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 425

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

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

_id	acadia18_156
id	acadia18_156
authors	Huang, Weixin; Zheng, Hao
year	2018
title	Architectural Drawings Recognition and Generation through Machine Learning
doi	https://doi.org/10.52842/conf.acadia.2018.156
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
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_197
id	caadria2018_197
authors	Rogers, Jessie, Schnabel, Marc Aurel and Lo, Tian Tian
year	2018
title	Digital Culture - An Interconnective Design Methodology Ecosystem
doi	https://doi.org/10.52842/conf.caadria.2018.1.493
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. 493-502
summary	Transitioning away from traditional design methodology, for example, paper sketching, CAAD works, and 'flat screen' rendering, this paper proposes a new methodological ecosystem of which tests its validity within a studio-based case study. The focus will prove whether dynamic implementation and interconnectivity of evolving design tools can create richness and complexity of a design outcome through arbitrary phases of a generative design methodology ecosystem. Processes tested include combinations of agent simulations, artistic image processing analysis, site photogrammetry, 3D immersive sketching both abstract and to site-scale, parametric design generation, and virtual reality style presentations. Enhancing the process of design with evolving techniques in a generative way which dynamically interconnects will stimulate a digital culture of design generation that includes new aspects of interest and introduces innovative opportunities within all corners of the architectural realm. Methodology components within this ecosystem of interaction prove that the architecture cannot be as rich and complex without the utilisation of all strengths within each unique design tool.
keywords	Methodology Ecosystem; Simulation; Immersive; Virtual Reality; Photogrammetry
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	acadia19_392
id	acadia19_392
authors	Steinfeld, Kyle
year	2019
title	GAN Loci
doi	https://doi.org/10.52842/conf.acadia.2019.392
source	ACADIA 19:UBIQUITY AND AUTONOMY [Proceedings of the 39th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-59179-7] (The University of Texas at Austin School of Architecture, Austin, Texas 21-26 October, 2019) pp. 392-403
summary	This project applies techniques in machine learning, specifically generative adversarial networks (or GANs), to produce synthetic images intended to capture the predominant visual properties of urban places. We propose that imaging cities in this manner represents the first computational approach to documenting the Genius Loci of a city (Norberg-Schulz, 1980), which is understood to include those forms, textures, colors, and qualities of light that exemplify a particular urban location and that set it apart from similar places. Presented here are methods for the collection of urban image data, for the necessary processing and formatting of this data, and for the training of two known computational statistical models (StyleGAN (Karras et al., 2018) and Pix2Pix (Isola et al., 2016)) that identify visual patterns distinct to a given site and that reproduce these patterns to generate new images. These methods have been applied to image nine distinct urban contexts across six cities in the US and Europe, the results of which are presented here. While the product of this work is not a tool for the design of cities or building forms, but rather a method for the synthetic imaging of existing places, we nevertheless seek to situate the work in terms of computer-assisted design (CAD). In this regard, the project is demonstrative of a new approach to CAD tools. In contrast with existing tools that seek to capture the explicit intention of their user (Aish, Glynn, Sheil 2017), in applying computational statistical methods to the production of images that speak to the implicit qualities that constitute a place, this project demonstrates the unique advantages offered by such methods in capturing and expressing the tacit.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:56

_id	ecaade2018_303
id	ecaade2018_303
authors	Werner, Liss C.
year	2018
title	Biological Computation of Physarum - From DLA to spatial adaptive Voronoi
doi	https://doi.org/10.52842/conf.ecaade.2018.2.531
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. 531-536
summary	Physarum polycephalum, also called slime mold or myxamoeba, has started attracting the attention of those architects, urban designers, and scholars, who work in experimental trans- and flexi-disciplines between architecture, computer sciences, biology, art, cognitive sciences or soft matter; disciplines that build on cybernetic principles. Slime mold is regarded as a bio-computer with intelligence embedded in its physical mechanisms. In its plasmodium stage, the single cell organism shows geometric, morphological and cognitive principles potentially relevant for future complexity in human-machines-networks (HMN) in architecture and urban design. The parametric bio-blob presents itself as a geometrically regulated graph structure-morphologically adaptive, logistically smart. It indicates cognitive goal-driven navigation and the ability to externally memorize (like ants). Physarum communicates with its environment. The paper introduces physarum polycephalum in the context of 'digital architecture' as a biological computer for self-organizing 2D- to 4D-geometry generation.
keywords	generative geometry; bio-computation; Voronoi
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2018_229
id	ecaade2018_229
authors	Rogers, Jessie and Schnabel, Marc Aurel
year	2018
title	Digital Design Ecology - An Analysis for an Intricate Framework of Architectural Design
doi	https://doi.org/10.52842/conf.ecaade.2018.1.459
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. 459-468
summary	This paper evaluates, along with expert assessment, the novel, evolving and creative instruments employed for a digital design process. Applications within this paper derive outputs which are attention-grabbing. These include Agent Simulations, Artistic Image Processing, Realistic Site Geometry, Projected 3D Space Sketching, Immersive 3D Space Sketching, Rhinoceros3D, Grasshopper3D, Fuzor, and Immersive Virtual Reality Presentation. The expert evaluations conclude that all design instruments and methodologies implemented within the digital design ecology work together well for educational purposes. Within the professional practice, however, the various tools could be implemented seamlessly; whereas some of them would not suit the industry from a time-cost perspective. Throughout this paper reason and insight becomes explained and is clear as to why various applications should be selected within various modes of operandi for design processes.
keywords	Methodology Ecology; Agent Simulation; Digital Design; Virtual Reality; Photogrammetry; Image Processing
series	eCAADe
email
last changed	2022/06/07 07:56

_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
doi	https://doi.org/10.52842/conf.acadia.2018.176
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
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	acadia18_276
id	acadia18_276
authors	Bilotti, Jeremy; Norman, Bennett; Rosenwasser, David; Leo Liu, Jingyang; Sabin, Jenny
year	2018
title	Robosense 2.0. Robotic sensing and architectural ceramic fabrication
doi	https://doi.org/10.52842/conf.acadia.2018.276
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. 276-285
summary	Robosense 2.0: Robotic Sensing and Architectural Ceramic Fabrication demonstrates a generative design process based on collaboration between designers, robotic tools, advanced software, and nuanced material behavior. The project employs fabrication tools which are typically used in highly precise and predetermined applications, but uniquely thematizes the unpredictable aspects of these processes as applied to architectural component design. By integrating responsive sensing systems, this paper demonstrates real-time feedback loops which consider the spontaneous agency and intuition of the architect (or craftsperson) rather than the execution of static or predetermined designs. This paper includes new developments in robotics software for architectural design applications, ceramic-deposition 3D printing, sensing systems, materially-driven pattern design, and techniques with roots in the arts and crafts. Considering the increasing accessibility and advancement of 3D printing and robotic technologies, this project seeks to challenge the erasure of materiality: when mistakes or accidents caused by inconsistencies in natural material are avoided or intentionally hidden. Instead, the incorporation of material and user-input data yields designs which are imbued with more nuanced traces of making. This paper suggests the potential for architects and craftspeople to maintain a more direct and active relationship with the production of their designs.
keywords	full paper, fabrication & robotics, robotic production, digital fabrication, digital craft
series	ACADIA
type	paper
email
last changed	2022/06/07 07:54

_id	ecaadesigradi2019_249
id	ecaadesigradi2019_249
authors	Chiarella, Mauro, Gronda, Luciana and Veizaga, Martín
year	2019
title	RILAB - architectural envelopes - From spatial representation (generative algorithm) to geometric physical optimization (scientific modeling)
doi	https://doi.org/10.52842/conf.ecaade.2019.3.017
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 3, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 17-24
summary	Augmented graphical thinking operates by integrating algorithmic, heuristic, and manufacturing processes. The Representation and Ideation Laboratory (RILAB-2018) exercise begins with the application of a parametric definition developed by the team of teachers, allowing for the construction of structural systems by the means of the combination of segmental shells and bending-active. The main objetive is the construction of a scientific model of simulation for bending-active laminar structures has brought into reality trustworthy previews for architectural envelopes through the interaction of parametrized relational variables. This way we put designers in a strategic role for the building of the pre-analysis models, allowing more preciseness at the time of picking and defining materials, shapes, spaces and technologies and thus minimizing the decisions based solely in the definition of structural typological categories, local tradition or direct experience. The results verify that the strategic integration of models of geometric physical optimization and spatial representation greatly expand the capabilities in the construction of the complex system that operates in the act of projecting architecture.
keywords	architectural envelopes; augmented graphic thinking; geometric optimization; bending-active
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:55

_id	ecaade2018_339
id	ecaade2018_339
authors	Fereos, Pavlos, Tsiliakos, Marios and Jaschke, Clara
year	2018
title	Spaceship Tectonics - Design Computation Pedagogy for Generative Sci-Fi Building Skins
doi	https://doi.org/10.52842/conf.ecaade.2018.2.357
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. 357-366
summary	Sci-Fi architecture, both as digital or physical representations, despite their inherent intricacy, lack the spatial depth of a structured interior, material definition or program information. This discrepancy, combined with the plethora of available sci-fi motifs, inspired the development of an integrated teaching approach with the academic objective to utilize computational methods for analysis, reproduction and composition of generative building skins, and consequently architecture, which aims to be 'outside of this world' as a sci-fi design quality-enriched result of our reality. The proposed methodology is implemented at the Spaceship Architecture Design Studio at the University of Innsbruck. Its capacity to achieve a successful assimilation of design computation in the curriculum is subsequently assessed by the documentation and quantitative/qualitative evaluation of the designs developed during two academic years, in line with a generative facade articulation schema, without however undermining the rest of the virtues of tectonic spaces. The introduction of a theme like sci-fi where the design objective is not clearly defined, is examined in comparison to similar approaches, towards the corroboration of the pedagogical method proposed.
keywords	Pedagogy; Computation; Facade Design; Generative; Sci-Fi; Patterns
series	eCAADe
email
last changed	2022/06/07 07:50

_id	caadria2018_270
id	caadria2018_270
authors	Houda, Maryam and Reinhardt, Dagmar
year	2018
title	Structural Optimisation for 3D Printing Bespoke Geometries
doi	https://doi.org/10.52842/conf.caadria.2018.1.235
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. 235-244
summary	Current advances in 3D printing technology enable novel design explorations with the potential to inform printing deposition through generative scripting and structural performance analysis. This paper presents ongoing research that involves three scales of operation; a global geometry for multi-skin cellular mesh densities; localised skin-porosity detailing, and material structural optimisation. Centering on a chair as a test case scenario, the research explores the affordances of a serialised, multi-material 3D printing process in the context of digital instruction, customisation, and material efficiency. The paper discusses two case studies with consecutive optimisation, and outlines the benefits and limitations of 3D printing for structural optimisation and multi-material grading in the additive process.
keywords	3D Printing; Bespoke Complexity; Digital Instruction; Mass Customisation; Multi-Material Grading; Robotic Deposition; Structural Optimisation
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	ecaade2018_180
id	ecaade2018_180
authors	Kwieciñski, Krystian and Markusiewicz, Jacek
year	2018
title	HOPLA - Interfacing Automation for Mass-customization
doi	https://doi.org/10.52842/conf.ecaade.2018.2.159
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. 159-168
summary	HOPLA (Home Planner) is a computer-aided design system aimed at simplifying customization of house design. It merges aspects of user-centered computer-aided design with machine-centered computerized design, as defined by Negroponte in The Architecture Machine. The tool was developed to fulfill mass-customization principles without compromising mass production efficiency and to support users' participation in design processes to help them formulate expectations and search for design solutions. We describe the details of the system development and its possible use in the process of mass-customization and participatory design of single-family houses. The system consists of two core elements: an algorithm based on a generic grammar responsible for generating design solutions in relation to user input, and a Tangible User Interface allowing users to introduce data and to control the process in an intuitive way. The main challenge in developing the system was to synchronize the freedom of user's design decisions with the rigor of machine's verification process.
keywords	mass-customization; participatory design; tangible user interface; house design; generative design
series	eCAADe
email
last changed	2022/06/07 07:55

_id	acadia18_434
id	acadia18_434
authors	Meibodi, Mania Aghaei ; Jipa, Andrei; Giesecke, Rena; Shammas, Demetris; Bernhard, Mathias; Leschok, Matthias; Graser, Konrad; Dillenburger, Benjamin
year	2018
title	Smart Slab. Computational design and digital fabrication of a lightweight concrete slab
doi	https://doi.org/10.52842/conf.acadia.2018.434
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. 434-443
summary	This paper presents a computational design approach and novel digital fabrication method for an optimized lightweight concrete slab using a 3D-printed formwork. Smart Slab is the first concrete slab fabricated with a 3D-printed formwork. It is a lightweight concrete slab, displaying three-dimensional geometric differentiation on multiple scales. The optimization of slab systems can have a large impact on buildings: more compact slabs allow for more usable space within the same building volume, refined structural concepts allow for material reduction, and integrated prefabrication can reduce complexity on the construction site. Among the main challenges is that optimized slab geometries are difficult to fabricate in a conventional way because non-standard formworks are very costly. Novel digital fabrication methods such as additive manufacturing of concrete can provide a solution, but until now the material properties and the surface quality only allow for limited applications. The fabrication approach presented here therefore combines the geometric freedom of 3D binderjet printing of formworks with the structural performance of fiber reinforced concrete. Using 3D printing to fabricate sand formwork for concrete, enables the prefabrication of custom concrete slab elements with complex geometric features with great precision. In addition, space for building systems such as sprinklers and Lighting could be integrated in a compact way. The design of the slab is based on a holistic computational model which allows fast design optimization and adaptation, the integration of the planning of the building systems, and the coordination of the multiple fabrication processes involved with an export of all fabrication data. This paper describes the context, design drivers, and digital design process behind the Smart Slab, and then discusses the digital fabrication system used to produce it, focusing on the 3D-printed formwork. It shows that 3D printing is already an attractive alternative for custom formwork solutions, especially when strategically combined with other CNC fabrication methods. Note that smart slab is under construction and images of finished elements can be integrated within couple of weeks.
keywords	full paper, digital fabrication, computation, generative design, hybrid practices
series	ACADIA
type	paper
email
last changed	2022/06/07 07:58

_id	ijac201816304
id	ijac201816304
authors	Miao, Yufan; Reinhard Koenig, Katja Knecht, Kateryna Konieva, Peter Buš and Mei-Chih Chang
year	2018
title	Computational urban design prototyping: Interactive planning synthesis methods—a case study in Cape Town
source	International Journal of Architectural Computing vol. 16 - no. 3, 212-226
summary	This article is motivated by the fact that in Cape Town, South Africa, approximately 7.5 million people live in informal settlements and focuses on potential upgrading strategies for such sites. To this end, we developed a computational method for rapid urban design prototyping. The corresponding planning tool generates urban layouts including street network, blocks, parcels and buildings based on an urban designer’s specific requirements. It can be used to scale and replicate a developed urban planning concept to fit different sites. To facilitate the layout generation process computationally, we developed a new data structure to represent street networks, land parcellation, and the relationship between the two. We also introduced a nested parcellation strategy to reduce the number of irregular shapes generated due to algorithmic limitations. Network analysis methods are applied to control the distribution of buildings in the communities so that preferred neighborhood relationships can be considered in the design process. Finally, we demonstrate how to compare designs based on various urban analysis measures and discuss the limitations that arise when we apply our method in practice, especially when dealing with more complex urban design scenarios.
keywords	Procedural modeling, spatial synthesis, generative design, urban planning
series	journal
email
last changed	2019/08/07 14:03

_id	ecaade2018_215
id	ecaade2018_215
authors	Mohite, Ashish, Kochneva, Mariia and Kotnik, Toni
year	2018
title	Material Agency in CAM of Undesignable Textural Effects - The study of correlation between material properties and textural formation engendered by experimentation with G-code of 3D printer
doi	https://doi.org/10.52842/conf.ecaade.2018.2.293
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. 293-300
summary	This paper presents intermediate results of an experimental research directed towards development of a method to use additive manufacturing technology as a generative agent in architectural design process. The primary technique is to variate speed of material deposition of a 3D printer in order to produce undetermined textural effects. These effects demonstrate local variation of material distribution, which is treated as a consequence of interaction between machining parameters and material properties. Current stage of inquiry is concerned with studying material agency by using two different materials as variables in the same experimental setup. The results suggest potential benefits for mass-customized fabrication and deeper understanding of how different materials can be employed in the same manufacturing system to achieve a range of effective behaviors.
keywords	digital fabrication; digital craft
series	eCAADe
email
last changed	2022/06/07 07:58

_id	caadria2018_228
id	caadria2018_228
authors	Newton, David
year	2018
title	Accommodating Change and Open-Ended Search in Design Optimization
doi	https://doi.org/10.52842/conf.caadria.2018.2.175
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. 175-184
summary	Many real-world architectural multi-objective problems (MOPs) are dynamic and may have objectives, decision variables, and constraints that change during the optimization process. These problems are known as dynamic MOPs (DMOPs). Dynamic multi-objective evolutionary algorithms (DMOEAs) have emerged in the fields of optimization, operations research, and computer science as one way to address the challenges posed by DMOPs. DMOEAs offer new capacities for exploration and interaction with the designer, but they have not yet been studied in the field of architecture. This research addresses these issues through the development of a unique interactive DMOEA-based design tool for the conceptual design phase. We propose a new modification to the popular nondominated sorting genetic algorithm II (NSGA-II), that we call the dynamic progressive for architecture NSGA-II (DPA-NSGA-II). We show that DPA-NSGA-II outperforms NSGA-II in finding novel solutions.
keywords	algorithmic design; multi-objective optimization; evolutionary computation; parametric design; generative design
series	CAADRIA
email
last changed	2022/06/07 07:58

_id	ecaade2018_323
id	ecaade2018_323
authors	Newton, David
year	2018
title	Multi-Objective Qualitative Optimization (MOQO) in Architectural Design
doi	https://doi.org/10.52842/conf.ecaade.2018.1.187
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. 187-196
summary	Architectural design problems are often multi-objective in nature, involving both qualitative and quantitative objectives. Previous research has focused exclusively on the development of multi-objective optimization algorithms that work with multiple quantitative objectives. No previous research has looked at the topic of multi-objective qualitative optimization (MOQO), in which multiple qualitative objectives are optimized simultaneously. This research addresses MOQO through the development of a unique multi-objective optimization algorithm for the conceptual design phase that uses three-dimensional convolutional neural networks (3D CNNs) to measure user-defined qualities in architectural massing models.
keywords	multi-objective optimization; generative design; multi-objective qualitative optimization; algorithmic design
series	eCAADe
email
last changed	2022/06/07 07:58

_id	ijac201816101
id	ijac201816101
authors	Nisztu, Maciejk and Pawe³ B. Myszkowsk
year	2018
title	Usability of contemporary tools for the computational design of architectural objects: Review, features evaluation and reflection
source	International Journal of Architectural Computing vol. 16 - no. 1, 58-84
summary	This article is an overview focused on functionality and usability of selected contemporary approaches for the computational floor plan generation of architectural objects. This article describes current solutions for generative architectural design and focuses on their usability from the point of view of architectural design practice. Recent research papers and prototypes, as well as the most important tools (selected computer-aided design and BIM software) for generative design from the architectural perspective, are described. The functionalities and level of usability of present-day software and prototypes are described. In addition, the descriptive review of the research prototypes architectural design outcomes is present. Furthermore, the survey among active architects regarding the usage of computational tools in the professional practice and possible guidelines for the development of such tools are present. This article summarises with the conclusion about the current state of generative floor plan design tools, the lack of fully functional and developed commercial tools of this type on the market and future directions for the development of generative floor plans tools.
keywords	Architectural design, case studies, computer-aided architectural design, optimisation in computer-aided architectural design, computer-aided architectural design applications
series	journal
email
last changed	2019/08/07 14:03

_id	ecaade2018_193
id	ecaade2018_193
authors	Ostrowska-Wawryniuk, Karolina and Nazar, Krzysztof
year	2018
title	Generative BIM Automation Strategies for Prefabricated Multi-Family Housing Design
doi	https://doi.org/10.52842/conf.ecaade.2018.1.247
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. 247-256
summary	The increasing housing shortage in contemporary Poland calls for efficient ways of design and construction. In the context of time efficiency and shrinking manpower, prefabrication is considered as one of the means of introducing low and middle income housing to the market. The article presents the process of developing an experimental tool for aiding multi-family housing architectural design with the use of prefabrication. We use the potential of BIM technology as a flexible environment for comparing multiple design options and, therefore, supporting the decision-making process. The presented experiment is realized in the Autodesk Revit environment and incorporates custom generative scripts developed in Dynamo-for-Revit and Grasshopper. The prototype tool analyzes an input Revit model and simulates a prefabricated alternative based on the user-specified boundary conditions. We present our approach to the analyzing and the splitting of the input model as well as five different strategies of performing the simulation within the Revit environment.
keywords	Building Information Modeling; generative BIM; residential building design; prefabrication; design automation; Dynamo
series	eCAADe
email
last changed	2022/06/07 08:00

_id	ijac201816305
id	ijac201816305
authors	Patt, Trevor Ryan
year	2018
title	Multiagent approach to temporal and punctual urban redevelopment in dynamic, informal contexts
source	International Journal of Architectural Computing vol. 16 - no. 3, 199-211
summary	This article presents design research speculating on computationally enabled planning approaches for urban sites where informal developments make conventional masterplans ineffectual. The project advances the thesis that the spatial complexity of urban sites can be effectively studied through a network or mesh representation and that rapid change in informal settlements is not an obstacle to planned redevelopment but can be addressed through dynamic modeling and punctual interventions. In this way, the rapid turnover of the built environment can be a mechanism through which to introduce directed planning without canceling out bottom-up actions. In the case study presented, we use a multiagent approach that is able to adapt to a continuously changing context. The agents are driven by weighted random walks and compute localized analyses of the morphology of the network of public space as they move. The information generated by the multiagent simulation is aggregated to identify potential modifications to the urban fabric, with an emphasis on pedestrian connectivity.
keywords	Adaptive planning, multiagent systems, urban morphology, network analysis, spectral clustering, informal urbanism, generative design, participatory frameworks
series	journal
email
last changed	2019/08/07 14:03

For more results click below: