documentation.
keywords	Reality-based surveying; Point cloud; As-is model; Building Information Modelling; Modern Heritage
series	SIGRADI
email
last changed	2021/03/28 19:58

_id	ecaaderis2023_45
id	ecaaderis2023_45
authors	Morton, David, Ahmed, Tarek MF and Humphery, Richard
year	2023
title	BIM and Teaching in Architecture: Current thinking and approaches
source	De Luca, F, Lykouras, I and Wurzer, G (eds.), Proceedings of the 9th eCAADe Regional International Symposium, TalTech, 15 - 16 June 2023, pp. 105–115
summary	Increasing use of BIM has represented a continuing shift in traditional assumptions on how we navigate the design process. BIM is affording the student the ability to gain a greater understanding of their design ideas via the exploration of scale, spatial organisation and structure, amongst many other design layers, in increasing levels of detail, at the same point in the design process. Architectural education is at a delayed tipping point where architectural students are increasingly looking towards BIM to streamline their design process drawn by the production of realistic visualisation, but with a lack of knowledge and skill in its application. With a lack of guidance and understanding around the application of BIM, the use of BIM in this manner overlooks the potential of BIM to construct and test virtual simulations of proposed schemes, to support design enquiry. A historical concern for the pedagogy constructed around the students’ design process is the application of methods and techniques that support the progression through the design process, (Ambrose, 2014; dash mei & Safari, 2018). This study examines the design process of architectural students and the interaction between analogue and digital methods used in design. These primary modes of communication, offer the opportunity to query the roles and rules of traditional architectural conventions around ‘problem finding’ and ‘problem solving’, challenging the ‘traditional’ design process examined by pioneers like Bruner (1966) and Schon (1987). These approaches are distilled from the findings of the study and presented as guidance to those teaching in architectural aBIMemia to align pedagogic goals to methods of abstraction in this new era of design education reconsidering digital methods in design.
keywords	BIM, BIM, Design Process, Architecture, Learning
series	eCAADe
email
last changed	2024/02/05 14:28

_id	acadia18_72
id	acadia18_72
authors	Nagy, Danil; Stoddart, Jim; Villaggi, Lorenzo; Burger, Shane; Benjamin, David
year	2018
title	Digital Dérive. Reconstructing urban environments based on human experience
source	ACADIA // 2018: Recalibration. On imprecisionand infidelity. [Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-17729-7] Mexico City, Mexico 18-20 October, 2018, pp. 72-81
doi	https://doi.org/10.52842/conf.acadia.2018.072
summary	This paper describes a novel method for reconstructing urban environments based on individual occupant experience. The method relies on a low-cost off-the-shelf 360-degree camera to capture video and audio data from a natural walk through the city. It then uses a custom workflow based on an open-source Structure from Motion (SfM) library to reconstruct a dense point cloud from images extracted from the 360-degree video. The point cloud and audio data are then represented within a virtual reality (VR) model, creating a multisensory environment that immerses the viewer into the subjective experience of the occupant. This work questions the role of precision and fidelity in our experience and representation of a “real” physical environment. On the one hand, the resulting VR environment is less complete and has lower fidelity than digital environments created through traditional modeling and rendering workflows. On the other hand, because each point in the point cloud is literally sampled from the actual environment, the resulting model also captures more of the noise and imprecision that characterizes our world. The result is an uncanny immersive experience that is less precise than traditional digital environments, yet represents many more of the unique physical characteristics that define our urban experiences.
keywords	full paper, urban design & analysis, representation + perception, interactive simulations, virtual reality
series	ACADIA
type	paper
email
last changed	2022/06/07 07:59

_id	acadia21_246
id	acadia21_246
authors	Safley, Nick
year	2021
title	Reconnecting...
source	ACADIA 2021: Realignments: Toward Critical Computation [Proceedings of the 41st Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-986-08056-7]. Online and Global. 3-6 November 2021. edited by B. Bogosian, K. Dörfler, B. Farahi, J. Garcia del Castillo y López, J. Grant, V. Noel, S. Parascho, and J. Scott. 246-255.
doi	https://doi.org/10.52842/conf.acadia.2021.246
summary	This design research reimagines the architectural detail in a postdigital framework and proposes digital methods to work upon discrete tectonics. Drawing upon Marco Frascari's writing The Tell-the-Tale Detail, the study aims to reimagine tectonic thinking for focused attention after the digital turn. Today, computational tools are powerful enough to perform operations more similar to physical tools than in the earlier digital era. These tools create a "digital materiality," where architects can manipulate digital information in parallel and overlapping ways to physical corollaries. (Abrons and Fure, 2018) To date, work in this area has focused on materiality specifically. This project reinterprets tectonics using texture map editing and point cloud information, particularly reconceptualizing jointing using images. Smartphone-based 3D digital scanning was used to captured details from a series of Carlo Scarpa's influential works, isolating these details from their physical sites and focusing attention upon individual tectonic moments. As digital scans, these details problematize the rhetoric of smoothness and seamlessness prevalent in digital architecture as they are discretely construed loci yet composed of digital meshes. (Jones 2014) Once removed from their contexts, reconnecting the digital scans into compositions of "compound details" necessitated a series of new mechanisms for constructing and construing not native to the material world. Using Photoshop editing of texture-mapped images, digital texturing of meshes, and interpretation of the initial material constructions, new joints within and between these the digital scanned details were created to reframe the original detail for the post-digital.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	caadria2018_167
id	caadria2018_167
authors	Sun, Chengyu, Zheng, Zhaohua, Wang, Yuze, Sun, Tongyu and Ruiz, Laura
year	2018
title	A Topological-Rule-Based Algorithm Converting a Point Cloud into a Key-Feature Mesh
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 597-606
doi	https://doi.org/10.52842/conf.caadria.2018.2.597
summary	As a bridge between tangible models and digital counter parts in almost all the architectural applications with Tangible User Interface, converting point clouds scanned from objects into light meshes with key-features are essential in the human-computer interaction. In this paper, an algorithm based on topological rules is introduced, which focuses on computing a topological-right mesh from a point cloud scanned by a low-cost device in real time. Mesh faces are extracted by analyzing distribution of the normal vectors of neighbor point clusters and mesh vertexes are calculated according to the topological conditions of local surrounding faces. Such a final key-feature mesh has the largest geometric similarity and least vertexes to the tangible model at an architectural cognitive level, whose dimensional accuracy is at an acceptable level concerning the low-cost device used.
keywords	Tangible model; Point cloud; Mesh simplification; Human Computer Interaction
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	ecaade2018_184
id	ecaade2018_184
authors	Tonn, Christian, Schmidt, Harald, Bringmann, Oliver and Klawitter, Daniel
year	2018
title	Abstracting and Trimming Reality - One-Click-Region-Growing and Surface Trimming in Point Clouds
source	Kepczynska-Walczak, A, Bialkowski, S (eds.), Computing for a better tomorrow - Proceedings of the 36th eCAADe Conference - Volume 1, Lodz University of Technology, Lodz, Poland, 19-21 September 2018, pp. 257-262
doi	https://doi.org/10.52842/conf.ecaade.2018.1.257
summary	Measured point clouds are the cast of the as-built reality. In this paper, we present an approach to derive a partially closed surface model from a point cloud. Without using fully-automated methods we instead leverage the users abstract thinking towards a half-automated approach. Hence we present our algorithm for a one click region growing in point clouds and intersecting and trimming those regions to achieve a partially watertight surface model.
keywords	Point cloud; Region growing; As-built environment; Region trimming; Surface model
series	eCAADe
email
last changed	2022/06/07 07:58

_id	acadia18_186
id	acadia18_186
authors	Yin, Hao; Guo, Zhe; Zhao, Yao; Yuan, Philip F.
year	2018
title	Behavior Visualization System Based on UWB Positioning Technology
source	ACADIA // 2018: Recalibration. On imprecisionand infidelity. [Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-17729-7] Mexico City, Mexico 18-20 October, 2018, pp. 186-195
doi	https://doi.org/10.52842/conf.acadia.2018.186
summary	This paper takes behavioral performance as a starting point and uses ultra-wideband (UWB) positioning technology and visualization methods to accurately collect and present in-place behavioral data so as to explore the behavioral characteristics of space users. In this process, we learned the observation, quantification, and presentation of behavioral data from the evolution of behavioral research. Secondly, after a comparative analysis of four types of indoor positioning technologies, we selected UWB-positioning technology and the JavaScript programming language as the development tools for a behavior visualization system. Next, we independently developed the behavior visualization system, which required a deep understanding of the working principle of UWB technology and the visualization method of the JavaScript programming language. Finally, the system was applied to an actual space, collecting and presenting users’ behavioral characteristics and habits in order to verify the applicability of the system in the field of behavioral research.
keywords	full paper, design tools, ai + machine learning, big data, behavioral performance + simulation
series	ACADIA
type	paper
email
last changed	2022/06/07 07:57

_id	caadria2018_217
id	caadria2018_217
authors	Zhang, Le-Min, Jeng, Tay-Sheng and Zhang, Ruo-Xi
year	2018
title	Integration of Virtual Reality, 3-D Eye-Tracking, and Protocol Analysis for Re-Designing Street Space
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 1, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 431-440
doi	https://doi.org/10.52842/conf.caadria.2018.1.431
summary	The objective of this paper is to develop an eye-tracking technology combined with a virtual reality system for an experimental study of an historical street design. Using protocol analysis, a set of design objects, parameters, and subjects are randomly selected for evaluation of the virtual street space of an ancient city. 3-D point-cloud data of spatial behaviors are tracked and analyzed. It is concluded that people with different cultural backgrounds each have a considerably different perception of the street space's characteristics. The methodology described in this paper can be used for spatial design of urban space in the future.
keywords	Virtual Reality; Eye-Tracking; Protocol Analysis; Street Space
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	caadria2018_314
id	caadria2018_314
authors	Kim, Jin Sung, Song, Jae Yeol and Lee, Jin Kook
year	2018
title	Approach to the Extraction of Design Features of Interior Design Elements Using Image Recognition Technique
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 287-296
doi	https://doi.org/10.52842/conf.caadria.2018.2.287
summary	This paper aims to propose deep learning-based approach to the auto-recognition of their design features of interior design elements using given digital images. The recently image recognition technique using convolutional neural networks has shown great success in the various field of research and industry. The open-source frameworks and pre-trained image recognition models supporting image recognition task enable us to easily retrain the models to apply them on any domain. This paper describes how to apply such techniques on interior design process and depicts some demonstration results in that approaches. Furniture that is one of the most common interior design elements has sub-feature including implicit design features, such as style, shape, function as well as explicit properties, such as component, materials, and size. This paper shows to retrain the model to extract some of the features for efficiently managing and utilizing such design information. The target element is chair and the target design features are limited to functional features, materials, seating capacity and design style. Total 3933 chair images dataset and 6 retrained image recognition models were utilized for retraining. Through the combination of those multiple models, inference demonstration also has been described.
keywords	Deep learning; Image recognition; Interior design elements; Design feature; Chair
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	acadia18_216
id	acadia18_216
authors	Ahrens, Chandler; Chamberlain, Roger; Mitchell, Scott; Barnstorff, Adam
year	2018
title	Catoptric Surface
source	ACADIA // 2018: Recalibration. On imprecisionand infidelity. [Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-17729-7] Mexico City, Mexico 18-20 October, 2018, pp. 216-225
doi	https://doi.org/10.52842/conf.acadia.2018.216
summary	The Catoptric Surface research project explores methods of reflecting daylight through a building envelope to form an image-based pattern of light on the interior environment. This research investigates the generation of atmospheric effects from daylighting projected onto architectural surfaces within a built environment in an attempt to amplify or reduce spatial perception. The mapping of variable organizations of light onto existing or new surfaces creates a condition where the perception of space does not rely on form alone. This condition creates a visual effect of a formless atmosphere and affects the way people use the space. Often the desired quantity and quality of daylight varies due to factors such as physiological differences due to age or the types of tasks people perform (Lechner 2009). Yet the dominant mode of thought toward the use of daylighting tends to promote a homogeneous environment, in that the resulting lighting level is the same throughout a space. This research project questions the desire for uniform lighting levels in favor of variegated and heterogeneous conditions. The main objective of this research is the production of a unique facade system that is capable of dynamically redirecting daylight to key locations deep within a building. Mirrors in a vertical array are individually adjusted via stepper motors in order to reflect more or less intense daylight into the interior space according to sun position and an image-based map. The image-based approach provides a way to specifically target lighting conditions, atmospheric effects, and the perception of space.
keywords	full paper, non-production robotics, representation + perception, performance + simulation, building technologies
series	ACADIA
type	paper
email
last changed	2022/06/07 07:54

_id	ijac201816406
id	ijac201816406
authors	As, Imdat; Siddharth Pal and Prithwish Basu
year	2018
title	Artificial intelligence in architecture: Generating conceptual design via deep learning
source	International Journal of Architectural Computing vol. 16 - no. 4, 306-327
summary	Artificial intelligence, and in particular machine learning, is a fast-emerging field. Research on artificial intelligence focuses mainly on image-, text- and voice-based applications, leading to breakthrough developments in self-driving cars, voice recognition algorithms and recommendation systems. In this article, we present the research of an alternative graph- based machine learning system that deals with three-dimensional space, which is more structured and combinatorial than images, text or voice. Specifically, we present a function-driven deep learning approach to generate conceptual design. We trained and used deep neural networks to evaluate existing designs encoded as graphs, extract significant building blocks as subgraphs and merge them into new compositions. Finally, we explored the application of generative adversarial networks to generate entirely new and unique designs.
keywords	Architectural design, conceptual design, deep learning, artificial intelligence, generative design
series	journal
email
last changed	2019/08/07 14:04

_id	caadria2018_343
id	caadria2018_343
authors	Kalantar, Negar and Borhani, Alireza
year	2018
title	Informing Deformable Formworks - Parameterizing Deformation Behavior of a Non-Stretchable Membrane via Kerfing
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 339-348
doi	https://doi.org/10.52842/conf.caadria.2018.2.339
summary	The process for constructing freeform buildings composed of many non-repetitive shapes and waste-free formwork systems remains relatively unexplored. This research reviews a method for fabricating complex double-curved shapes without utilizing single-use formworks. This work answers questions regarding the manufacturing of these shapes in an environmentally-friendly and economic fashion. The proposed method, called a "transformative formwork," could replace state-of-the-art CNC-milled molds and is potentially suitable for large-scale construction. The transformative formwork uses a stretchable membrane or "interpolation layer" that can be manipulated into any curved surface by using vertical bars capable of being rearranged into different heights. Here, to accurately generate most of the smooth, double-curved surfaces, laser kerfing is used for bending interpolation layer into almost any complex shape. A parametric model simplifies local or global changes to the density of the kerfing patterns, modifying the deformation behavior of the layer. Several kerfed interpolation layers produced for four transformative formworks showed that the application of this method.
keywords	Transformative Formwork, Interpolation Layer, Relief-cut Patterns, Positive & Negative Gaussian Curvatures, Interlocking Archimedean Spiral-Patterns, Kerfing
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	caadria2018_126
id	caadria2018_126
authors	Khean, Nariddh, Kim, Lucas, Martinez, Jorge, Doherty, Ben, Fabbri, Alessandra, Gardner, Nicole and Haeusler, M. Hank
year	2018
title	The Introspection of Deep Neural Networks - Towards Illuminating the Black Box - Training Architects Machine Learning via Grasshopper Definitions
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 2, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 237-246
doi	https://doi.org/10.52842/conf.caadria.2018.2.237
summary	Machine learning is yet to make a significant impact in the field of architecture and design. However, with the combination of artificial neural networks, a biologically inspired machine learning paradigm, and deep learning, a hierarchical subsystem of machine learning, the predictive capabilities of machine learning processes could prove a valuable tool for designers. Yet, the inherent knowledge gap between the fields of architecture and computer science has meant the complexity of machine learning, and thus its potential value and applications in the design of the built environment remain little understood. To bridge this knowledge gap, this paper describes the development of a learning tool directed at architects and designers to better understand the inner workings of machine learning. Within the parametric modelling environment of Grasshopper, this research develops a framework to express the mathematic and programmatic operations of neural networks in a visual scripting language. This offers a way to segment and parametrise each neural network operation into a basic expression. Unpacking the complexities of machine learning in an intermediary software environment such as Grasshopper intends to foster the broader adoption of artificial intelligence in architecture.
keywords	machine learning; neural network; action research; supervised learning; education
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ecaade2018_315
id	ecaade2018_315
authors	Koehler, Daniel, Abo Saleh, Sheghaf, Li, Hua, Ye, Chuwei, Zhou, Yaonaijia and Navasaityte, Rasa
year	2018
title	Mereologies - Combinatorial Design and the Description of Urban Form.
source	Kepczynska-Walczak, A, Bialkowski, S (eds.), Computing for a better tomorrow - Proceedings of the 36th eCAADe Conference - Volume 2, Lodz University of Technology, Lodz, Poland, 19-21 September 2018, pp. 85-94
doi	https://doi.org/10.52842/conf.ecaade.2018.2.085
summary	This paper discusses the ability to apply machine learning to the combinatorial design-assembly at the scale of a building to urban form. Connecting the historical lines of discrete automata in computer science and formal studies in architecture this research contributes to the field of additive material assemblies, aggregative architecture and their possible upscaling to urban design. The following case studies are a preparation to apply deep-learning on the computational descriptions of urban form. Departing from the game Go as a testbed for the development of deep-learning applications, an equivalent platform can be designed for architectural assembly. By this, the form of a building is defined via the overlap between separate building parts. Building on part-relations, this research uses mereology as a term for a set of recursive assembly strategies, integrated into the design aspects of the building parts. The models developed by research by design are formally described and tested under a digital simulation environment. The shown case study shows the process of how to transform geometrical elements to architectural parts based merely on their compositional aspects either in horizontal or three-dimensional arrangements.
keywords	Urban Form; Discrete Automata ; Combinatorics; Part-Relations; Mereology; Aggregative Architecture
series	eCAADe
email
last changed	2022/06/07 07:51

_id	caadria2018_083
id	caadria2018_083
authors	Luo, Dan, Wang, Jinsong and Xu, Weiguo
year	2018
title	Robotic Automatic Generation of Performance Model for Non-Uniform Linear Material via Deep Learning
source	T. Fukuda, W. Huang, P. Janssen, K. Crolla, S. Alhadidi (eds.), Learning, Adapting and Prototyping - Proceedings of the 23rd CAADRIA Conference - Volume 1, Tsinghua University, Beijing, China, 17-19 May 2018, pp. 39-48
doi	https://doi.org/10.52842/conf.caadria.2018.1.039
summary	In the following research, a systematic approach is developed to generate an experiment-based performance model that computes and customizes properties of non-uniform linear materials to accommodate the form of designated curve under bending and natural force. In this case, the test subject is an elastomer strip of non-uniform sections. A novel solution is provided to obtain sufficient training data required for deep learning with an automatic material testing mechanism combining robotic arm automation and image recognition. The collected training data are fed into a deep combination of neural networks to generate a material performance model. Unlike most traditional performance models that are only able to simulate the final form from the properties and initial conditions of the given materials, the trained neural network offers a two-way performance model that is also able to compute appropriate material properties of non-uniform materials from target curves. This network achieves complex forms with minimal and effective programmed materials with complicated nonlinear properties and behaving under natural forces.
keywords	Material performance model; Deep Learning; Robotic automation; Material computation; Neural network
series	CAADRIA
email
last changed	2022/06/07 07:59

For more results click below: