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 464

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

_id	ecaade2017_101
id	ecaade2017_101
authors	Ayoub, Mohammed and Wissa, Magdi
year	2017
title	Daylight Optimization - A Parametric Study of Urban Façades Design within Hybrid Settlements in Hot-Desert Climate
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 193-202
doi	https://doi.org/10.52842/conf.ecaade.2017.2.193
summary	Unprecedented growth of hybrid settlements causes deterioration to the indoor environmental quality. Due to their narrow street-networks and fully packed urban fabric, lower floors are subjected to severe overshadow condition, which has adverse effects on the health of the inhabitants. This paper aims to investigate techniques to mitigate the under-lit indoor environment for a group of buildings with variable heights and orientations, with regard to the urban façades parameters. It reflects an intervention in an existing hybrid settlements, within hot-desert climate, to alter façades configurations for daylight optimization, and ultimately recover the lost indoor quality of users in such contexts.
keywords	Daylight Optimization; Urban Façade; Simulation; Hybrid Settlements ; Parametric Design
series	eCAADe
email
last changed	2022/06/07 07:54

_id	ecaade2017_271
id	ecaade2017_271
authors	Narahara, Taro
year	2017
title	Collective Construction Modeling and Machine Learning: Potential for Architectural Design
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 341-348
doi	https://doi.org/10.52842/conf.ecaade.2017.2.341
summary	Recently, there are significant developments in artificial intelligence using advanced machine learning algorithms such as deep neural networks. These new methods can defeat human expert players in strategy-based board games such as Go and video games such as Breakout. This paper suggests a way to incorporate such advanced computing methods into architectural design through introducing a simple conceptual design project inspired by computational interpretations of wasps' collective constructions. At this stage, the paper's intent is not to introduce a practical and fully finished tool directly useful for architectural design. Instead, the paper proposes an example of a program that can potentially become a conceptual framework for incorporating such advanced methods into architectural design.
keywords	Design tools; Stigmergy; Machine learning
series	eCAADe
email
last changed	2022/06/07 07:58

_id	ecaade2017_041
id	ecaade2017_041
authors	Fukuda, Tomohiro, Kuwamuro, Yasuyuki and Yabuki, Nobuyoshi
year	2017
title	Optical Integrity of Diminished Reality Using Deep Learning
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 1, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 241-250
doi	https://doi.org/10.52842/conf.ecaade.2017.1.241
summary	A new method is proposed to improve diminished reality (DR) simulations to allow the demolition and removal of entire buildings in large-scale spaces. Our research goal was to obtain optical integrity by using a scientific and reliable simulation approach. Further, we tackled presumption of the texture of the background sky by applying deep learning. Our approach extracted the background sky using information from the actual sky obtained from a photographed image. This method comprised two steps: (1) detection of the sky area from the image through image segmentation and (2) creation of an image of the sky through image inpainting. The deep convolutional neural networks developed by us to train and predict images were evaluated to be feasible and effective.
keywords	Diminished Reality; Optical Integrity; Deep Learning; Augmented Reality; Landscape assessment
series	eCAADe
email
last changed	2022/06/07 07:50

_id	ecaade2023_259
id	ecaade2023_259
authors	Sonne-Frederiksen, Povl Filip, Larsen, Niels Martin and Buthke, Jan
year	2023
title	Point Cloud Segmentation for Building Reuse - Construction of digital twins in early phase building reuse projects
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. 327–336
doi	https://doi.org/10.52842/conf.ecaade.2023.2.327
summary	Point cloud processing has come a long way in the past years. Advances in computer vision (CV) and machine learning (ML) have enabled its automated recognition and processing. However, few of those developments have made it through to the Architecture, Engineering and Construction (AEC) industry. Here, optimizing those workflows can reduce time spent on early-phase projects, which otherwise could be spent on developing innovative design solutions. Simplifying the processing of building point cloud scans makes it more accessible and therefore, usable for design, planning and decision-making. Furthermore, automated processing can also ensure that point clouds are processed consistently and accurately, reducing the potential for human error. This work is part of a larger effort to optimize early-phase design processes to promote the reuse of vacant buildings. It focuses on technical solutions to automate the reconstruction of point clouds into a digital twin as a simplified solid 3D element model. In this paper, various ML approaches, among others KPConv Thomas et al. (2019), ShapeConv Cao et al. (2021) and Mask-RCNN He et al. (2017), are compared in their ability to apply semantic as well as instance segmentation to point clouds. Further it relies on the S3DIS Armeni et al. (2017), NYU v2 Silberman et al. (2012) and Matterport Ramakrishnan et al. (2021) data sets for training. Here, the authors aim to establish a workflow that reduces the effort for users to process their point clouds and obtain object-based models. The findings of this research show that although pure point cloud-based ML models enable a greater degree of flexibility, they incur a high computational cost. We found, that using RGB-D images for classifications and segmentation simplifies the complexity of the ML model but leads to additional requirements for the data set. These can be mitigated in the initial process of capturing the building or by extracting the depth data from the point cloud.
keywords	Point Clouds, Machine Learning, Segmentation, Reuse, Digital Twins
series	eCAADe
email
last changed	2023/12/10 10:49

_id	caadria2017_029
id	caadria2017_029
authors	Sun, Zheng and Cao, Yong Kang
year	2017
title	Applications of Integrated Digital Technologies for Surveying Tibetan Architectural Heritage:Three Years of Experiences
source	P. Janssen, P. Loh, A. Raonic, M. A. Schnabel (eds.), Protocols, Flows, and Glitches - Proceedings of the 22nd CAADRIA Conference, Xi'an Jiaotong-Liverpool University, Suzhou, China, 5-8 April 2017, pp. 663-672
doi	https://doi.org/10.52842/conf.caadria.2017.663
summary	Absence of reliable and accurate surveying of Tibetan architectural heritage has long been a major constraint for architects, architectural historians and archeologists working in that region. Due to distinctive geographical environment and architectural typology, unique surveying technologies are required in Tibet. In the last three years, integrated digital surveying technologies are applied to architectural heritage in Gyantse, a Tibetan city. The aim of the surveying is to document and analyze local architectural heritage for potential technical intervention such as consolidation, restoration and renovation. Key technical issues ranging from reliability of consumer-level UAV to BIM-based platform are presented in the article. The conclusions are that digital technologies greatly improve architectural heritage surveying in Tibet in terms of accuracy, efficiency and versatility. Future works will be addressed in more robust algorithms for points cloud semantic segmentation, change detection of large-scale architectural heritage based on remotely sensed imagery over time, and data exchange and coordination between BIM and GIS, etc.
keywords	Architectural heritage; Digital survey; Tibet; UAV; BIM
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	acadia17_238
id	acadia17_238
authors	El-Zanfaly, Dina
year	2017
title	A Multisensory Computational Model for Human-Machine Making and Learning
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 238-247
doi	https://doi.org/10.52842/conf.acadia.2017.238
summary	Despite the advancement of digital design and fabrication technologies, design practices still follow Alberti’s hylomorphic model of separating the design phase from the construction phase. This separation hinders creativity and flexibility in reacting to surprises that may arise during the construction phase. These surprises often come as a result of a mismatch between the sophistication allowed by the digital technologies and the designer’s experience using them. These technologies and expertise depend on one human sense, vision, ignoring other senses that could be shaped and used in design and learning. Moreover, pedagogical approaches in the design studio have not yet fully integrated digital technologies as design companions; rather, they have been used primarily as tools for representation and materialization. This research introduces a multisensory computational model for human-machine making and learning. The model is based on a recursive process of embodied, situated, multisensory interaction between the learner, the machines and the thing-in-the-making. This approach depends heavily on computational making, abstracting, and describing the making process. To demonstrate its effectiveness, I present a case study from a course I taught at MIT in which students built full-scale, lightweight structures with embedded electronics. This model creates a loop between design and construction that develops students’ sensory experience and spatial reasoning skills while at the same time enabling them to use digital technologies as design companions. The paper shows that making can be used to teach design while enabling the students to make judgments on their own and to improvise.
keywords	education, society & culture; fabrication
series	ACADIA
email
last changed	2022/06/07 07:55

_id	sigradi2017_039
id	sigradi2017_039
authors	González Böhme, Luis Felipe; Francisco Javier Quitral Zapata, Sandro Maino Ansaldo, Marcela Hurtado Saldías
year	2017
title	Reconstrucción robotizada del patrimonio arquitectónico chileno en madera [Robotic reconstruction of Chilean wooden architectural heritage]
source	SIGraDi 2017 [Proceedings of the 21th Conference of the Iberoamerican Society of Digital Graphics - ISBN: 978-956-227-439-5] Chile, Concepción 22 - 24 November 2017, pp.267-272
summary	We present a proof of concept of parametric 3D models of fully associative geometry and milling tool paths for the robotic machining of traditional timber joints, using a visual robot-programming environment integrated into a popular CAD software. A representative sample of traditional timber joints was obtained from a field survey conducted in Valparaíso, Chile. Each specimen was theoretically validated in nearly half a hundred carpentry treatises and manuals corresponding to the historical period in which the surveyed buildings were built. Parametric robotic milling prototypes were experimentally validated in manufacturing process using two industrial robots with different spindles and cutting tools.
series	SIGRADI
email
last changed	2021/03/28 19:58

_id	acadia17_382
id	acadia17_382
authors	Melenbrink, Nathan; Kassabian, Paul; Menges, Achim; Werfel, Justin
year	2017
title	Towards Force-aware Robot Collectives for On-site Construction
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 382- 391
doi	https://doi.org/10.52842/conf.acadia.2017.382
summary	Due to the irregular and variable environments in which most construction projects take place, the topic of on-site automation has previously been largely neglected in favor of off-site prefabrication. While prefabrication has certain obvious economic and schedule benefits, a number of potential applications would benefit from a fully autonomous robotic construction system capable of building without human supervision or intervention; for example, building in remote environments, or building structures whose form changes over time. Previous work using a swarm approach to robotic assembly generally neglected to consider forces acting on the structure, which is necessary to guarantee against failure during construction. In this paper we report on key findings for how distributed climbing robots can use local force measurements to assess aspects of global structural state. We then chart out a broader trajectory for the affordances of distributed on-site construction in the built environment and position our contributions within this research agenda. The principles explored in simulation are demonstrated in hardware, including solutions for force-sensing as well as a climbing robot.
keywords	material and construction; physics; construction/robotics; simulation & optimization
series	ACADIA
email
last changed	2022/06/07 07:58

_id	acadia17_392
id	acadia17_392
authors	Mesa, Olga; Stavric, Milena; Mhatre, Saurabh; Grinham, Jonathan; Norman, Sarah; Sayegh, Allen; Bechthold, Martin
year	2017
title	Non-Linear Matters: Auxetic Surfaces
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 392- 403
doi	https://doi.org/10.52842/conf.acadia.2017.392
summary	Auxetic structures exhibiting non-linear buckling are a prevalent research topic in the material sciences due to the ability to tune their reversible actuation, porosity, and negative Poisson’s ratio. However, the research is limited to feature sizes at scales below 10 mm2, and to date, there are no available efficient design and prototyping methods for architectural designers. Our study develops design principles and workflow methods to transform standard materials into auxetic surfaces at an architectural scale. The auxetic behavior is accomplished through buckling and hinging by subtracting from a homogeneous material to create perforated patterns. The form of the perforations, including shape, scale, and spacing, determines the behavior of multiple compliant "hinges" generating novel patterns that include scaling and tweening transformations. An analytical method was introduced to generate hinge designs in four-fold symmetric structures that approximate non-linear buckling. The digital workflow integrates a parametric geometry model with non-linear finite element analysis (FEA) and physical prototypes to rapidly and accurately design and fabricate auxetic materials. A robotic 6-axis waterjet allowed for rapid production while maintaining needed tolerances. Fabrication methods allowed for spatially complex shaping, thus broadening the design scope of transformative auxetic material systems by including graphical and topographical biases. The work culminated in a large-scale fully actuated and digitally controlled installation. It was comprised of auxetic surfaces that displayed different degrees of porosity, contracting and expanding while actuated electromechanically. The results provide a promising application for the rapid design of non-linear auxetic materials at scales complimentary to architectural products.
keywords	material and construction; CAM; prototyping; smart materials; auxetic
series	ACADIA
email
last changed	2022/06/07 07:58

_id	ecaade2018_325
id	ecaade2018_325
authors	Peteinarelis, Alexandros and Yiannoudes, Socrates
year	2018
title	Parametric Models and Algorithmic Thinking in Architectural Education
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. 401-410
doi	https://doi.org/10.52842/conf.ecaade.2018.2.401
summary	Part of our research and teaching agenda at the School of Architecture of the Technical University of Crete focuses on algorithmic design with parametric models, its methodological characteristics and the study of applied and theoretical work that defined this architectural design thinking. Our work challenges architectural design processes, through the systematic study of parametric models. This paper presents three projects from the undergraduate elective course "Special Topics in Architectural Design", which took place during the spring semester of 2017, that investigated parametric models for a given architectural problem, inspired, to some extent, by precedents in 20th century architecture where students traced algorithmic design thinking. Although students understood well the concept and function of parametric models and in many cases applied them successfully for their design objectives, several of them did not fully assimilate some critical aspects of computation. This allowed us to determine areas of improvement and points of complete reevaluation in our educational strategy approach.
keywords	algorithmic thinking; parametric model; computational thinking; architectural education; Frei Otto
series	eCAADe
email
last changed	2022/06/07 08:00

_id	ecaade2017_302
id	ecaade2017_302
authors	Saleh Tabari, Mohammad Hassan, Kalantari, Saleh and Ahmadi, Nooshin
year	2017
title	Biofilm-inspired Formation of Artificial Adaptive Structures
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 303-312
doi	https://doi.org/10.52842/conf.ecaade.2017.2.303
summary	Todays design researchers are beginning to develop a process-based approach to biomimicry. Instead of merely looking at static natural structures for inspiration, we are learning to draw from the underlying organic processes that lead to the creation of those structures. This paradigm shift points us in the direction of adaptive fabrication systems that can grow through processes of self-assembly and can reconfigure themselves to meet the contours of local environments. In this study we examined the structural growth patterns of bacterial biofilms as a basis for a new kind of artificial, self-assembling module. This demonstration of bio-inspired design shows how contemporary technology allows us to harness the lessons of evolution in new and innovative ways. By exploring the dynamic assembly of complex structural formations in nature, we are able to derive new resource-efficient approaches to adaptable designs that are suited to changing environments. Ultimately we aspire to produce fully synthetic analogues that follow similar patterns of self-assembly to those found in bacterial biofilm colonies. Designers have only just begun to explore the tremendous wealth of natural form-creation processes that can now be replicated with computer-aided design and fabrication; this project shows just one example of what the future might hold.
keywords	Biofilm; Adaptive Structure; Formation; Quorum Sensing; Parametric Condition
series	eCAADe
email
last changed	2022/06/07 07:56

_id	acadia17_474
id	acadia17_474
authors	Peng, Wenzhe; Zhang, Fan; Nagakura, Takehiko
year	2017
title	Machines’ Perception of Space: Employing 3D Isovist Methods and a Convolutional Neural Network in Architectural Space Classification
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 474- 481
doi	https://doi.org/10.52842/conf.acadia.2017.474
summary	Simple and common architectural elements can be combined to create complex spaces. Different spatial compositions of elements define different spatial boundaries, and each produces a unique local spatial experience to observers inside the space. Therefore an architectural style brings about a distinct spatial experience. While multiple representation methods are practiced in the field of architecture, there lacks a compelling way to capture and identify spatial experiences. Describing an observer’s spatial experiences quantitatively and efficiently is a challenge. In this paper, we propose a method that employs 3D isovist methods and a convolutional neural network (CNN) to achieve recognition of local spatial compositions. The case studies conducted validate that this methodology works well in capturing and identifying local spatial conditions, illustrates the pattern and frequency of their appearance in designs, and indicates peculiar spatial experiences embedded in an architectural style. The case study used small designs by Mies van der Rohe and Aldo van Eyck. The contribution of this paper is threefold. First, it introduces a sampling method based on 3D Isovist that generates a 2D image that can be used to represent a 3D space from a specific observation point. Second, it employs a CNN model to extract features from the sampled images, then classifies their corresponding space. Third, it demonstrates a few case studies where this space classification method is applied to different architectural styles.
keywords	design methods; information processing; AI; machine learning; computer vision; representation
series	ACADIA
email
last changed	2022/06/07 08:00

_id	ecaade2017_202
id	ecaade2017_202
authors	Sollazzo, Aldo, Trento, Armando and Baseta, Efilena
year	2017
title	Machinic Agency - Implementing aerial robotics and machine learning to map public space
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 611-618
doi	https://doi.org/10.52842/conf.ecaade.2017.2.611
summary	The research presented in this paper is focused on proposing a new digital workflow, involving unmanned aerial vehicles (UAV) and machines learning systems, in order to detect and map citizen's behaviors in the context of public spaces.Novel machinic abilities can be implemented in the understanding of the human context, decoding, through computer visions and machine learning, complex systems into intelligible outputs (Olson, 2008), mapping the relationships of our reality. In this framework, robotic and computational strategies can be implemented in order to offer a new description of public spaces, bringing to light the hidden forces and multiple layers constituting the urban habitat. The presented study focuses on the development of a methodology turning video frames collected from cameras installed on drones into large datasets used to train convolutional networks and enable machines learning systems to detect and map pedestrians in public spaces.
keywords	mapping; drones; machine learning; computer vision; city
series	eCAADe
email
last changed	2022/06/07 07:56

_id	ecaade2017_009
id	ecaade2017_009
authors	Takizawa, Atsushi and Furuta, Airi
year	2017
title	3D Spatial Analysis Method with First-Person Viewpoint by Deep Convolutional Neural Network with Omnidirectional RGB and Depth Images
source	Fioravanti, A, Cursi, S, Elahmar, S, Gargaro, S, Loffreda, G, Novembri, G, Trento, A (eds.), ShoCK! - Sharing Computational Knowledge! - Proceedings of the 35th eCAADe Conference - Volume 2, Sapienza University of Rome, Rome, Italy, 20-22 September 2017, pp. 693-702
doi	https://doi.org/10.52842/conf.ecaade.2017.2.693
summary	The fields of architecture and urban planning widely apply spatial analysis based on images. However, many features can influence the spatial conditions, not all of which can be explicitly defined. In this research, we propose a new deep learning framework for extracting spatial features without explicitly specifying them and use these features for spatial analysis and prediction. As a first step, we establish a deep convolution neural network (DCNN) learning problem with omnidirectional images that include depth images as well as ordinary RGB images. We then use these images as explanatory variables in a game engine to predict a subjects' preference regarding a virtual urban space. DCNNs learn the relationship between the evaluation result and the omnidirectional camera images and we confirm the prediction accuracy of the verification data.
keywords	Space evaluation; deep convolutional neural network; omnidirectional image; depth image; Unity; virtual reality
series	eCAADe
email
last changed	2022/06/07 07:56

_id	acadia17_164
id	acadia17_164
authors	Brugnaro, Giulio; Hanna, Sean
year	2017
title	Adaptive Robotic Training Methods for Subtractive Manufacturing
source	ACADIA 2017: DISCIPLINES & DISRUPTION [Proceedings of the 37th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-96506-1] Cambridge, MA 2-4 November, 2017), pp. 164-169
doi	https://doi.org/10.52842/conf.acadia.2017.164
summary	This paper presents the initial developments of a method to train an adaptive robotic system for subtractive manufacturing with timber, based on sensor feedback, machine-learning procedures and material explorations. The methods were evaluated in a series of tests where the trained networks were successfully used to predict fabrication parameters for simple cutting operations with chisels and gouges. The results suggest potential benefits for non-standard fabrication methods and a more effective use of material affordances.
keywords	design methods; information processing; construction; robotics; ai & machine learning; digital craft; manual craft
series	ACADIA
email
last changed	2022/06/07 07:52

_id	caadria2017_105
id	caadria2017_105
authors	Janssen, Patrick
year	2017
title	Evolutionary Urbanism - Exploring Form-based Codes Using Neuroevolution Algorithms
source	P. Janssen, P. Loh, A. Raonic, M. A. Schnabel (eds.), Protocols, Flows, and Glitches - Proceedings of the 22nd CAADRIA Conference, Xi'an Jiaotong-Liverpool University, Suzhou, China, 5-8 April 2017, pp. 303-312
doi	https://doi.org/10.52842/conf.caadria.2017.303
summary	Form-Based Codes are legal regulations adopted by local government that allow specific urban forms to be achieved. Such codes have a significant impact on the performative potential of the urban environment. This paper explores the possibility of using a neuroevolution algorithm to elucidate the complex relationship between Form-based Codes and their performative potential. More specifically, Compositional Pattern Producing Networks (CPPN) are used to generate parameter fields, which then drive the generation of varied urban models. For evolving the CPPN networks, a neuroevolution algorithm is used, called Neuroevolution of Augmenting Topologies (NEAT). In order to test the feasibility of the proposed approach, an abstract experiment is described in which a population of urban models are evolved, optimising a set of performance criteria related to the vista and location of the residential units.
keywords	Form-based codes; evolutionary design; neural networks; neuroevolution; urban planning
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ijac201715102
id	ijac201715102
authors	Klemmt, Christoph and Klaus Bollinger
year	2017
title	Angiogenesis as a model for the generation of load-bearing networks
source	International Journal of Architectural Computing vol. 15 - no. 1, 18-36
summary	This research suggests an algorithm to generate structural networks based on discreet elements for given locations of support points and point loads. Previous research attempted to achieve this by using a computational growth simulation of venation systems, which form the structure of leaves. However, such networks always start from a single point and therefore cannot be used to form arches or beams. In order to generate networks that are based on two or three support points, an algorithm has been developed that is inspired instead by angiogenesis, the process by which vascular systems develop. The algorithm is based on a spring system with a variable network graph that connects the support points and is pulled upwards and split sideways into multiple veins by a given set of load points. The algorithm has been used to grow architectural structures. Different networks have been tested using finite element analysis and compared with both venation and column-and-beam structures. The angiogenesis networks as well as the venation network are shown to perform well and may be suitable as architectural structural systems.
keywords	Architecture, angiogenesis, structure, network, growth
series	other
type	normal paper
email
last changed	2019/08/02 08:25

_id	cf2017_110
id	cf2017_110
authors	Koenig, Reinhard; Miao, Yufan; Knecht, Katja; Bus, Peter; Mei-Chih, Chang
year	2017
title	Interactive Urban Synthesis: Computational Methods for Fast Prototyping of Urban Design Proposals
source	Gülen Çagdas, Mine Özkar, Leman F. Gül and Ethem Gürer (Eds.) Future Trajectories of Computation in Design [17th International Conference, CAAD Futures 2017, Proceedings / ISBN 978-975-561-482-3] Istanbul, Turkey, July 12-14, 2017, p. 110.
summary	In this paper, we present a method for generating fast conceptual urban design prototypes. We synthesize spatial configurations for street networks, parcels and building volumes. Therefore, we address the problem of implementing custom data structures for these configurations and how the generation process can be controlled and parameterized. We exemplify our method by the development of new components for Grasshopper/Rhino3D and their application in the scope of selected case studies. By means of these components, we show use case applications of the synthesis algorithms. In the conclusion, we reflect on the advantages of being able to generate fast urban design prototypes, but we also discuss the disadvantages of the concept and the usage of Grasshopper as a user interface.
keywords	Procedural grammars, Artificial intelligence in design, Urban synthesis, Generative design, Grasshopper plugin, Cognitive design computing
series	CAAD Futures
email
last changed	2017/12/01 14:37

_id	caadria2017_063
id	caadria2017_063
authors	Ma, Yidong and Xu, Weiguo
year	2017
title	Physarealm - A Bio-inspired Stigmergic Algorithm Tool for Form-Finding
source	P. Janssen, P. Loh, A. Raonic, M. A. Schnabel (eds.), Protocols, Flows, and Glitches - Proceedings of the 22nd CAADRIA Conference, Xi'an Jiaotong-Liverpool University, Suzhou, China, 5-8 April 2017, pp. 499-508
doi	https://doi.org/10.52842/conf.caadria.2017.499
summary	Physarum Polycephalum is a widespread eukaryotic microbe capable of producing effective networks between food particles to solve spatial planning problems. This paper investigates a previous algorithm for simulating Physarum Polycephalum. An open-source tool named Physarealm is developed for simulation in Rhino's graphical algorithm editor, Grasshopper. The tool adopts a previous stigmergic multi-agent algorithm for simulation and expands its boundary into three dimensions. In addition, this tool adds some custom rules, thus giving the designer more creative control over the produced results. Two research projects have applied this tool in the design process. The first project mainly takes advantage of the tool's path-planning ability, while the second one utilizes its aesthetic values, demonstrating the potential of the tool for further applications.
keywords	stigmergy; multi-agent systems; form finding; computation; biomimicry
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	ecaade2023_44
id	ecaade2023_44
authors	Mayrhofer-Hufnagl, Ingrid and Ennemoser, Benjamin
year	2023
title	From Linear to Manifold Interpolation: Exemplifying the paradigm shift through interpolation
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. 419–429
doi	https://doi.org/10.52842/conf.ecaade.2023.2.419
summary	The advent of artificial intelligence, specifically neural networks, has marked a significant turning point in the field of computation. During such transformative times, we are often faced with a dearth of appropriate vocabulary, which forces us to rely on existing terms, regardless of their inadequacy. This paper argues that the term “interpolation,” typically used in deep learning (DL), is a prime example of this phenomenon. It is not uncommon for beginners to misunderstand its meaning, as DL pioneer Francois Chollet (2017) has noted. This misreading is especially true in the discipline of architecture, and this study aims to demonstrate how the meaning of “interpolation” has evolved in the second digital turn. We begin by illustrating, using 2D data, the difference between linear interpolation in the context of topological figures and its use in DL algorithms. We then demonstrate how 3DGANs can be employed to interpolate across different topologies in complex 3D space, highlighting the distinction between linear and manifold interpolation. In both 2D and 3D examples, our results indicate that the process does not involve continuous morphing but instead resembles the piecing together of a jigsaw puzzle to form many parts of a larger ambient space. Our study reveals how previous architectural research on DL has employed the term “interpolation” without clarifying the crucial differences from its use in the first digital turn. We demonstrate the new possibilities that manifold interpolation offers for architecture, which extend well beyond parametric variations of the same topology.
keywords	Interpolation, 3D Generative Adversarial Networks, Deep Learning, Hybrid Space
series	eCAADe
email
last changed	2023/12/10 10:49

For more results click below: