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 725

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

_id	ecaade2023_247
id	ecaade2023_247
authors	Wang, Jinyu, Huang, Chenyu, Zhu, Elaine, Shen, Yanting, Yao, Jiawei, Shi, Hang and Peng, Rui
year	2023
title	Enhanced Crowd-Driven Retail Counter Layout Design Using Generative Adversarial Network
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 511–518
doi	https://doi.org/10.52842/conf.ecaade.2023.2.511
summary	In the design of retail counter layout, visitor flow is crucial as it greatly impacts the product exposure, sales expectation, and shopping experience. These factors can be expressed through crowd flow-related indicators, including flow speed, acceleration, visit count, and demand fulfillment degree. Although these indicators can be obtained through crowd simulation and be optimized with genetic algorithm, layout optimization may require hundreds of iterations. This means that simulation can take a long time, hindering the efficiency of layout optimization. To address this issue, we accelerated simulation through a surrogate model and proposed a data-driven layout design and optimization workflow. Firstly, we generalized common plan in the real world and designed an automatic generative parametric model to generate random layouts. Next, we obtained multiple crowd flow-related indicators through batch simulation with PedSim Pro. We then collected data and trained a generative adversarial network (GAN) as a surrogate model to capture the relationship between multiple indicators at different positions of regions of interest and the geometric features of counter layout. The trained model can be used with genetic algorithms for automatic optimization to assist designers in obtaining the best layout. Compared to crowd simulation, our trained GAN model is hundreds of times faster in predicting crowd flow-related indicators and has a high predictive accuracy performance with R2=0.7. The proposed workflow can significantly improve the optimization process in retail counter layout design.
keywords	Retail Layout Optimization, Crowd Flow Simulation and Prediction, Generative Adversarial Network
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2023_403
id	caadria2023_403
authors	Kim, Jong Bum, Kim, Seongchan and Aman, Jayedi
year	2023
title	An Urban Building Energy Simulation Method Integrating Parametric BIM and Machine Learning
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 665–674
doi	https://doi.org/10.52842/conf.caadria.2023.1.665
summary	This research investigates a method of urban building energy simulation (UBES) by integrating Building Information Modeling (BIM), building simulation, and algorithm-based prediction to forecast the impact of surrounding conditions. In the urban context, building energy performances are determined not only by the individual building design but also by the building's surrounding context. Many energy performances are sensitive to outdoor and surrounding building conditions, such as neighbouring building volumes, heights, and spaces between buildings. However, such surrounding conditions were overlooked because they can exponentially increase the complexity of urban modeling and simulation. In that regard, the research sought to investigate a novel framework to take advantage of accurate performance simulations and algorithm-based fast predictions. This paper presents our UBES method implemented from three research phases: (i) building a parametric urban model in BIM to provide simulation inputs, (ii) creating a parametric simulation interface to produce training and validation data, and (iii) creating a prediction interface using a Support Vector Machine (SVR) algorithm. Lastly, the paper elaborates on the findings from the prediction results.
keywords	Urban Energy Simulation, Solar Accessibility, Surrounding Conditions, Parametric BIM, Machine Learning, Support Vector Machine, Sustainable Cities and Communities
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	ijac202321302
id	ijac202321302
authors	Ortner, F Peter; Jing Zhi Tay
year	2023
title	Exploring a circular economy solution space A comparative study to develop automated optimisation workflows supported by machine learning for circular design problems
source	International Journal of Architectural Computing 2023, Vol. 21 - no. 3, 404–420
summary	Embedding circular economy (CE) principles in early design requires iterative evaluation across multiple lifecycle phases, with trade-offs between objectives complicating the identification of best solutions. This paper puts forward methods to automatically discover diverse, yet well-performing solution types within complex multi-objective CE design optimisation models. Working with a parametric model derived from a furniture design for CE case study, a comparison is made between weighted-sum single objective optimisation and multi-objective optimisation augmented with clustered solution types targeted by the reference pointbased NSGA-II optimisation algorithm. Efficiency of optimisation, quality of results and distinctiveness of solution types presented by each method is compared in an effort to understand which will best assist designers to manage complexity in CE design. The generalisability of the presented methods to larger scale CE design problems is discussed and future areas of work on computational design for CE are extrapolated from the presented results
keywords	Circular economy, machine learning, optimisation, computational design, sustainability
series	journal
last changed	2024/04/17 14:30

_id	ijac202321207
id	ijac202321207
authors	Sebestyen, Adam; Hirschberg, Urs; Rasoulzadeh, Shervin
year	2023
title	Using deep learning to generate design spaces for architecture
source	International Journal of Architectural Computing 2023, Vol. 21 - no. 2, 337–357
summary	We present an early prototype of a design system that uses Deep Learning methodology—Conditional Variational Autoencoders (CVAE)—to arrive at custom design spaces that can be interactively explored using semantic labels. Our work is closely tied to principles of parametric design. We use parametric models to create the dataset needed to train the neural network, thus tackling the problem of lacking 3D datasets needed for deep learning. We propose that the CVAE functions as a parametric tool in itself: The solution space is larger and more diverse than the combined solution spaces of all parametric models used for training. We showcase multiple methods on how this solution space can be navigated and explored, supporting explorations such as object morphing, object addition, and rudimentary 3D style transfer. As a test case, we implemented some examples of the geometric taxonomy of “Operative Design” by Di Mari and Yoo.
keywords	deep learning, generative methods, parametric design, design space, 3D object generation, variational autoencoder, operative design, artificial intelligence, machine learning, voxels
series	journal
last changed	2024/04/17 14:30

_id	ijac202321411
id	ijac202321411
authors	Khodadadi, Anahita
year	2023
title	A Generative Design Exploration Methodology for Integration of Structural, Environmental, and User Agencies in an Early Design Stage
source	International Journal of Architectural Computing 2023, Vol. 21 - no. 4, 757-780
summary	This article presents a generative design exploration methodology utilized to assist designers in problem structuring and decision-making in a multi-disciplinary setting. This novel design exploration methodology is based on the hybridization of a genetic algorithm (GA) and the Theory of Innovative Problem Solving (TRIZ). This methodology allows investigation of unexpected solutions, application of innovative ideas for resolving contradictory design objectives, and continuous interaction between designers and the search engine. In this study, the design case of a mid-rise apartment complex is used to examine the capacity of the proposed multi-agent design exploration method. Accordingly, both quality and numeric performance-based values of the design alternatives, including the visual appearance of the complex and apartments’ shadows over one another, structural and energy efficiency, and life-cycle impact of the building’s structural system, are investigated to demonstrate the usability and benefits of the developed method.
keywords	Conceptual design, design exploration, TRIZ, genetic algorithm, multi-objective design, Cross-Laminated Timber (CLT) plates, informed decision-making, life-cycle assessment
series	journal
last changed	2024/04/17 14:30

_id	caadria2023_340
id	caadria2023_340
authors	Kimm, Geoff, White, Marcus and Burry, Mark
year	2023
title	Extending Visuospatial Analysis in Design Computing: An Exploration With a Novel GPU-Based Algorithm and Form-Based Codes
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 655–664
doi	https://doi.org/10.52842/conf.caadria.2023.1.655
summary	This paper responds to a gap observed between the contemporary capacity for calculation and analysis of visibility of built environment features, such as buildings, in digital urban and architectural computational research models and the functionality of off-the-shelf software tools available to professionals. The research investigates the potential of visibility analysis to be embedded and extended within computational-based workflows of software tools to better meet urban design and planning industry needs. We introduce a novel method for visibility calculation that exposes output data for further analysis within a computational workflow and implement it in a game development engine used by software tool providers. Based in our engagement with a local government authority, we then use that method to demonstrate a workflow in the context of form-based building codes in which the visual impact of a building is considered rather than prescriptive limits on dimensions and use. Our results indicate the novel method has substantial performance improvements compared to an alternative mode of visibility calculation and that software providers could more thoroughly integrate and extend visibility analysis to meet industry needs.
keywords	design computing, viewsheds, isovists, GPU shader, Unity 3D, genetic algorithm, generative design, form-based building codes
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	caadria2023_1
id	caadria2023_1
authors	Koh, Immanuel
year	2023
title	AI-Bewitched Architecture of Hansel and Gretel: Food-to-Architecture in 2D & 3D with GANs and Diffusion Models
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 9–18
doi	https://doi.org/10.52842/conf.caadria.2023.1.009
summary	Architects such as Le Corbusier, Frank Gehry, Aldo Rossi, and Greg Lynn have implicitly turned culinary formalism into architectural formalism during their careers. How might AI assist in a similar act of bisociation (or conceptual blending)? The paper is the first to explore this food2architecture bisociation explicitly, and specifically with generative adversarial networks (GANs) such as CycleGAN and VQGAN-CLIP, and diffusion models such as OpenAI’s DALL-E 2, Midjourney and DreamFusion (using Stable Diffusion). Instead of using textual input prompts to generate images of architecture only with the discipline’s own vocabulary, the research merges them with the vocabulary of food, thus exploiting their potential in blending their respective conceptual and formal characteristics. While these diffusion models have recently been used by the general public to generate 2D imagery posts on various social media platforms, no existing work has conducted a detailed and systematic analysis on their exclusive capacity in bisociating food and architecture. Imagery outputs generated during two workshops involving 150 designers and non-designers are included here as illustrations. Beginning and ending the paper with the all-familiar fairy tale of the gingerbread house, the research explores the creative design bisociative affordance of today's text-to-image and text-to-3D models by turning culinary inputs into architectural outputs -- envisioning an explicitly computational version of the implicit 'food2architecture' mental models plausibly used by some of the most creative architects.
keywords	Deep Learning, Midjourney, DALL-E 2, DreamFusion, Stable Diffusion, GANs
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	sigradi2023_161
id	sigradi2023_161
authors	Portillo, Juan Pablo and Flores, Luis
year	2023
title	Heritage parametric modeling
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 277–288
summary	The study focuses on the digital documentation and geometric modeling of the Susana Soca Chapel, an architectural masterpiece designed by Antonio Bonet in Uruguay. The chapel is known for its unique geometric form composed of equilateral triangles, and it holds significant historical and cultural value. The research utilizes advanced digital technologies such as laser scanning and photogrammetry to capture the three-dimensional data of the chapel. The model is then analyzed to establish compositional rules and generate a new model using Dynamo Revit and parametric design techniques. The results include a high-quality point cloud model, facilitating the exploration of generative design principles. The discussion highlights the use of non-explicit modeling tools in architecture, emphasizing the need to understand the underlying geometric principles that govern the creation of complex spatial compositions. The research aims to establish guidelines and protocols for the digital documentation and algorithmic design of architectural landmarks, presenting a challenging yet promising proposition in the field.
keywords	Digital heritage, Dynamo, Point cloud, Parametric design, 3D scanning
series	SIGraDi
email
last changed	2024/03/08 14:06

_id	sigradi2023_365
id	sigradi2023_365
authors	Shimabukuro, Paulo
year	2023
title	Urban Design Sustainability Through AI and Genetic Algorithms: San Felipe Case Study
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 1749–1760
summary	The research explores urban generative design in the San Felipe Residential Area using genetic algorithms, machine learning, and neural networks. Three urban scenarios are evaluated. The MEPS method (Spatial Metrics, Prediction and Segmentation) is introduced to analyze urban patterns and predict activities, producing an optimized pre-design whose urban spatial characteristics contribute to the sustainability of cities by maximizing their resources and minimizing their environmental impact.
keywords	Machine Learning, Neural Networks, Genetic Algorithms, Architectural Optimization, MEPS Method
series	SIGraDi
email
last changed	2024/03/08 14:09

_id	ascaad2023_077
id	ascaad2023_077
authors	Tabassum, Nusrat; Duarte, Jose; Nazarian, Shadi
year	2023
title	Advancing 3D Concrete Printing for Affordable Housing: A Shape Grammar-Based Approach to Print Spanning Roof Structures
source	C+++: Computation, Culture, and Context – Proceedings of the 11th International Conference of the Arab Society for Computation in Architecture, Art and Design (ASCAAD), University of Petra, Amman, Jordan [Hybrid Conference] 7-9 November 2023, pp. 344-364.
summary	3D concrete printing (3DCP) technology is expected to address the construction industry's inefficiency, lack of skilled labor, and safety concerns, while tackling the housing shortage due to global population growth. Current applications in academia and industry have mainly focused on fabricating wall elements, which do not fulfill the potential of this technology to fully automate the construction process, including enclosures. In concrete construction, formwork is an essential part that fundamentally influences labor needs, quality, time, and cost. Many building components, such as walls, beams, columns, and prefabricated blocks, have been successfully printed without formwork using various additive manufacturing (AM) techniques for 3DCP. However, due to a 60-degree printing angle restriction when using a horizontal slicing technique and a corbelling printing method, to print spanning structures without formwork remains a challenge. Most state-of-the-art studies in 3DCP have focused on developing strategies to fabricate formwork, rather than developing new techniques for printing them without formwork. This research aims to leverage the power of shape grammar to overcome the challenges of printing spanning roof structures in 3DCP. By drawing inspiration from historical structures, we propose a multi-directional printing approach, integrating corbelling, radial, and inclined slicing techniques for toolpath design. Our objective is to establish shape grammar rules to break down enclosures into printable patches, design corresponding toolpaths using various slicing techniques, and validate the effectiveness of this approach by physically fabricating a prototype. To achieve this objective, an algorithm, incorporating shape grammar rules and numerical modelling software, to optimize the 3D concrete printing process for spanning roof structures was developed. Through this generative design system, designers can efficiently generate diverse and sustainable roof designs, specifically tailored for affordable housing solutions.
series	ASCAAD
email
last changed	2024/02/13 14:40

_id	acadia23_v2_430
id	acadia23_v2_430
authors	Vaidhyanathan, Vishal; T R, Radhakrishnan; Garcia del Castillo Lopez, Jose Luis
year	2023
title	Spacify: A Generative Framework for Spatial Comprehension, Articulation and Visualization using Large Language Models (LLMs) and eXtended Reality (XR)
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-9-8]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 430-443.
summary	Spatial design, the thoughtful planning and creation of built environments, typically requires advanced technical knowledge and visuospatial skills, making it largely exclusive to professionals like architects, interior designers, and urban designers. This exclusivity limits non-experts' access to spatial design, despite their ability to describe requirements and suggestions in natural language. Recent advancements in generative artificial intelligence (AI), particularly large language models (LLMs), and extended reality, (XR) offer the potential to address this limitation. This paper introduces Spacify (Figure 1), a framework that utilizes the generalizing capabilities of LLMs, 3D data-processing, and XR interfaces to create an immersive medium for language-driven spatial understanding, design, and visualization for non-experts. This paper describes the five components of Spacify: External Data, User Input, Spatial Interface, Large Language Model, and Current Spatial Design; which enable the use of generative AI models in a) question/ answering about 3D spaces with reasoning, b) (re)generating 3D spatial designs with natural language prompts, and c) visualizing designed 3D spaces with natural language descriptions. An implementation of Spacify is demonstrated via an XR smartphone application, allowing for an end-to-end, language-driven interior design process. User survey results from non-experts redesigning their spaces in 3D using this application suggest that Spacify can make spatial design accessible using natural language prompts, thereby pioneering a new realm of spatial design that is naturally language-driven.
series	ACADIA
type	paper
email
last changed	2024/04/17 13:59

_id	acadia23_v2_582
id	acadia23_v2_582
authors	Wu, Kaicong; Li, Chenming; Su, Wenjun
year	2023
title	The Chair Game Experiment: Transforming Multiplayer Design Processes with Text-to-Image Generation and 2D-to-3D Modelling
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 2: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-9-8]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 582-595.
summary	The urgency for an inclusive architectural design process in conceptualizing the built environment stems from the need to establish effective communication between under- represented groups and design professionals. However, various challenges hinder the development of an inclusive design process that accommodates diverse stakeholders. Individual designers or selective design teams are frequently limited by their own visions, causing them to potentially overlook alternative solutions. Moreover, stakeholders who lack professional training might struggle to articulate their expectations. The emergence of generative AI (artificial intelligence) technologies has significantly reduced the tech- nical barriers in design, and has empowered non-professionals to vividly express their ideas regarding forms and spaces. This has presented a valuable opportunity to better understand the perspectives of underrepresented groups through visual representations. Therefore, this research aims to explore the impact of image generation on the democ- ratization of the design process. Using chair design as a testing ground, we propose an evolutionary computing framework that simulates interactions among designers and participants empowered by emerging AI technologies. To investigate the potential impact of image generation, we have implemented a multiplayer design game to allow computing agents to compete in exploring 3D chair forms. Through this approach, we aim to gain insights into how image generation influences design decisions, whether it generates more diversified solutions, and what values could be introduced into the built environment.
series	ACADIA
type	paper
email
last changed	2024/04/17 13:59

_id	ascaad2023_055
id	ascaad2023_055
authors	Yildiz, Berfin; Çagdaº, Gülen; Zincir, lbrahim
year	2023
title	Deep Architectural Floor Plan Generation: An Approach for Open-Planned Residential Spaces
source	C+++: Computation, Culture, and Context – Proceedings of the 11th International Conference of the Arab Society for Computation in Architecture, Art and Design (ASCAAD), University of Petra, Amman, Jordan [Hybrid Conference] 7-9 November 2023, pp. 685-705.
summary	This research investigates the collaborative potential of artificial intelligence and deep learning in architectural design, focusing on comprehending and synthesizing the complex relationships within architectural floor plans. The primary question addressed is whether deep learning algorithms can effectively generate residential floor plans characterized by open-planned architectural spaces. To address this, the study introduces a novel model employing generative adversarial networks (GANs) to create open-planned layouts within residential floor plans. Open-planned spaces refers to a design approach in which interior spaces within a structure are intentionally devoid of traditional partitioning elements such as walls and doors. The layout typically features interconnected and visually continuous spaces that flow seamlessly from one area to another. The research contributes by addressing a gap in the literature through the exploration of functional space differentiations within residences characterized by open plan arrangement without walls as a separating element. Furthermore, the study extends this investigation by applying the proposed methodology to angular and circular plans as well as orthogonal plan sets. In the generative model created with GAN, the space functions are defined and labelled with the RGB color codes assigned to them. For the RGB label representation of the open-plan layout, gradient coloring prepared. By using this method, it was investigated whether the generation of the plans was realized with an open-plan structure by examining the gradient generation results. In the generative model, the footprint of the plan is given as an input for the algorithm to produce by adhering to an outer boundary. Accordingly, it is aimed to learn how the network can be arranged within the given boundaries. The Pix2pix method was used for this generative model, which is defined as the problem of obtaining images from images. The model results advance the AI-driven understanding of architectural design by providing architects with an innovative tool to explore open-plan spatial solutions.
series	ASCAAD
email
last changed	2024/02/13 14:34

_id	cdrf2023_35
id	cdrf2023_35
authors	Zexi Lyu, Zao Li, Zijing Wu
year	2023
title	Research on Image-to-Image Generation and Optimization Methods Based on Diffusion Model Compared with Traditional Methods: Taking Façade as the Optimization Object
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_4
summary	The intersection of technology and culture has become a topic of great interest worldwide, with China's development embracing this integration as an essential direction. One critical area where these two fields converge is in the inheritance, translation, and creative design of cultural heritage. In line with this trend, our study explores the potential of stable diffusion to produce highly detailed and visually stunning building façades. We start by providing an overall survey and algorithm fundamentals of the generative deep learning models used so far, namely, GAN and Diffusion models. Then, we present our methodology for using Diffusion Model to generate architecture façades. We then demonstrate how the fine-tuning is done for Stable Diffusion is done to yield optimal performance and then evaluate four different training methods of SD. We also compare existing GAN based façade generation method with our Diffusion based method. Our results show that our Diffusion-based approach outperforms existing methods in terms of detail and quality, highlighting the potential of stable diffusion in generating visually appealing building façades. This research contributes to the growing body of work on the integration of technology and culture in architecture and offers insights into the potential of stable diffusion for creative design applications.
series	cdrf
email
last changed	2024/05/29 14:04

_id	ecaade2023_162
id	ecaade2023_162
authors	Zhao, Hanbing, Savov, Anton, Zhang, Hang and Dillenburger, Benjamin
year	2023
title	A Framework for the Design and Evaluation of Architectural Tilesets
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 491–500
doi	https://doi.org/10.52842/conf.ecaade.2023.2.491
summary	Generative design, increasingly prevalent in architecture, enables design exploration and enhanced productivity compared to traditional methods. Researchers have investigated combinatorial design using tilesets, which encode architectural meaning and promote user-friendly interactions. However, most research focuses on discovering designs rather than fine-tuning tilesets. We propose a tile-based method that introduces metrics for evaluating generated layouts and tileset design space, addressing the research gap and facilitating practical applications. The design space evaluation feedback aids architects in customizing tilesets according to their objectives by exploring the impact of tile topology and rule changes. Our framework, illustrated through double-floor single-family house tilesets using the Wave Function Collapse algorithm, generates 3D designs and 2D layouts, enables minimal-specification diverse tilesets, and demonstrates fine-tuning to avoid grid-like monotonicity, a common limitation of tile-based generative design methods.
keywords	Generative Architectural Design, Data Analysis, Tileset, Wave Function Collapse
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_466
id	ecaade2023_466
authors	Liu, Zidong, Li, Han, Koehler, Daniel and Li, Yan
year	2023
title	Predicting Non-functional Nodes of Floorplan via Graph Neural Network (GNN)
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 529–538
doi	https://doi.org/10.52842/conf.ecaade.2023.2.529
summary	This paper presents an innovative approach to automating the floorplan generation process by employing Graph Neural Networks (GNN) to facilitate the transition from functional assignment lists to bubble diagrams and eventually to floorplan graphs. In recent years, there have been many studies on the interconversion of floorplan graph and layout design. However, these studies usually mix up floorplan graph and bubble diagram, despite their distinct roles in representing spatial and functional relationships, respectively. To address this disparity, we introduce a research framework comprising three main steps. First, we generate the CubiBubble5k dataset, which encompasses bubble diagrams and functional lists, drawing on the existing CubiCasa5k and CubiGraph5k datasets. Next, we train a GNN to transform design assignments into structured graph data, utilizing functional lists as input and bubble diagrams as output. Subsequently, we train another GNN that predicts and inserts non-functional spaces, such as corridors and anterooms, into purely functional bubble diagrams, using bubble graphs as input and floorplan graphs as output. We assess the performance of both GNNs and, by integrating our framework with the established graph2plan study, successfully demonstrate the generation of real-world floorplans from project task books. Lastly, we conduct case studies to validate the feasibility of our proposed framework. We use the existing graph2plan platform to visualize the impact of our algorithm on the final layout.
keywords	Floorplan Automation, Bubble Diagram, Graph Restructure, Graph Neural Network
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ecaade2023_113
id	ecaade2023_113
authors	Pereira da Silva, Nuno, Eloy, Sara and Resende, Ricardo
year	2023
title	Drone Robotic Construction: A methodology for simulating the construction performed by drones using virtual and augmented reality
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 1, Graz, 20-22 September 2023, pp. 781–790
doi	https://doi.org/10.52842/conf.ecaade.2023.2.781
summary	The economic and social impacts of robotic construction in Architecture, Engineering, and construction (AEC) are hard to assess and quantify without physical in situ testing, which is expensive and time-consuming This paper presents a methodology for the simulation of robotic construction technologies, namely drones, in a human-machine cooperation (HMC) using virtual (VR) and augmented (AR) reality environments. The developed methodology for robotic construction has the potential to be applied before the start of construction and to use real, virtual and augmented environments for robotic construction simulations. The application of such simulation methodology allows to test HMC scenarios and has the potential to increase construction precision while predicting both construction duration and cost. We present a review of the literature on drone and hybrid automatic construction solutions, as well as VR and AR construction simulations. Then a HMC simulation methodology is proposed and detailed. Three cases of application of the methodology are presented testing different approaches and cooperation scenarios in robotic construction. These cases are: (i) a drone construction in a real environment, (ii) a VR robotic construction simulation and (iii) an AR HMC. The application cases assess how the developed methodology is applicable to a set of different types of simulations that include different criteria.
keywords	Robotic construction, drones, VR/AR, simulation, Human-Machine Cooperation
series	eCAADe
email
last changed	2023/12/10 10:49

_id	ijac202321404
id	ijac202321404
authors	Melih, Kamaoglu
year	2023
title	The idea of evolution in digital architecture: Toward united ontologies?
source	International Journal of Architectural Computing 2023, Vol. 21 - no. 4, 622-634
summary	Humans have always sought to grasp nature’s working principles and apply acquired intelligence to artefacts since nature has always been the source of inspiration, solution and creativity. For this reason, there is a comprehensive interrelationship between the philosophy of nature and architecture. After Charles Darwin’s revolutionary work, living beings have started to be comprehended as changing, evolving and developing dynamic entities. Evolution theory has been accepted as the interpretive power of biology after several discussions and objections among scientists. In time, the working principles of evolutionary mechanisms have begun to be explained from genetic code to organism and environmental level. Afterwards, simulating nature’s evolutionary logic in the digital interface has become achievable with computational systems’ advancements. Ultimately, architects have begun to utilise evolutionary understanding in design theories and methodologies through computational procedures since the 1990s. Although several studies about technical and pragmatic elements of evolutionary tools in design, there is still little research on the historical, theoretical and philosophical foundations of evolutionary understanding in digital architecture. This paper fills this literature gap by critically reviewing the evolutionary understanding embedded in digital architecture theories and designs since the beginning of the 1990s. The original contribution is the proposed intellectual framework seeking to understand and conceptualise how evolutionary processes were defined in biology and philosophy, then represented through computational procedures, to be finally utilised by architectural designers. The network of references and concepts is deeply connected with the communication between natural processes and their computational simulations. For this reason, another original contribution is the utilisation of theoretical limits and operative principles of computation procedures to shed light on the limitations, shortcomings and potentials of design theories regarding their speculations on the relationship between natural and computational ontologies.
keywords	Evolution, computation, digital architecture, ontology, architectural theory
series	journal
last changed	2024/04/17 14:30

_id	sigradi2023_463
id	sigradi2023_463
authors	Acuna, Tomás, Avendano, Martín, García-Alvarado, Rodrigo, Banda, Pablo and Soza, Pedro
year	2023
title	Parametric design of multipurpose 3d-printed walls based on Roberto Matta´s drawings
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 483–494
summary	A research and workflow are presented for the parametric design and 3D printing of multipurpose walls, based on illustrations of residential environments made by the Chilean surrealist painter Roberto Matta. These drawings present walls with different shapes and associated uses that expand the housing experiences and suggest relaxed and suggestive spaces. The work analyzes the formal variations and different types of elements that can be included in the design of walls, as well as different textures and ribs that can be incorporated into the walls for their appearance and structural integrity. Possibilities are reviewed for the efficient design and execution of complex shapes using parametric procedures for 3D printing. Determining a generative capacity with high functional and expressive versatility, and construction feasibility.
keywords	Parametric Design, 3d-printing, Wall, Surrealism, Roberto Matta
series	SIGraDi
email
last changed	2024/03/08 14:07

_id	ascaad2023_075
id	ascaad2023_075
authors	Aljhadali, Abdulrahman; Megahed, Yasser; Gwilliam, Julie
year	2023
title	Artificial Intelligence (AI) and Machine Learning (ML) in Practice: A Comprehensive Investigation into the Utilization of Generative Artificial Intelligence (AI) and Machine Learning (ML) in Architectural Practice
source	C+++: Computation, Culture, and Context – Proceedings of the 11th International Conference of the Arab Society for Computation in Architecture, Art and Design (ASCAAD), University of Petra, Amman, Jordan [Hybrid Conference] 7-9 November 2023, pp. 324-343.
summary	This study offers a comprehensive investigation into the utilization of artificial intelligence (AI) and machine learning (ML) technologies within architectural practices. Since the introduction of computer-aided design (CAD), technology has had a significant impact on the way architects conduct their work. This study explores the potential of AI/ML in actual architectural workflows, with a particular emphasis on the capacity of deep neural networks to assist in the design process.The outcome will help to develop a clearer picture of the opportunities and barriers associated with AI for architects; they will also inform the prioritization of focus for future development of this technology in architectural practice, as well as identifying the specific tasks and project phases in which ML could play a role. This research reviewed literature to explore various approaches for applying AI/ML technologies within the field of architecture. Also , complemented by a number of interviews to investigate the ways in which participants are currently using AI/ML in their work, framing the current feedback and the future potential of AI/ML technologies in architecture. The data collection methods adopted involved semi-structured one-on-one interviews with professionals from multi-regional architecture firms and AI developers. The architects interviewed exhibited diverse ways of benefiting from AI/ML technology, with varying approaches and some common trends. The findings demonstrate that AI has played a pivotal role in expediting the design process and enhancing visualization within the field. However, it has also raised concerns, particularly in the realm of privacy.
series	ASCAAD
email
last changed	2024/02/13 14:40

For more results click below: