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 10417

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

_id	caadria2024_355
id	caadria2024_355
authors	Wu, Zhaoji, Wang, Zhe, Cheng, Jack C.P. and Kwok, Helen H.L.
year	2024
title	A Knowledge Graph Model for Performance-Based Generative Design and Its Applications in Accelerated Design
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 1, pp. 395–404
doi	https://doi.org/10.52842/conf.caadria.2024.1.395
summary	Data integration and information enrichment pose significant challenges to the advancement of Performance-based Generative Design (PGD). One potential solution to these challenges is the utilization of Knowledge Graph (KG). However, the implementation of KG in PGD, particularly in leveraging expert knowledge to accelerate the process, remains an area that has not been thoroughly explored. In this research, we propose a PGD-KG schema to capture and represent the topological relationships and functionalities within PGD. We also introduce a method for automatically generating PGD-KG models from parametric design models enriched with semantic information. Additionally, we develop reasoning algorithms based on expert knowledge of sustainable design to facilitate automated performance evaluation. The effectiveness of the PGD-KG approach was demonstrated through its implementation in a design project, where the reasoning algorithms proved capable of significantly reducing the solution space in PGD by 88.50%, while still ensuring the inclusion of an adequate number of Pareto optimal solutions. This research contributes to the design acceleration by integration of expert knowledge, particularly sustainable design strategies, into PGD.
keywords	performance-based generative design, knowledge graph, reasoning algorithm, building performance evaluation, sustainable building design.
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	ecaade2024_105
id	ecaade2024_105
authors	Wu, Zhaoji; Li, Mingkai; Liu, Wenli; Wang, Zhe; Cheng, Jack C.P.; Kwok, Helen H.L.
year	2024
title	A Data-Driven Model for Sustainable Performance Prediction of Residential Block Layout Design Using Graph Neural Network
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 575–584
doi	https://doi.org/10.52842/conf.ecaade.2024.1.575
summary	Performance evaluation plays a pivotal role in sustainable architectural design, guiding the design direction towards sustainable objectives. Building simulations based on physical modeling are commonly adopted for performance prediction, but the high computational cost hinders their applications in early design stages that require prompt feedback. Surrogate models have been proposed to emulate the expensive high-fidelity building simulation models using data-driven models. Several studies have been conducted to develop surrogate models for sustainable performance prediction of residential block layout design, but the features proposed by these studies were based on specific cases and cannot represent general residential block layout design. To overcome this gap, this study proposes a novel surrogate model for multi-objective sustainable performance prediction based on graph neural network (GNN), which can be adopted in practical early design stages of residential block layout design. First, a graph schema is proposed to represent the general topological relations among components in residential block layout design. Second, an architecture using graph attention network (GAT) is proposed for multiple sustainable performance predictions. Third, a dataset is established based on parametric design models of residential blocks and simulations of sustainable performance, including energy consumption, daylighting, and thermal comfort. Fourth, the proposed surrogate model using the proposed architecture are trained and fine-tuned to learn the relationship between the residential block design and sustainable performance. Finally, the proposed model is evaluated in terms of accuracy, comparing with benchmark models using graph convolutional network (GCN) and artificial neural network (ANN). The results show that the proposed model (GAT) outperforms the benchmark models (GCN and ANN). The proposed model can achieve a satisfactory accuracy with small CV(RMSE)s of 11.97%, 7.88% and 10.11% in terms of energy use intensity (EUI), annual comfort hour (ACH) and useful daylight illuminance (UDI) in the test dataset.
keywords	Surrogate model, Graph neural network, Building performance prediction, Sustainable building design, Residential block
series	eCAADe
email
last changed	2024/11/17 22:05

_id	caadria2022_255
id	caadria2022_255
authors	Wu, Zihao, Zhang, Yunsong and Tong, Ziyu
year	2022
title	Quantification of the Thermal Environmental Value of Urban Pores: A Case Study of Nanjing
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 719-728
doi	https://doi.org/10.52842/conf.caadria.2022.2.719
summary	The term "Urban pores‚ refers to the space formed by the enclosure of buildings, which have great value for regulating the microclimate. Many previous studies have focused only on a single urban pore section, ignoring the spatial distribution at the urban scale. In this study, the openness of urban pores in Nanjing was quantified and grouped, and then the spatial distribution characteristics of each openness group were further calculated. Based on this, the study combined the spatial distribution characteristics of urban pores with urban thermal environment data and an LCZ urban form classification model to analyse the impact of urban pores on the urban thermal environment. The results show that 1) the impact of urban pores is greater in summer and autumn, where its spatial agglomeration has a higher cooling value for the urban thermal environment, while this is not significant in winter; 2) the spatial agglomeration of urban pores in the high openness group, mid-high openness group and mid-low openness group have a higher cooling effect, which mainly corresponds to water, open spaces or parks and urban roads. These spaces should be given more attention when developing urban design strategies. The results can provide some references for urban development.
keywords	urban pores, openness, spatial distribution, urban thermal environment, local climate zone (LCZ), SDG 11, SDG 13
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	21e9
authors	Wurman, R.S. (ed.)
year	1996
title	Information Architects
source	Graphic Press Ltd., Zurich, Switzerland
summary	There is a tsunami of data that is crashing onto the beaches of the civilized world. This is a tidal wave of unrelated, growing data formed in bits and bytes, coming in an unorganized, uncontrolled, incoherent cacophony of foam. None of it is easily related, none of it comes with any organization methodology. Now for the good news: There is a dune on the beach. There is a breakwater in the ocean that is clearly emerging in these last fleeting moments of the 20th century. The breakwater is indeed breaking up the tsunami of data and focusing it in a more organized way to answer our questions and concerns. There is a new breed of graphic designers, exhibition designers, illustrators and photographers, whose passion it is to make the complex clear. I call this new breed of talented thinkers Information Architects and this book was created to help celebrate and understand the importance of their work - a work which inspires hope that as we expand our capabilities to inform and communicate that we will value, with equal enthusiasm, the design of understanding.
series	other
last changed	2003/04/23 15:14

_id	ecaade2012_144
id	ecaade2012_144
authors	Wurzer, Gabriel ; Pak, Burak
year	2012
title	Lawnmower: Designing a web-based visual programming environment that generates code to help students learn textual programming
source	Achten, Henri; Pavlicek, Jiri; Hulin, Jaroslav; Matejovska, Dana (eds.), Digital Physicality - Proceedings of the 30th eCAADe Conference - Volume 1 / ISBN 978-9-4912070-2-0, Czech Technical University in Prague, Faculty of Architecture (Czech Republic) 12-14 September 2012, pp. 655-663.
doi	https://doi.org/10.52842/conf.ecaade.2012.1.655
wos	WOS:000330322400069
summary	Learning programming can be a challenging task for design students, especially when code is to be entered in textual form. Visual programming languages, such as McNeil’s Grasshopper, have helped students to engage in scripting without having to deal with lower level syntax that is often hindering them in expressing their thoughts. However, the problem with learning how to program textually is only postponed: When switching to a new platform, students may be forced to learn coding from scratch, and, even worse, to do so in a textual environment that is yet unfamiliar. Our idea is simple: Connect visual programming with textual coding, using code-generation as means. Using this approach enables students to think visually, and see the results textually. An added bonus is the possibility to use debugging, a feature that is yet lacking from Grasshopper. By this way, our language aims to enable students to gradually move from visual to textual programming in a comfortable manner.
keywords	Visual Programming; Structured Code; Teaching; Code Generation
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2012_059
id	ecaade2012_059
authors	Wurzer, Gabriel ; Popov, Nikolay ; Lorenz, Wolfgang E.
year	2012
title	Meeting Simulation Needs of Early-Stage Design Through Agent-Based Simulation
source	Achten, Henri; Pavlicek, Jiri; Hulin, Jaroslav; Matejovska, Dana (eds.), Digital Physicality - Proceedings of the 30th eCAADe Conference - Volume 1 / ISBN 978-9-4912070-2-0, Czech Technical University in Prague, Faculty of Architecture (Czech Republic) 12-14 September 2012, pp. 613-620.
doi	https://doi.org/10.52842/conf.ecaade.2012.1.613
wos	WOS:000330322400064
summary	During early-stage planning, numerous design decisions are taken in an argumentative manner, based on occupation with the building site according to the different infl uencing aspects (e.g. topology, wind, visibility, circulation, activities etc.). In this context, sketches, diagrams and spreadsheets are the workhorses for elaboration. However, some of these phenomena are dynamic by nature, and are rather poorly modeled when utilizing static media. In our work, we thus show how agent-based simulation can be used to compute and visualize dynamic factors, in order to inform the decision process on a qualitative level. As a matter of fact, simulations may be used as a design tool in their own right, for analysis and objectifi ed comparison among multiple design variations.
keywords	Agent-Based Simulation; Early-Stage Planning; NetLogo; Design Process.
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaadesigradi2019_315
id	ecaadesigradi2019_315
authors	Wurzer, Gabriel and Coraglia, Ugo Maria
year	2019
title	Refurb! - A tool allowing for iterative refurbishment
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 55-60
doi	https://doi.org/10.52842/conf.ecaade.2019.2.055
summary	Refurbishments and adaptations to existing building structures can be a challenging problem: Keeping track of all building measures (e.g. what walls, doors and installations to add or remove) is equally demanding as trying to keep an eye on the constraints (e.g. natural lighting) and functions that the changed structure will provide. It also demands a integrated view of the redesign (spatial aspect) and the refurbishment as a project (time aspect). To this end, we have been developing our planning tool "Refurb!", which lets a user plan refurbishments and adaptations to existing structures using a mixed metaphor of "CAD-tool + project plan", including a variety of analysis tools to compare the original state of a structure to the planned one (e.g. adjacency and circulation before and after adaptation). The tool is aimed at project planners and ranges from small scenarios (e.g. relocation/adaptation/refurbishment of a department) to big scenarios (e.g. relocation when bringing a hospital into service).
keywords	Refurbishment; Planning Tool; Cellular Automaton
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:57

_id	ecaade2016_018
id	ecaade2016_018
authors	Wurzer, Gabriel and Lorenz, Wolfgang E.
year	2016
title	SpaceBook - A Case Study of Social Network Analysis in Adjacency Graphs
source	Herneoja, Aulikki; Toni Österlund and Piia Markkanen (eds.), Complexity & Simplicity - Proceedings of the 34th eCAADe Conference - Volume 2, University of Oulu, Oulu, Finland, 22-26 August 2016, pp. 229-238
doi	https://doi.org/10.52842/conf.ecaade.2016.2.229
wos	WOS:000402064400022
summary	In this paper, we have adopted methods from Social Network Analysis in order to analyze adjacency graphs. Our intent was to uncover as much hidden structures as possible so as to improve adjacency requirements before they are used further on during the design process. To that end, we have conducted a case study using two readily available software packages (Gephi, Pajek), concluding that these could benefit from being more transparent about the underlying algorithms and more geared towards the problem domain 'adjacency analysis' when it comes to data entry and visualization. As a matter of fact, we produced an open-source prototype called SpaceBook, which customizes computation and visualization in the aforementioned spirit.
keywords	Adjacency Graph; Social Network Analysis
series	eCAADe
email
last changed	2022/06/07 07:57

_id	caadria2017_174
id	caadria2017_174
authors	Wurzer, Gabriel and Lorenz, Wolfgang
year	2017
title	Fracam - Cell Phone Application to Measure Box Counting Dimension
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. 725-734
doi	https://doi.org/10.52842/conf.caadria.2017.725
summary	There are two kinds of algorithms: those that are 'better' with respect to accuracy and those that are 'faster'. In the past, fractal analysis by means of box-counting - including both, binary and greyscale analysis - has been focused on the former. In our work, however, we want to aim at the second category: algorithms that are fast and easy to use, without losing view on significance. To this end we have devised a cell phone application which let users grasp and analyse photographs regarding the box-counting dimension of e.g. facades. The application includes two measurement methods for binary images, based on threshold conversions, and one for greyscale images. Accuracy has been tested on deterministic fractals with known fractal dimension. As a matter of fact we are able to produce what was formerly constraint to scientific implementations or discourse on every day's hardware.
keywords	Fractal analysis; Differential Box-counting; Fractal dimension; Cell phone application
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	ecaade2020_185
id	ecaade2020_185
authors	Wurzer, Gabriel, Lorenz, Wolfgang E., Forster, Julia, Bindreiter, Stefan, Lederer, Jakob, Gassner, Andreas, Mitteregger, Mathias, Kotroczo, Erich, Pöllauer, Pia and Fellner, Johann
year	2020
title	M-DAB - Towards re-using material resources of the city
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. 127-132
doi	https://doi.org/10.52842/conf.ecaade.2020.1.127
summary	If we strive for a de-carbonized future, we need to think of buildings within a city as resources that can be re-used rather than being disposed of. Together with considerations on refurbishment options and future building materials, this gives a decision field for stakeholders which depends on the current "building stock" - the set of pre-existing buildings which are characterized e.g. by building period, location and material composition. Changes in that context are hard to argue for since (1.) some depend on statistics, other (2.) on the concrete neighborhood and thus the space in which buildings are embedded, yet again others on (3.) future extrapolations again dealing with both of the aforementioned environments. To date, there exists no tool that can handle this back-and-forth between different abstraction levels and horizons in time; nor is it possible to pursue such an endeavor without a proper framework. Which is why the authors of this paper are aiming to provide one, giving a model of change in the context of re-using material resource of the city, when faced with numerous abstraction levels (spatial or abstract; past, current or future) which have feedback loops between them. The paper focuses on a concrete case study in the city of Vienna, however, chances are high that this will apply to every other building stock throughout the world if enough data is available. As a matter of fact, this approach will ensure that argumentation can happen on multiple levels (spatial, statistical, past, now and future) but keeps its focus on making the building stock of a city a resource for sustainable development.
keywords	material reuse; sustainability; waste reduction; Design and computation of urban and local systems – XS to XL; Health and materials in architecture and cities
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2013_086
id	ecaade2013_086
authors	Wurzer, Gabriel; Martens, Bob and Bühler, Katja
year	2013
title	3D Regular Expressions - Searching Shapes IN Meshes
source	Stouffs, Rudi and Sariyildiz, Sevil (eds.), Computation and Performance – Proceedings of the 31st eCAADe Conference – Volume 2, Faculty of Architecture, Delft University of Technology, Delft, The Netherlands, 18-20 September 2013, pp. 279-288
doi	https://doi.org/10.52842/conf.ecaade.2013.2.279
wos	WOS:000340643600028
summary	We have grown accustomed to performing elaborate queries on textual data, e.g. via online search engines, file system managers and word processors. In the past decade, retrieval methods that also work on non-textual data have become mainstream (e.g. face recognition software). Sadly, these developments have so far not caught on for data mining within geometrical data, e.g. 3D meshes generated in the course of architectural work. Specifically during data exchange, such a search functionality would be handy, as it often happens that geometry is exported but object identity is lost - think, for example, of generative geometry or exported BIM data. In this paper, we present an example of such a search functionality, based on angular search. Our method is inspired by regular expressions, a string matching technique commonly employed for matching substrings.
keywords	Shape retrieval; angular search; sub-mesh; regular expressions.
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2024_151
id	ecaade2024_151
authors	Wurzer, Gabriel; Salkic, Nirmala Maja; Lorenz, Wolfgang E.
year	2024
title	Visualizing Urban Transformations using a 3D Cellular Automaton
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 657–664
doi	https://doi.org/10.52842/conf.ecaade.2024.2.657
summary	Urban transformation is key to achieving more livable and sustainable cities. However, modelling this evolution is highly non-trivial since there are many factors at play that manifest themselves in the built (or: non-built/restored) environment. In our most recent work, we have represented urban change as rules of a three-dimensional Cellular Automaton. With these rules we represent a variety of retrofitting options - additive (e.g. densification through roof extensions, facade greening, installation of solar panels) or subtractive (e.g. soil descaling), that lead to urban change as an emergent outcome. The editing of rules is embedded into a web-based visualization which acts as a test-bed and platform we have used in a design studio setting and can thus report on our lessons learned in that context.
keywords	Cellular Automata, Urban Transformation, Web Tool
series	eCAADe
email
last changed	2024/11/17 22:05

_id	ddss9505
id	ddss9505
authors	Wyatt, Ray
year	1994
title	Strategic Decision Support: Using Neural Networks to Enhance and Explore Human Strategizing
source	Second Design and Decision Support Systems in Architecture & Urban Planning (Vaals, the Netherlands), August 15-19, 1994
summary	This paper focuses on a mechanism by which planners and designers are thought to reduce complexity. The mechanism involves choosing a potentially profitable direction of search, or choosing potentially profitable set of aims to pursue, within which a detailed solution might be found, and rejecting all potentially unprofitable directions of search. The literature of psychology, planning and operations research is drawn upon to argue that designers base such initial choice of direction on their candidate aims' relative scores for eight key parameters: probability, returns for effort, delay, robustness, difficulty, present satisfaction and dependence. The paper then describes a piece of decision support software which, by eliciting any user's scores for their candidate aims on the eight key parameters, is able to order such aims into a strategic plan. Such software also incorporates a simulated neural network which attempts to "learn", from users' recorded responses to the software-suggested strategies, how users actually weight the relative importances of the eight key parameters. That is, it is hoped that the neural network will "converge' to some prototypical pattern(s) of weightings. Having such a tool would certainly constitute an advance in the state of the art of computer-aided strategy development. Alternatively, if the network never converges, the use of neural networks in computer-aided planning is perhaps not advisable. Accordingly, a test was conducted in which a group of planners used the software to address a typical spatial problem. The results, in terms of whether or not the neural network converged, will be reported.
series	DDSS
email
last changed	2003/08/07 16:36

_id	cf2003_m_026
id	cf2003_m_026
authors	WYELD, Theodor G.
year	2003
title	An Object Server System for 3D Digital Design Collaboration
source	Digital Design - Research and Practice [Proceedings of the 10th International Conference on Computer Aided Architectural Design Futures / ISBN 1-4020-1210-1] Tainan (Taiwan) 13–15 October 2003, pp. 235-248
summary	Moving through and between computer generated 3D objects we experience a 'virtual world'. Virtual Worlds have created a dream-like landscape. They also have facilitated a paradigm shift for architects working with CAD tools where they now desire to “design three-dimensional spaces in an immersed way” (Strehlke and Engeli 2001). Architects are already working in computer-moderated collaborative networked organisations. A 3D Virtual World offers a different kind of collaboration. To understand how architects might design in an 'immersed way', three experiments are described. The experiments attempt to investigate how participants experience the 3D spaces within which they collaborated. In particular, the last experiment makes use of 'shared objects' in the scene. The software chosen to create these Virtual Worlds was VRML and JAVA due to their flexibility and rapid prototyping. Where VRML differs from most CAD languages is in its openness. This paper describes an object sharing client-server architecture based on a simple multi-user system providing navigation in CosmoPlayer 2.11 ported through Netscape. The Object Server System allows multiple clients, as avatars, and objects to be manipulated in a 3D Virtual World. The system updates the transforms of the objects explicitly allowing their transform values to be shared across multiple browser sessions.
keywords	collaboration, multi-user, object sharing
series	CAAD Futures
last changed	2003/09/22 12:21

_id	ijac20075213
id	ijac20075213
authors	Wyeld, Theodor G.; Carroll, Joti; Gibbons, Craig; Ledwich, Brendan; Leavy, Brett; Hills, James; Docherty, Michael
year	2007
title	Doing Cultural Heritage Using the Torque Game Engine: Supporting Indigenous Storytelling in a 3D Virtual Environment
source	International Journal of Architectural Computing vol. 5 - no. 2, pp. 418-435
summary	Digital Songlines (DSL) is an Australasian CRC for Interaction Design (ACID) project that is developing protocols, methodologies and toolkits to facilitate the collection, education and sharing of indigenous cultural heritage knowledge. This paper outlines the goals achieved over the last three years in the development of the Digital Songlines game engine (DSE) toolkit that is used for Australian Indigenous storytelling. The project explores the sharing of indigenous Australian Aboriginal storytelling in a sensitive manner using a game engine. The use of the game engine in the field of Cultural Heritage is expanding. They are an important tool for the recording and re-presentation of historically, culturally, and sociologically significant places, infrastructure, and artefacts, as well as the stories that are associated with them. The DSL implementation of a game engine to share storytelling provides an educational interface. Where the DSL implementation of a game engine in a CH application differs from others is in the nature of the game environment itself. It is modelled on the 'country' (the 'place' of their heritage which is so important to the clients' collective identity) and authentic fauna and flora that provides a highly contextualised setting for the stories to be told. This paper provides an overview on the development of the DSL game engine.
series	journal
last changed	2007/08/29 16:23

_id	sigradi2021_317
id	sigradi2021_317
authors	Xavier, Edemar, Silva, Adriane Borda Almeida da and Pires, Janice
year	2021
title	Digital Photogrammetry: For Playing With Historical Architecture Anamorphisms and For Seeking Authorship Traces
source	Gomez, P and Braida, F (eds.), Designing Possibilities - Proceedings of the XXV International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2021), Online, 8 - 12 November 2021, pp. 593–604
summary	The techniques of representation by digital photogrammetry and laser scanning make it possible to obtain accurate three-dimensional models and are necessary to support the production of documents about built heritage, a process that can trigger advances in knowledge concerning the represented object. Through these technologies, a study is carried out to generate information about two elements of the eclectic architecture of Pelotas, one of them, the half-dome of a Chapel, authored by José Isella, and the other, the skylight of a mansion, which still has unproven indicators regarding its authorship. An analysis of formal organization under a geometric approach whas used, to identify aspects as that cloud increase or refute personal doubt. The associative logic between the parts of the elements and the mastery in controlling the anamortic effects promoted by these elements increase the hypothesis that Isella is also responsible for the skylight design.
keywords	patrimônio arquitetônico, José Isella, anamorfismo, fotogrametria digital, jogo.
series	SIGraDi
email
last changed	2022/05/23 12:11

_id	caadria2017_005
id	caadria2017_005
authors	Xia, Tian, Koh, Jing Lin, Chen, Yutong, Goh, Yi Qian and Dritsas, Stylianos
year	2017
title	Form-finding with Robotics - Fusing Physical Simulation and Digital Fabrication
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. 893-902
doi	https://doi.org/10.52842/conf.caadria.2017.893
summary	We present an experimental digital design and fabrication process investigating the integration of form-finding and industrial robotics. The design process is inspired by classical experiments producing minimal surfaces and tensile structures via physical simulation. The fabrication process resembles thermoforming whereby sheets of PET material are heat treated and while in a malleable state, where the material behaves like stretchable fabric, an industrial articulated robotic arm impresses a form while the sheet is air cooled and its final shape becomes stable and rigid. The three-dimensional plastic sheets are used as molds for glass-reinforced concrete casting. The key aspects of our approach include: (a) Mold-less fabrication: the design of our robotic end-effector can produce a range of free-form geometries without need for complex mold making (b) Reusable and durable artifacts: unlike traditional physical form-finding processes where the derived form is often ephemeral or fragile our process affords the detachment of a rigid artifacts which can be digitized, used as-is or employed in (c) Multi-stage fabrication: as the form-found geometry can be directly used for processes such as casting with excellent results in terms of surface finish. We present the design and development of our system and its deployment for an installation artwork.
keywords	Form-Finding; Digital Fabrication; Architectural Robotics
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	caadria2020_172
id	caadria2020_172
authors	Xia, Xinyu and Tong, Ziyu
year	2020
title	A Machine Learning-Based Method for Predicting Urban Land Use
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. 21-30
doi	https://doi.org/10.52842/conf.caadria.2020.2.021
summary	Land use is one of the most basic elements of urban management. In urban planning and design, land use is often determined by experience and case studies. However, the development of urbanization has led to a combinatory trend for land use, and the land use of a plot is always impacted by the surrounding environment. In such a complex situation, it is difficult to find hidden relationships among types of land use by humans alone. Within artificial intelligence, machine learning can help find correlations among data. This paper presents a new method for learning the rules relating the known land use data and predicting the land use of a target plot by constructing an artificial neural network. We take Nanjing as a specific case and study the logic of its land use. The results not only demonstrate associations between the surroundings and the target but also show the feasibility of a combinatory land use index in urban planning and design.
keywords	Land use; Urban planning and design; Machine learning; Artificial neural network
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	caadria2020_028
id	caadria2020_028
authors	Xia, Yixi, Yabuki, Nobuyoshi and Fukuda, Tomohiro
year	2020
title	Development of an Urban Greenery Evaluation System Based on Deep Learning and Google Street View
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 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 783-792
doi	https://doi.org/10.52842/conf.caadria.2020.1.783
summary	Street greenery has long played a vital role in the quality of urban landscapes and is closely related to people's physical and mental health. In the current research on the urban environment, researchers use various methods to simulate and measure urban greenery. With the development of computer technology, the way to obtain data is more diverse. For the assessment of urban greenery quality, there are many methods, such as using remote sensing satellite images captured from above (antenna, space) sensors, to assess urban green coverage. However, this method is not suitable for the evaluation of street greenery. Unlike most remote sensing images, from a pedestrian perspective, urban street images are the most common view of green plants. The street view image presented by Google Street View image is similar to the captured by the pedestrian perspective. Thus it is more suitable for studying urban street greening. With the development of artificial intelligence, based on deep learning, we can abandon the heavy manual statistical work and obtain more accurate semantic information from street images. Furthermore, we can also measure green landscapes in larger areas of the city, as well as extract more details from street view images for urban research.
keywords	Green View Index; Deep Learning; Google Street View; Segmentation
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	ecaade2020_395
id	ecaade2020_395
authors	Xian, Ziju, Hoban, Nicholas and Peters, Brady
year	2020
title	Spatial Timber Assembly - Robotically Fabricated Reciprocal Frame Wall
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. 403-412
doi	https://doi.org/10.52842/conf.ecaade.2020.2.403
summary	Though highly robust and economical, traditional lamella and reciprocal structural systems cannot adapt to surfaces with complex double curvature; as the timber members are standardized with no variation. Recent research has explored the use of computation for design, structural optimization, and use of robotic systems for the automated fabrication of timber joints. The disconnection between fabrication and assembly makes the construction of non-uniform double-curved reciprocal frames challenging, due to the required precise placement of discrete members with compound angle butt joints. This project investigates the use of robotic fabrication to cut and assemble a timber reciprocal frame assembly. A computational model was created to generate the double-curved reciprocal frame geometry. Within this computational framework, joint analysis, fabrication, and assembly were monitored and adjusted to meet limiting factors. An industrial robot was implemented as a bridge between the computational model and the physical construction. This paper presents a number of novel computational and robotic fabrication techniques in designing, cutting, and positioning. These techniques were explored through the robotic fabrication and assembly of a demonstrator - a double-curved reciprocal frame wall.
keywords	Robotic Fabrication; Reciprocal Frame; Prototyping
series	eCAADe
email
last changed	2022/06/07 07:57

For more results click below: