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 483

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

_id	acadia18_20
id	acadia18_20
authors	Leach, Neil
year	2018
title	We Have Never Been Digital
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. 20-29
doi	https://doi.org/10.52842/conf.acadia.2018.020
summary	The recent debate about the nature of the “postdigital” prompts the question as to whether we have ever been digital. This article looks at Bruno Latour’s book We Have Never Been Modern (1993) and questions whether its logic could not also be transferred to the realm of the digital. The issue is not so much that much of what is called “digital” in fact refers to analog processes that are simply controlled by the digital. Nor is it simply that we are often not aware of what has been “digitally” produced. Rather, the issue is that many of our operations within the digital realm are still controlled by the designer and do not operate within an autonomous realm. The notion of a purely objective digital operation without any subjective intervention on the part of the designer is something of a myth. The paper concludes that we have never been digital, just as we have never been modern. As such, we might argue that the term “postdigital” makes little sense, in that we have never been digital in the first place.
keywords	full paper, hybrid practices, history/theory of computation, design history and theory
series	ACADIA
type	paper
email
last changed	2022/06/07 07:52

_id	sigradi2018_1875
id	sigradi2018_1875
authors	Kalantari, Cruze-Garza; Banner, Pamela; Contreras-Vidal, Jose Luis
year	2018
title	Computationally Analyzing Biometric Data and Virtual Response Testing in Evaluating Learning Performance of Educational Setting Through
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. 390-396
summary	Due to construction costs, the human effects of innovations in architectural design can be expensive to test. Post-occupancy studies provide valuable data about what did and did not work in the past, but they cannot provide direct feedback for new ideas that have not yet been attempted. This presents designers with something of a dilemma. How can we harness the best potential of new technology and design innovation, while avoiding costly and potentially harmful mistakes? The current research use virtual immersion and biometric data to provide a new form of extremely rigorous human-response testing prior to construction. The researchers’ hypothesis was that virtual test runs can help designers to identify potential problems and successes in their work prior to its being physically constructed. The pilot study aims to develop a digital pre-occupancy toolset to understand the impact of different interior design variables of learning environment (independent variables) on learning performance (dependent variable). This project provides a practical toolset to test the potential human impacts of architectural design innovations. The research responds to a growing call in the field for evidence-based design and for an inexpensive means of evaluating the potential human effects of new designs. Our research will address this challenge by developing a prototype mobile brain-body imaging interface that can be used in conjunction with virtual immersion.
keywords	Signal Processing; Brain; EEG; Virtual Reality; Big Data; Learning Performance
series	SIGRADI
email
last changed	2021/03/28 19:58

_id	ijac201816301
id	ijac201816301
authors	Rasmussen, Troels A. and Timothy Merritt
year	2018
title	ProjecTables: Augmented CNC tools for sustainable creative practices
source	International Journal of Architectural Computing vol. 16 - no. 3, 227-242
summary	Computer numerical control (CNC) cutting machines have become essential tools for designers and architects enabling rapid prototyping, model building, and production of high-quality components. Designers often cut from new materials, discarding the irregularly shaped remains. We introduce ProjecTables, a visual augmented reality system for interactive packing of model parts onto sheet materials. ProjecTables enables designers to (re)use scrap materials for computer numerical control cutting that would have been previously thrown away, at the same time supporting esthetic choices related to wood grain, avoiding surface blemishes, and other relevant material properties. We conducted evaluations of ProjecTables with design students from Aarhus School of Architecture, demonstrating that participants could quickly and easily place and orient model parts reducing material waste. Contextual interviews and ideation sessions led to a deeper understanding of current work practices and sustainability issues with computer numerical control cutting machines and identified useful features for interactive packing to reduce waste while supporting esthetic concerns for exhibition quality design projects.
keywords	Sustainability, fabrication, computer numerical control cutting machines, CNC cutting machines, visual augmentation, digital tools
series	journal
email
last changed	2019/08/07 14:03

_id	ecaade2018_155
id	ecaade2018_155
authors	Zupancic, Tadeja, Herneoja, Aulikki, Schoonjans, Yves and Achten, Henri
year	2018
title	A Research Framework of Digital Leadership
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. 641-646
doi	https://doi.org/10.52842/conf.ecaade.2018.1.641
summary	In leading architectural offices where digital technologies have become de facto part and parcel of the architectural design process, it has become pointless to talk about "architectural design" and "digital technology" as separate phenomena. In fact, those offices showcase advances in their designs through combined developments in process, tools, teams, materials, and research. Far from being a passive addition to conventional processes, digital technologies transform the whole spectrum of architectural endeavour. Architects and offices in the front of these development showcase a particular competence set that is distinct from others, which we propose to call "digital leadership." We define "digital leadership" as the "integration of distributed knowledge from social sciences/humanities and digital technologies through the integrative artistic power of Architectural Design applied to the built environment as a real-world research and design laboratory." Although there have been many digital pioneers since the early 1960'ies, we can now see digital leadership as a more mainstream movement. However, there is no unified framework or theoretical understanding of digital leadership. In this paper we report on work carried out on four universities which has the aim to build such a framework.
keywords	Digital leadership; Architectural design process; Collaborative environments; Digital ecologies; Human resources
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2018_124
id	ecaade2018_124
authors	Asanowicz, Aleksander
year	2018
title	Digital Architectural Composition in Virtual Space
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. 703-710
doi	https://doi.org/10.52842/conf.ecaade.2018.2.703
summary	The paper is divided into two main parts. The first part refers to the history of attempts to use VR technology in the process of architectural space creation in a dynamic way. The second part presents the experiment carried out at our Faculty, in which we implemented VR in the Digital Architectural Composition course. This experiment was divided into two parts. In the both parts Google Blocks software was used. In the first part we have used the first exercises which was completed by students during the first semester in a traditional way (a cardboard mock-up) and then in the third semester as a digital model in Cinema 4D. It was a Solid form with. In the second part of this experiment we asked students to create a sketch of walk through space and they can created their own shapes in their design. The analysis of the results allows to formulate the thesis that there is a qualitative revolution in the area of human-computer interface. The main conclusion is that Virtual Reality eliminates the boundaries between the spectator and the space and that the idea - Designing Become a Place" is still actual.
keywords	Architectural composition; virtual reality; direct design
series	eCAADe
email
last changed	2022/06/07 07:54

_id	acadia18_176
id	acadia18_176
authors	Bidgoli, Ardavan; Veloso,Pedro
year	2018
title	DeepCloud. The Application of a Data-driven, Generative Model in Design
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. 176-185
doi	https://doi.org/10.52842/conf.acadia.2018.176
summary	Generative systems have a significant potential to synthesize innovative design alternatives. Still, most of the common systems that have been adopted in design require the designer to explicitly define the specifications of the procedures and in some cases the design space. In contrast, a generative system could potentially learn both aspects through processing a database of existing solutions without the supervision of the designer. To explore this possibility, we review recent advancements of generative models in machine learning and current applications of learning techniques in design. Then, we describe the development of a data-driven generative system titled DeepCloud. It combines an autoencoder architecture for point clouds with a web-based interface and analog input devices to provide an intuitive experience for data-driven generation of design alternatives. We delineate the implementation of two prototypes of DeepCloud, their contributions, and potentials for generative design.
keywords	full paper, design tools software computing + gaming, ai & machine learning, generative design, autoencoders
series	ACADIA
type	paper
email
last changed	2022/06/07 07:52

_id	caadria2018_278
id	caadria2018_278
authors	Caetano, In?s, Ilunga, Guilherme, Belém, Catarina, Aguiar, Rita, Feist, Sofia, Bastos, Francisco and Leit?o, António
year	2018
title	Case Studies on the Integration of Algorithmic Design Processes in Traditional Design Workflows
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. 111-120
doi	https://doi.org/10.52842/conf.caadria.2018.1.111
summary	Algorithmic design processes have enormous potential for architecture. Even though some large design offices have already incorporated such processes in their workflow, so far, these have not been seriously considered by the large majority of traditional small-scale studios. Nevertheless, as the integration of algorithmic techniques inside architectural studios does not require mastering programming skills, but rather taking advantage of a collaborative design process, small design studios are therefore able of using such strategies within their workflow. This paper discusses a series of challenges presented by one of these studios, where we had to integrate algorithmic design processes with the studio's traditional workflow.
keywords	Collaborative design; Algorithmic design; Design strategies; Design workflow processes
series	CAADRIA
email
last changed	2022/06/07 07:54

_id	sigradi2018_1749
id	sigradi2018_1749
authors	Canavezzi de Abreu, Sandro
year	2018
title	Hidra System(!) in the tension between Internet of Things and Virtual Reality: programming meta-objects
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. 908-913
summary	We will characterize the relationship between Internet of Things (IOT) and Virtual Reality (VR) as the tension between analog and digital domains, organized by several interfaces specifically developed for this study, during de course Interactive Architecture at the Architecture School - UFMG. These interfaces, referred here as programmable meta-objects (MOPs), recombine themselves to form an environment where inputs and outputs of each MOP are made available to other networked MOPs through the Hydra System (!). These MOPs can have both a physical existence (object present in physical space) and a "virtual" existence (it exists in the Virtual Reality environment).
keywords	Virtual Reality; Internet of Things; Combinatorial; Meta-objects; Programmable
series	SIGRADI
email
last changed	2021/03/28 19:58

_id	caadria2021_089
id	caadria2021_089
authors	Cristie, Verina, Ibrahim, Nazim and Joyce, Sam Conrad
year	2021
title	Capturing and Evaluating Parametric Design Exploration in a Collaborative Environment - A study case of versioning for parametric design
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 131-140
doi	https://doi.org/10.52842/conf.caadria.2021.2.131
summary	Although parametric modelling and digital design tools have become ubiquitous in digital design, there is a limited understanding of how designers apply them in their design processes (Yu et al., 2014). This paper looks at the use of GHShot versioning tool developed by the authors (Cristie & Joyce, 2018; 2019) used to capture and track changes and progression of parametric models to understand early-stage design exploration and collaboration empirically. We introduce both development history graph-based metrics (macro-process) and parametric model and geometry change metric (micro-process) as frameworks to explore and understand the captured progression data. These metrics, applied to data collected from three cohorts of classroom collaborative design exercises, exhibited students' distinct modification patterns such as major and complex creation processes or minor parameter explorations. Finally, with the metrics' applicability as an objective language to describe the (collaborative) design process, we recommend using versioning for more data-driven insight into parametric design exploration processes.
keywords	Design exploration; parametric design; history recording; version control; collaborative design
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	caadria2018_333
id	caadria2018_333
authors	Cupkova, Dana, Byrne, Daragh and Cascaval, Dan
year	2018
title	Sentient Concrete - Developing Embedded Thermal and Thermochromic Interactions for Architecture and Built Environment
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. 545-554
doi	https://doi.org/10.52842/conf.caadria.2018.2.545
summary	Historically, architectural design focused on adaptation of built environment to serve human needs. Recently embedded computation and digital fabrication have advanced means to actuate physical infrastructure in real-time. These 'reactive spaces' have typically explored movement and media as a means to achieve reactivity and physical deformation (Chatting et al. 2017). However, here we recontextualize 'reactive' as finding new mechanisms for permanent and non-deformable everyday materials and environments. In this paper, we describe our ongoing work to create a series of complex forms - modular concrete panels - using thermal, tactile and thermochromic responses controlled by embedded networked system. We create individualized pathways to thermally actuate these surfaces and explore expressive methods to respond to the conditions around these forms - the environment, the systems that support them, their interaction and relationships to human occupants. We outline the design processes to achieve thermally adaptive concrete panels, illustrate interactive scenarios that our system enables, and discuss opportunities for new forms of interactivity within the built environment.
keywords	Responsive environments; Geometrically induced thermodynamics; Ambient devices; Internet of things; Modular electronic systems
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	ecaade2018_433
id	ecaade2018_433
authors	Daher, Elie, Kubicki, Sylvain and Pak, Burak
year	2018
title	Participation-based Parametric Design in Early Stages - A participative design process for spatial planning in office building
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. 429-438
doi	https://doi.org/10.52842/conf.ecaade.2018.1.429
summary	The term participation has been used to define different activities, such as civil debate, communication, consultation, delegation, self-help construction, political decisions. However, participation in design started from the idea that individuals whom being affected by a design project must contribute to the design process. Recently, designers have been moving closer to the future users and developing new ways to empower them to get involved in the design process. In this paper we rethink the way the early design process is developed in a participatory approach thanks to parametric methods. A use case is proposed showing the potential of parametric design methods to empower the participation of users in the design of their facilities. The use case is dealing in particular with the spatial planning of an office building where the users together with the spatial planning team are able to design the layout spatial configuration by 1) fixing the objectives, 2) manipulating the model, 3)modifying some parameters, 4) visualizing the iterations and evaluating in a real-time each solution in an interactive 3D environment and together with facility managers 5) choosing the configuration of the spatial layout.
keywords	Computational design; Participatory design; Optimization ; Parametric design
series	eCAADe
email
last changed	2022/06/07 07:56

_id	sigradi2018_1879
id	sigradi2018_1879
authors	Danesh Zand, Foroozan; Baghi, Ali; Kalantari, Saleh
year	2018
title	Digitally Fabricating Expandable Steel Structures Using Kirigami Patterns
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. 724-731
summary	This article presents a computational approach to generating architectural forms for large spanning structures based on a “paper-cutting” technique. In this traditional artform, a flat sheet is cut and scored in such a way that a small application of force prompts it to expand into a three-dimensional structure. To make these types of expandable structures feasible at an architectural scale, four challenges had to be met during the research. The first was to map the kinetic properties of a paper-cut model, investigating formative parameters such as the width and frequency of cuts to determine how they affect the resulting structure. The second challenge was to computationally simulate the paper-cut structure in an accurate fashion. We accomplished this task using finite element analysis in the Ansys software platform. The third challenge was to create a prediction model that could precisely forecast the characteristics of a paper-cutting pattern. We made significant strides in this demanding task by using a data-mining approach and regression analysis through 400 simulations of various cutting patterns. The final challenge was to verify the efficiency and accuracy of our prediction model, which we accomplished through a series of physical prototypes. Our resulting computational paper-cutting system can be used to estimate optimal cutting patterns and to predict the resulting structural characteristics, thereby providing greater rigor to what has previously been an ad-hoc and experimental design approach.
keywords	Transformable Paper-cut; Design method; Prediction Model; Regression analysis; Physical prototype
series	SIGRADI
email
last changed	2021/03/28 19:58

_id	sigradi2018_1261
id	sigradi2018_1261
authors	de Mendonça Peixoto, Irene; de Souza, Felipe; de Pontes, José Carlos
year	2018
title	Artist´s book Poor Fish Memories in digital version
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. 1098-1104
summary	The passages and combinations between analog and digital languages point to issues that have persisted for decades and which continue to foster contemporary, ethical and aesthetic debates about experience and temporality. Problematizing these questions, we extend the discussion to the importance of contemporary design to adopt creative strategies that articulate thoughts from other areas of knowledge, such as philosophy and art, from the perspective of multiplicity of mediums. The intention is to oxygenate classic design issues, such as conception, form creation, and user interaction, through the provocative sensory and temporal displacements that artistic creation promotes.
keywords	Art; Design; Aesthetic experience; Temporality
series	SIGRADI
email
last changed	2021/03/28 19:58

_id	ecaade2018_226
id	ecaade2018_226
authors	Dounas, Theodoros and Lombardi, Davide
year	2018
title	A CAD-Blockchain Integration Strategy for Distributed Validated Digital Design - Connecting the Blockchain
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. 223-230
doi	https://doi.org/10.52842/conf.ecaade.2018.1.223
summary	We present a proof of concept implementation of an integration strategy for connecting CAD with Blockchain. We explain the components of most blockchains and the value they bring to the built environment ecosystem, the potential impact a complete integration might have and we demonstrate the first two of four levels of integration we have identified between CAD and blockchain technologies. For the purposes of the paper we use Rhino / Grasshopper and Ethereum as the two components of integration.
keywords	Blockchain; Cryptography; CAD; BIM; distributed ledgers; cryptocoin; distributed CAD
series	eCAADe
email
last changed	2022/06/07 07:55

_id	cdrf2023_526
id	cdrf2023_526
authors	Eric Peterson, Bhavleen Kaur
year	2023
title	Printing Compound-Curved Sandwich Structures with Robotic Multi-Bias Additive Manufacturing
source	Proceedings of the 2023 DigitalFUTURES The 5st International Conference on Computational Design and Robotic Fabrication (CDRF 2023)
doi	https://doi.org/https://doi.org/10.1007/978-981-99-8405-3_44
summary	A research team at Florida International University Robotics and Digital Fabrication Lab has developed a novel method for 3d-printing curved open grid core sandwich structures using a thermoplastic extruder mounted on a robotic arm. This print-on-print additive manufacturing (AM) method relies on the 3d modeling software Rhinoceros and its parametric software plugin Grasshopper with Kuka-Parametric Robotic Control (Kuka-PRC) to convert NURBS surfaces into multi-bias additive manufacturing (MBAM) toolpaths. While several high-profile projects including the University of Stuttgart ICD/ITKE Research Pavilions 2014–15 and 2016–17, ETH-Digital Building Technologies project Levis Ergon Chair 2018, and 3D printed chair using Robotic Hybrid Manufacturing at Institute of Advanced Architecture of Catalonia (IAAC) 2019, have previously demonstrated the feasibility of 3d printing with either MBAM or sandwich structures, this method for printing Compound-Curved Sandwich Structures with Robotic MBAM combines these methods offering the possibility to significantly reduce the weight of spanning or cantilevered surfaces by incorporating the structural logic of open grid-core sandwiches with MBAM toolpath printing. Often built with fiber reinforced plastics (FRP), sandwich structures are a common solution for thin wall construction of compound curved surfaces that require a high strength-to-weight ratio with applications including aerospace, wind energy, marine, automotive, transportation infrastructure, architecture, furniture, and sports equipment manufacturing. Typical practices for producing sandwich structures are labor intensive, involving a multi-stage process including (1) the design and fabrication of a mould, (2) the application of a surface substrate such as FRP, (3) the manual application of a light-weight grid-core material, and (4) application of a second surface substrate to complete the sandwich. There are several shortcomings to this moulded manufacturing method that affect both the formal outcome and the manufacturing process: moulds are often costly and labor intensive to build, formal geometric freedom is limited by the minimum draft angles required for successful removal from the mould, and customization and refinement of product lines can be limited by the need for moulds. While the most common material for this construction method is FRP, our proof-of-concept experiments relied on low-cost thermoplastic using a specially configured pellet extruder. While the method proved feasible for small representative examples there remain significant challenges to the successful deployment of this manufacturing method at larger scales that can only be addressed with additional research. The digital workflow includes the following steps: (1) Create a 3D digital model of the base surface in Rhino, (2) Generate toolpaths for laminar printing in Grasshopper by converting surfaces into lists of oriented points, (3) Generate the structural grid-core using the same process, (4) Orient the robot to align in the direction of the substructure geometric planes, (5) Print the grid core using MBAM toolpaths, (6) Repeat step 1 and 2 for printing the outer surface with appropriate adjustments to the extruder orientation. During the design and printing process, we encountered several challenges including selecting geometry suitable for testing, extruder orientation, calibration of the hot end and extrusion/movement speeds, and deviation between the computer model and the physical object on the build platen. Physical models varied from their digital counterparts by several millimeters due to material deformation in the extrusion and cooling process. Real-time deviation verification studies will likely improve the workflow in future studies.
series	cdrf
email
last changed	2024/05/29 14:04

_id	ecaade2018_190
id	ecaade2018_190
authors	Gless, Henri-Jean, Halin, Gilles and Hanser, Damien
year	2018
title	Need of a BIM-agile Coach to Oversee Architectural Design - From one pedagogical experiment to another
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. 445-450
doi	https://doi.org/10.52842/conf.ecaade.2018.1.445
summary	This paper is part of our research on the digital transition in architecture, and more particularly on the integration of BIM (Building Information Management) technology. Indeed, in the field of AEC in France, this transition is still ongoing and remains difficult for architects. BIM technology changes the way people work and communicate, and remains only a tool without a method behind it. His arrival then raises technical but also human questions. Our research then turns to the social sciences and project management sciences to see if the creation or adaptation of project management methods can facilitate this integration. In other fields such as industry, software engineering, or HMI design, we have seen the emergence of agile methods that focus more on design teams, and therefore communication, than on the process itself. After experimenting with several agile practices, we identified the need for a design team to be mentored by someone in the role of facilitator or coach. This article describes how we can transfer to students an agile practice called BIM-agile Coach that we experimented during a weeklong workshop.
keywords	Architectural design; Agile methods; Agile practices; BIM technology; Collaborative design; Project management
series	eCAADe
email
last changed	2022/06/07 07:51

_id	acadia20_382
id	acadia20_382
authors	Hosmer, Tyson; Tigas, Panagiotis; Reeves, David; He, Ziming
year	2020
title	Spatial Assembly with Self-Play Reinforcement Learning
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 382-393.
doi	https://doi.org/10.52842/conf.acadia.2020.1.382
summary	We present a framework to generate intelligent spatial assemblies from sets of digitally encoded spatial parts designed by the architect with embedded principles of prefabrication, assembly awareness, and reconfigurability. The methodology includes a bespoke constraint-solving algorithm for autonomously assembling 3D geometries into larger spatial compositions for the built environment. A series of graph-based analysis methods are applied to each assembly to extract performance metrics related to architectural space-making goals, including structural stability, material density, spatial segmentation, connectivity, and spatial distribution. Together with the constraint-based assembly algorithm and analysis methods, we have integrated a novel application of deep reinforcement (RL) learning for training the models to improve at matching the multiperformance goals established by the user through self-play. RL is applied to improve the selection and sequencing of parts while considering local and global objectives. The user’s design intent is embedded through the design of partial units of 3D space with embedded fabrication principles and their relational constraints over how they connect to each other and the quantifiable goals to drive the distribution of effective features. The methodology has been developed over three years through three case study projects called ArchiGo (2017–2018), NoMAS (2018–2019), and IRSILA (2019-2020). Each demonstrates the potential for buildings with reconfigurable and adaptive life cycles.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	acadia18_156
id	acadia18_156
authors	Huang, Weixin; Zheng, Hao
year	2018
title	Architectural Drawings Recognition and Generation through Machine Learning
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. 156-165
doi	https://doi.org/10.52842/conf.acadia.2018.156
summary	With the development of information technology, the ideas of programming and mass calculation were introduced into the design field, resulting in the growth of computer- aided design. With the idea of designing by data, we began to manipulate data directly, and interpret data through design works. Machine Learning as a decision making tool has been widely used in many fields. It can be used to analyze large amounts of data and predict future changes. Generative Adversarial Network (GAN) is a model framework in machine learning. It’s specially designed to learn and generate output data with similar or identical characteristics. Pix2pixHD is a modified version of GAN that learns image data in pairs and generates new images based on the input. The author applied pix2pixHD in recognizing and generating architectural drawings, marking rooms with different colors and then generating apartment plans through two convolutional neural networks. Next, in order to understand how these networks work, the author analyzed their framework, and provided an explanation of the three working principles of the networks, convolution layer, residual network layer and deconvolution layer. Lastly, in order to visualize the networks in architectural drawings, the author derived data from different layer and different training epochs, and visualized the findings as gray scale images. It was found that the features of the architectural plan drawings have been gradually learned and stored as parameters in the networks. As the networks get deeper and the training epoch increases, the features in the graph become more concise and clearer. This phenomenon may be inspiring in understanding the designing behavior of humans.
keywords	full paper, design study, generative design, ai + machine learning, ai & machine learning
series	ACADIA
type	paper
email
last changed	2022/06/07 07:49

_id	caadria2018_161
id	caadria2018_161
authors	Huang, Xiaoran, White, Marcus and Burry, Mark
year	2018
title	Design Globally, Immerse Locally - A Synthetic Design Approach by Integrating Agent Based Modelling with Virtual Reality
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. 473-482
doi	https://doi.org/10.52842/conf.caadria.2018.1.473
summary	The last three decades have witnessed the explosion of technology and its impact on the architecture discipline which has drastically changed the methods of design. New techniques such as Agent-based modeling (ABM) and Virtual Reality (VR) have been widely implemented in architectural and urban design domains, yet the potential integration between these two methods remains arguably unexploited. The investigation in this paper aims to probe the following questions: How can architects and urban designers be informed more comprehensively by melding ABM and VR techniques at the preliminary/conceptual design stage? Which platform is considered more appropriate to facilitate a user-friendly system and reduces the steep learning curve? And what are the potential benefits of this approach in architectural education, particularly for the design studio environment? With those questions, we proposed a prototype in Unity, a multi-platform development tool that originated from the game industry, to simulate and visualize pedestrian behaviors in urban environments with immersive design experience and tested it in a scenario-based case study. This approach has also been further tested in an architectural design studio, demonstrating its technical feasibility as well as the potential contributions to the pedagogy.
keywords	Agent based modelling; Virtual Reality; Urban Design
series	CAADRIA
email
last changed	2022/06/07 07:49

_id	ecaade2018_w02
id	ecaade2018_w02
authors	Jabi, Wassim and Aish, Robert
year	2018
title	Non-manifold Topology for Architectural and Engineering Modelling
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. 57-60
doi	https://doi.org/10.52842/conf.ecaade.2018.1.057
summary	Non-manifold topology (NMT) allows the user to construct light-weight conceptual spatial architectural models which define the overall enclosure and the internal cellular division within that enclosure. The objective of this workshop is to give participants hands-on opportunities with a new software library that we have been developing under a research grant from the Leverhulme Trust. On the first day, the concepts of non-manifold topology will be introduced, including non-regular modelling operations. On the second day, we will introduce two plug-ins, which have been interfaced to our NMT tools: a) building energy simulation using OpenStudio and EnergyPlus and b) structural analysis software.
keywords	Non-manifold topology; Visual data flow programming; Building performance simulation; Computational design
series	eCAADe
email
last changed	2022/06/07 07:50

For more results click below: