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 638

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

_id	acadia20_178
id	acadia20_178
authors	Meeran, Ahmed; Conrad Joyce, Sam
year	2020
title	Machine Learning for Comparative Urban Planning at Scale: An Aviation Case Study
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. 178-187.
doi	https://doi.org/10.52842/conf.acadia.2020.1.178
summary	Aviation is in flux, experiencing 5.4% yearly growth over the last two decades. However, with COVID-19 aviation was hard hit. This, along with its contribution to global warming, has led to louder calls to limit its use. This situation emphasizes how urban planners and technologists could contribute to understanding and responding to this change. This paper explores a novel workflow of performing image-based machine learning (ML) on satellite images of over 1,000 world airports that were algorithmically collated using European Space Agency Sentinel2 API. From these, the top 350 United States airports were analyzed with land use parameters extracted around the airport using computer vision, which were mapped against their passenger footfall numbers. The results demonstrate a scalable approach to identify how easy and beneficial it would be for certain airports to expand or contract and how this would impact the surrounding urban environment in terms of pollution and congestion. The generic nature of this workflow makes it possible to potentially extend this method to any large infrastructure and compare and analyze specific features across a large number of images while being able to understand the same feature through time. This is critical in answering key typology-based urban design challenges at a higher level and without needing to perform on-ground studies, which could be expensive and time-consuming.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	cdrf2019_17
id	cdrf2019_17
authors	Chuan Liu, Jiaqi Shen, Yue Ren, and Hao Zheng
year	2020
title	Pipes of AI – Machine Learning Assisted 3D Modeling Design
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_2
summary	Style transfer is a design technique that is based on Artificial Intelligence and Machine Learning, which is an innovative way to generate new images with the intervention of style images. The output image will carry the characteristic of style image and maintain the content of the input image. However, the design technique is employed in generating 2D images, which has a limited range in practical use. Thus, the goal of the project is to utilize style transfer as a toolset for architectural design and find out the possibility for a 3D modeling design. To implement style transfer into the research, floor plans of different heights are selected from a given design boundary and set as the content images, while a framework of a truss structure is set as the style image. Transferred images are obtained after processing the style transfer neural network, then the geometric images are translated into floor plans for new structure design. After the selection of the tilt angle and the degree of density, vertical components that connecting two adjacent layers are generated to be the pillars of the structure. At this stage, 2D style transferred images are successfully transformed into 3D geometries, which can be applied to the architectural design processes. Generally speaking, style transfer is an intelligent design tool that provides architects with a variety of choices of idea-generating. It has the potential to inspire architects at an early stage of design with not only 2D but also 3D format.
series	cdrf
email
last changed	2022/09/29 07:51

_id	cdrf2019_36
id	cdrf2019_36
authors	Dan Luo, Joseph M. Gattas, and Poah Shiun Shawn Tan
year	2020
title	Real-Time Defect Recognition and Optimized Decision Making for Structural Timber Jointing
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_4
summary	Non-structural or out-of-grade timber framing material contains a large proportion of visual and natural defects. A common strategy to recover usable material from these timbers is the marking and removing of defects, with the generated intermediate lengths of clear wood then joined into a single piece of fulllength structural timber. This paper presents a novel workflow that uses machine learning based image recognition and a computational decision-making algorithm to enhance the automation and efficiency of current defect identification and rejoining processes. The proposed workflow allows the knowledge of worker to be translated into a classifier that automatically recognizes and removes areas of defects based on image capture. In addition, a real-time optimization algorithm in decision making is developed to assign a joining sequence of fragmented timber from a dynamic inventory, creating a single piece of targeted length with a significant reduction in material waste. In addition to an industrial application, this workflow also allows for future inventory-constrained customizable fabrication, for example in production of non-standard architectural components or adaptive reuse or defect-avoidance in out-of-grade timber construction.
series	cdrf
email
last changed	2022/09/29 07:51

_id	acadia20_594
id	acadia20_594
authors	Farahbakhsh, Mehdi; Kalantar, Negar; Rybkowski, Zofia
year	2020
title	Impact of Robotic 3D Printing Process Parameters on Bond Strength
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. 594-603.
doi	https://doi.org/10.52842/conf.acadia.2020.1.594
summary	Additive manufacturing (AM), also known as 3D printing, offers advantages over traditional construction technologies, increasing material efficiency, fabrication precision, and speed. However, many AM projects in academia and industrial institutions do not comply with building codes. Consequently, they are not considered safe structures for public utilization and have languished as exhibition prototypes. While three discrete scales—micro, mezzo, and macro—are investigated for AM with paste in this paper, structural integrity has been tackled on the mezzo scale to investigate the impact of process parameters on the bond strength between layers in an AM process. Real-world material deposition in a robotic-assisted AM process is subject to environmental factors such as temperature, humidity, the load of upper layers, the pressure of the nozzle on printed layers, etc. Those factors add a secondary geometric characteristic to the printed objects that was missing in the initial digital model. This paper introduces a heuristic workflow for investigating the impacts of three selective process parameters on the bond strength between layers of paste in the robotic-assisted AM of large-scale structures. The workflow includes a method for adding the secondary geometrical characteristic to the initial 3D model by employing X-ray computerized tomography (CT) scanning, digital image processing, and 3D reconstruction. Ultimately, the proposed workflow offers a pattern library that can be used by an architect or artificial intelligence (AI) algorithms in automated AM processes to create robust architectural forms.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2020_432
id	ecaade2020_432
authors	Fragkia, Vasiliki and Worre Foged, Isak
year	2020
title	Methods for the Prediction and Specification of Functionally Graded Multi-Grain Responsive Timber Composites
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 585-594
doi	https://doi.org/10.52842/conf.ecaade.2020.2.585
summary	The paper presents design-integrated methods for high-resolution specification and prediction of functionally graded wood-based thermal responsive composites, using machine learning. The objective is the development of new circular design workflow, employing robotic fabrication, in order to predict fabrication files linked to material performance and design requirements, focused on application for intrinsic responsive and adaptive architectural surfaces. Through an experimental case study, the paper explores how machine learning can form a predictive design framework where low-resolution data can solve material systems at high resolution. The experimental computational and prototyping studies show that the presented image-based machine learning method can be adopted and adapted across various stages and scales of architectural design and fabrication. This in turn allows for a design-per-requirement approach that optimizes material distribution and promotes material economy.
keywords	material specification; responsive timber composites; machine learning; robotic fabrication; building envelopes
series	eCAADe
email
last changed	2022/06/07 07:50

_id	acadia20_658
id	acadia20_658
authors	Ho, Brian
year	2020
title	Making a New City Image
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. 658-667.
doi	https://doi.org/10.52842/conf.acadia.2020.1.658
summary	This paper explores the application of computer vision and machine learning to streetlevel imagery of cities, reevaluating past theory linking urban form to human perception. This paper further proposes a new method for design based on the resulting model, where a designer can identify areas of a city tied to certain perceptual qualities and generate speculative street scenes optimized for their predicted saliency on labels of human experience. This work extends Kevin Lynch’s Image of the City with deep learning: training an image classification model to recognize Lynch’s five elements of the city image, using Lynch’s original photographs and diagrams of Boston to construct labeled training data alongside new imagery of the same locations. This new city image revitalizes past attempts to quantify the human perception of urban form and improve urban design. A designer can search and map the data set to understand spatial opportunities and predict the quality of imagined designs through a dynamic process of collage, model inference, and adaptation. Within a larger practice of design, this work suggests that the curation of archival records, computer science techniques, and theoretical principles of urbanism might be integrated into a single craft. With a new city image, designers might “see” at the scale of the city, as well as focus on the texture, color, and details of urban life.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	cdrf2019_93
id	cdrf2019_93
authors	Jiaxin Zhang , Tomohiro Fukuda , and Nobuyoshi Yabuki
year	2020
title	A Large-Scale Measurement and Quantitative Analysis Method of Façade Color in the Urban Street Using Deep Learning
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_9
summary	Color planning has become a significant issue in urban development, and an overall cognition of the urban color identities will help to design a better urban environment. However, the previous measurement and analysis methods for the facade color in the urban street are limited to manual collection, which is challenging to carry out on a city scale. Recent emerging dataset street view image and deep learning have revealed the possibility to overcome the previous limits, thus bringing forward a research paradigm shift. In the experimental part, we disassemble the goal into three steps: firstly, capturing the street view images with coordinate information through the API provided by the street view service; then extracting facade images and cleaning up invalid data by using the deep-learning segmentation method; finally, calculating the dominant color based on the data on the Munsell Color System. Results can show whether the color status satisfies the requirements of its urban plan for façade color in the street. This method can help to realize the refined measurement of façade color using open source data, and has good universality in practice.
series	cdrf
email
last changed	2022/09/29 07:51

_id	acadia20_282
id	acadia20_282
authors	Steinfeld, Kyle
year	2020
title	Drawn, Together
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. 282-289.
doi	https://doi.org/10.52842/conf.acadia.2020.1.282
summary	Changes in the media through which design proceeds are often associated with the emergence of novel design practices and new subjectivities. While the dynamic between design tools and design practices is complex and nondeterministic, there are moments when rapid development in one of these areas catalyzes changes in the other. The nascent integration of machine learning (ML) processes into computer-aided design suggests that we are in just such a moment. It is in this context that an undergraduate research studio was conducted at UC Berkeley in the spring of 2020. By introducing novice students to a set of experimental tools (Steinfeld 2020) and processes based on ML techniques, this studio seeks to uncover those original practices or new subjectivities that might thereby arise. We describe here a series of small design projects that examine the applicability of such tools to early-stage architectural design. Specifically, we document the integration of several conditional text-generation models and conditional image-generation models into undergraduate architectural design pedagogy, and evaluate their use as “creative provocateurs” at the start of a design. After surveying the resulting student work and documenting the studio experience, we conclude that the approach taken here suggests promising new modalities of design authorship, and we offer reflections that may serve as a useful guide for the more widespread adoption of machine-augmented design tools in architectural practice.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	acadia20_160
id	acadia20_160
authors	Sun, Yunjuan; Jiang, Lei; Zheng, Hao
year	2020
title	A Machine Learning Method of Predicting Behavior Vitality Using Open Source Data
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. 160-168.
doi	https://doi.org/10.52842/conf.acadia.2020.2.160
summary	The growing popularity of machine learning has provided new opportunities to predict certain behaviors precisely by utilizing big data. In this research, we use an image-based neural network to explore the relationship between the built environment and the activity of bicyclists in that environment. The generative model can produce heat maps that can be used to predict quantitatively the cycling and running activity in a given area, and then use urban design to enhance urban vitality in that area. In the machine learning model, the input image is a plan view of the built environment, and the output image is a heat map showing certain activities in the corresponding area. After it is trained, the model yields output (the predicted heat map) at an acceptable level of accuracy. The heat map shows the levels and conditions of the subject activity in different sections of the built environment. Thus, the predicted results can help identify where regional vitality can be improved. Using this method, designers can not only predict the behavioral heat distribution but also examine the different interactions between behaviors and aspects of the environment. The extent to which factors might influence behaviors is also studied by generating a heat map of the modified plan. In addition to the potential applications of this approach, its limitations and areas for improvement are also proposed.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	caadria2020_233
id	caadria2020_233
authors	Bar-Sinai, Karen Lee, Shaked, Tom and Sprecher, Aaron
year	2020
title	Sensibility at Large - A Post-Anthropocene Vision for Architectural Landscape Editing
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. 223-232
doi	https://doi.org/10.52842/conf.caadria.2020.2.223
summary	The irreversible imprint of humankind on Earth calls for revisiting current construction practices. This paper forwards a vision for post-Anthropocene, large-scale, architectural, and landscape construction. This vision relates to transforming natural terrains into architecture using on-site robotic tools and enabling greater sustainability through increased sensibility. Despite advancements in large-scale digital fabrication in architecture, the field still mainly focuses on the production of objects. The proposed vision aims to advance theory and practice towards territorial scale digital fabrication of environments. Three notions are proposed: material-aware construction, large-scale customization, and integrated fabrication. These aspects are demonstrated through research and teaching projects. Using scale models, they explore the deployment of robotic tools toward reforming, stabilizing, and reconstituting soil in an architectural context. Together, they propose a theoretical ground for in situ digital fabrication for a new era, relinking architecture to the terrains upon which it is formed.
keywords	Digital Fabrication; territorial scale; on-site robotics; geomaterials; computational design
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	sigradi2020_449
id	sigradi2020_449
authors	Becerra-Santacruz, Habid; Becerra-Santacruz, Axel
year	2020
title	Mapping of emerging territorial phenomena at Micro Scale: Development of collaborative database as a base for Evidence-Based Design Strategies
source	SIGraDi 2020 [Proceedings of the 24th Conference of the Iberoamerican Society of Digital Graphics - ISSN: 2318-6968] Online Conference 18 - 20 November 2020, pp. 449-454
summary	This paper presents an active analysis and research approach for design workshops at the Faculty of Architecture at UMNSH. The proposed scheme for final year design studio demands students to participate in the confrontation of reality to understand first-hand through databases; the complex problems of contemporary society and its relationship with the habitat. In order to understand the diverse emergent phenomena of the city, a collaborative work is implemented for the development of a database, occupation maps and territorial dynamics on a micro scale. From the evidence supported by data, students articulate design strategies and specific territorial actions.
keywords	Collaborative database, Evidence-based design strategies, Emergent phenomena mapping, Design pedagogy
series	SIGraDi
email
last changed	2021/07/16 11:49

_id	acadia20_226p
id	acadia20_226p
authors	Borhani, Alireza; Kalantar, Negar
year	2020
title	Interlocking Shell
source	ACADIA 2020: Distributed Proximities / Volume II: Projects [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95253-6]. Online and Global. 24-30 October 2020. edited by M. Yablonina, A. Marcus, S. Doyle, M. del Campo, V. Ago, B. Slocum. 226-231
summary	With a specific focus on robotic stereotomy, two full-scale vault structures were designed to explore the potential of self-standing building structures made from interlocking components; these structures were fabricated with a track-mounted industrial-scale robot (ABB 4600). To respond to the economic affordances of robotic subtractive cutting, all uniquely shaped structural modules came from one block of material (48"" x96"" x36""). Through the discretization of curvilinear tessellated vault surfaces into a limited number of uniquely shaped modules with embedded form-fitting connectors, the project exhibited the potential for programming a robot to cut ruled surfaces to produce freeform shells of any kind. Representing nearly zero-waste construction, the developed technology can potentially be used for self-supporting emergency shelters and field medical clinics, facilitating easy shipping and speedy assembly. Without using any scaffolding, a few people can erect and dismantle an entire mortar-free structure at the construction site. The disassembled structure occupies minimal space in storage, and the structure’s pieces can be transported to the site in stacks. Robot milling is a common technique for removing material to transform a block into a sculptural shape. Unlike milling techniques that produce significant waste, we used a hotwire that sliced through a Geofoam block to create almost no waste pieces. Since the front side of every module was concurrent with the backside of the next one, such a decision allowed to operate just one cut per front side of each module. In this case, by having three cuts, two neighboring modules were fabricated. The form of the structure and its modules emerged from the constraints of the fabrication technique, aiming to establish a feedback loop between geometry, material, simulation, and tool. By cross-referencing geometric data across Grasshopper, a customized tessellation script was made to breakdown a vault into its modular ruled surface constructs.
series	ACADIA
type	project
email
last changed	2021/10/26 08:08

_id	acadia20_150
id	acadia20_150
authors	Gaudilliere-Jami, Nadja
year	2020
title	AD Magazine
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. 150-159.
doi	https://doi.org/10.52842/conf.acadia.2020.1.150
summary	This paper aims to contribute to a history of computational design and to a historiography of the field by proposing a study of the development of sociotechnical networks of computation in architecture between 1965 and 2020 as shown in AD magazine. The research focuses on two aspects: (1) a methodological approach for the constitution of a comprehensive history of the field and the application of that methodology to a corpus of items published in AD, and (2) questions the relevance of the outlook into computational design as given by the magazine in comparison to a more comprehensive history taking into account other sources. First, the paper presents the history and the editorial line of AD, as well as its pertinence as a primary source. Second, a brief account of the history emerging from this research is given, with a focus on four different periods: pioneering research of the 1960s–1970s, emergence of 3D modeling tools and the procedural winter in the 1980s–1990s, constitution of a large-scale academic and professional network in the 2000s, and democratization of algorithmic design tools in the 2010s. Third, observations are made on editorial choices of the magazine and the biases of its account of computational research, with a special focus on the period 2000–2020, during which many issues have been dedicated to computational design themes, therefore making potential biases more visible. Despite the preponderance of specific topics, editors, and contributors, AD magazine provides an outlook into key concerns of the community at given times. The main biases identified, including a strong focus on the themes of biodesign and rationalization of practices, mirror the biases of the computational field itself, demonstrating the value of AD as an archive for the history of the field.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	acadia20_416
id	acadia20_416
authors	Genadt, Ariel
year	2020
title	Discrete Continuity in the Urban Architectures of H. Hara & K. Kuma
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. 416-424.
doi	https://doi.org/10.52842/conf.acadia.2020.1.416
summary	The 2020 pandemic has laid bare the ambiguous value of the virtual proximity that distributed computing enables. The remote interaction it ushered in at an unprecedented scale also spawned social isolation, which is symbolically underscored by the reliance of this form of connectivity on individuals’ discrete digital identification. This cyber-spatial dualism may be called ‘discrete continuity,’ and it already appeared in architectural thought in the 1960s with the advent of cybernetics and the first computers. The duality resurfaced in the 1990s in virtual projects, when architectural software was first widely commercialized, and it reappeared in built form in the past decade. This paper sheds light on the architectural aspects of this conceptual duality by identifying the use of discreteness and continuity in the theories of two Japanese architects, Hiroshi Hara (b.1936) and his former student, Kengo Kuma (b.1954), in their attempts to combine the two topological conditions as metaphors of societal structures. They demonstrate that the onset of the current condition, while new in its pervasiveness, has been latent in architectural thinking for several decades. This paper examines Hara’s and Kuma’s theories in light of the author’s interviews with the architects, their writings, and specific projects that illustrate metaphoric translations of topological terms into social structures, reflected in turn in the organization of urban schemes and building parts. While Hara’s and Kuma’s respective implementations are poles apart visually and materially, they share the idea that the discrete continuity of contemporary urban experience ought to be reflected in architecture. This link between their ideas has previously been overlooked.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2020_131
id	ecaade2020_131
authors	Gortazar-Balerdi, Ander and Markusiewicz, Jacek
year	2020
title	Legible Bilbao - Computational method for urban legibility
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. 209-218
doi	https://doi.org/10.52842/conf.ecaade.2020.1.209
summary	Legibility is a core concept in spatial cognition theories since Kevin Lynch published The Image of the City in 1960. It is the ability of a city to be interpreted and easily used, travelled and enjoyed, from the pedestrian's perspective. Following a proposal in the participatory budget process of the city of Bilbao, we wrote a technical report to improve the urban legibility of the city and facilitate wayfinding through innovations in signage. This paper aims to present this project, which is an application of computational methods to measure urban legibility that resulted in a proposal for a new wayfinding strategy for Bilbao. The method is based on GIS data, and it simulates urban processes using dedicated algorithms, allowing us to perform two analyses that resulted in two overlapping maps: a heat map of decision points and a map of visual openings. It allowed us to perceive common urban elements that can help to decide both the location of the wayfinding signage and how it should provide the relevant information. In addition, the research introduces the concept of anticipation points, as a complement to the existing idea of decision points.
keywords	Wayfinding; Urban legibility; Spatial cognition
series	eCAADe
email
last changed	2022/06/07 07:51

_id	ecaade2020_222
id	ecaade2020_222
authors	Ikeno, Kazunosuke, Fukuda, Tomohiro and Yabuki, Nobuyoshi
year	2020
title	Automatic Generation of Horizontal Building Mask Images by Using a 3D Model with Aerial Photographs for Deep Learning
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 271-278
doi	https://doi.org/10.52842/conf.ecaade.2020.2.271
summary	Information extracted from aerial photographs is widely used in urban planning and design. An effective method for detecting buildings in aerial photographs is to use deep learning for understanding the current state of a target region. However, the building mask images used to train the deep learning model are manually generated in many cases. To solve this challenge, a method has been proposed for automatically generating mask images by using virtual reality 3D models for deep learning. Because normal virtual models do not have the realism of a photograph, it is difficult to obtain highly accurate detection results in the real world even if the images are used for deep learning training. Therefore, the objective of this research is to propose a method for automatically generating building mask images by using 3D models with textured aerial photographs for deep learning. The model trained on datasets generated by the proposed method could detect buildings in aerial photographs with an accuracy of IoU = 0.622. Work left for the future includes changing the size and type of mask images, training the model, and evaluating the accuracy of the trained model.
keywords	Urban planning and design; Deep learning; Semantic segmentation; Mask image; Training data; Automatic design
series	eCAADe
email
last changed	2022/06/07 07:50

_id	acadia20_154p
id	acadia20_154p
authors	Josephson, Alex; Friedman, Jonathan; Salance, Benjamin; Vasyliv, Ivan; Melnichuk, Tim
year	2020
title	Gusto: Rationalizing Computational Masonry Design
source	ACADIA 2020: Distributed Proximities / Volume II: Projects [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95253-6]. Online and Global. 24-30 October 2020. edited by M. Yablonina, A. Marcus, S. Doyle, M. del Campo, V. Ago, B. Slocum. 154-159
summary	Gusto 501 is a multi-level Infill Building on the footprint of an old car garage. Surrounded by an overpass and former factories, the restaurant and event spaces take the form of a ‘Hyper garage’ as a nod to its urban context. The interior is punctuated with standard terracotta blocks formed to create an intricate play of shadows during the day and embedded with LEDs to provide atmospheric illumination at night. The client's vision, our narrative, and the program demanded an innovative use of the primal material: terracotta. The scale of the project required the use of 3,700 blocks. Within the array wrapped around a 50ft tall interior volume, each block needed to be formed and sequenced uniquely to maintain structural integrity and interface with building systems, and express the sculptural qualities our team had designed. Standard approaches to the masonry could not achieve the effects our team was striving for - we had to develop our ground-up process to manufacture and install mass-customized masonry. The design process involved an algorithmic approach to a series of cuts and geometric manipulations to the blocks that allowed for near-endless combinations/configurations to create a dynamic interior facade system. Partisans, partnering with a terracotta block manufacturer, a local mason, and a masonry engineer, pursued simplifying production using wire cutter systems. Digital and physical mock-ups were then used to create a robust library of parameterized design criteria that optimized corbelling, grout thickness, weight, and fabrication complexity. Working sets of drawings were automated through a fully integrated BIM model, simplifying and speeding up installation. The challenge of marrying these processes with the physical realities of installation required another level of collaboration that included the masons themselves and the electricians who would eventually combine lighting systems into the sculpted block array.
series	ACADIA
type	project
email
last changed	2021/10/26 08:03

_id	caadria2020_078
id	caadria2020_078
authors	Joyce, Gabriella and Pelosi, Antony
year	2020
title	Robotic Connections for CLT Panels
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. 403-412
doi	https://doi.org/10.52842/conf.caadria.2020.2.403
summary	In a climate where standard methods of construction are being challenged, developments in engineered timbers are allowing mass timber construction to be explored as a sustainable alternative to current building methods that can change the future of the built environment. Cross-laminated timber (CLT) is at the forefront of this evolution and, with the advancement in computational design and digital fabrication tools, there lies an opportunity to redefine standard construction. This project creates connections inspired by traditional Japanese joinery that have been adapted to be used for the panel construction of CLT structures. Using a combination of digital modelling and advanced digital fabrication, the project utilizes CLT offcuts as a primary connection material. The system not only reduces waste but also mitigates thermal bridging and lowers the number of connection points whilst increasing the ease of building and fabrication. Connection systems are designed and prototyped using a robotic arm and are then evaluated within the context of a building scale and considers largeâ€scale fabrication and onâ€site assembly whilst continuing to focus on the reduction of waste.
keywords	Robotics; CLT; Connections; Waste; Timber
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	acadia20_142p
id	acadia20_142p
authors	Kilian, Axel
year	2020
title	The Flexing Room
source	ACADIA 2020: Distributed Proximities / Volume II: Projects [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95253-6]. Online and Global. 24-30 October 2020. edited by M. Yablonina, A. Marcus, S. Doyle, M. del Campo, V. Ago, B. Slocum. 142-147
summary	Robotics has been largely confined to the object category with fewer examples at the scale of buildings. Robotic buildings present unique challenges in communicating intent to the enclosed user. Precedent work in architectural robotics explored the performative dimension, the playful and interactive qualities, and the cognitive challenges of AI systems interacting with people in architecture. The Flexing Room robotic skeleton was installed at MIT at its full designed height for the first time and tested for two weeks in the summer of 2019. The approximately 13-foot-tall structure is comprised of 36 pneumatic actuators and an active bend fiberglass structure. The full height allowed for a wide range of postures the structure could take. Acoustic monitoring through Piezo pickup mics was added that allowed for basic rhythmic responses of the structure to people tapping or otherwise triggering the vibration sensors. Data streams were collected synchronously from Kinect skeleton tracking, piezo pickup mics, camera streams, and posture data. The emphasis in this test period was first to establish reliable hardware operations at full scale and second to record correlated data streams of the sensors installed in the structure together with the actuation triggers and the human poses of the inhabitant. The full-scale installation of hardware was successful and proved the feasibility of the structural and actuation approach previously tested on a one-level setup. The range of postures was increased and more transparent for the occupant. The perception of the structure as space was also improved as the system reached regular ceiling height and formed a clearer architectural scale enclosure. The ambition of communicating through architectural postures has not been achieved yet, but promising directions emerged from the test and data collection
series	ACADIA
type	project
email
last changed	2021/10/26 08:03

_id	acadia20_484
id	acadia20_484
authors	Kim, Namjoo; Otitigbe, Eto; Shannon, Caroline; Smith, Brian; Seyedahmadian, Alireza; Höweler, Eric; Yoon, J. Meejin; Marshall, Durham; Durham, James
year	2020
title	Parametric Photo V-Carve for Variable Surfaces
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. 484-493.
doi	https://doi.org/10.52842/conf.acadia.2020.1.484
summary	This research project was part of the design and construction of the Memorial to Enslaved Laborers (MEL) at the University of Virginia (UVA). The MEL was dedicated to an estimated 4,000 enslaved persons who worked at UVA between 1817 and 1865. The 80-foot-diameter memorial is a tapered toroidal shape composed of 75 stone blocks. This project demonstrates how computational design tools along with robotic digital fabrication can be used to achieve unique social and experiential effects in an architectural application. The memorial’s design was informed by an extensive community engagement process that clarified the importance of including a visual representation of enslaved people on the memorial. With this input, the eyes of Isabella Gibbons were selected to be used as a symbolic representation of triumph on the outer wall of the memorial. The MEL project could not rely solely on prior methods or existing software applications to design and fabricate this portrait due to four particularities of the project: material, geometry, representation, and scale. To address these challenges, the MEL design team employed an interdisciplinary collaborative process to develop an innovative parametric design technique: parametric photo V-carve. This technique allowed the MEL design team to render a large-scale photo-realistic portrait into stone. This project demonstrates how the synthesis of artistic motivations, computational design, and robotic digital fabrication can develop unique expressions that shape personal and cultural experiences.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

For more results click below: