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 567

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

_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
doi	https://doi.org/10.52842/conf.ecaade.2023.2.327
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
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	ecaade2017_243
id	ecaade2017_243
authors	Schwartz, Mathew and Zarzycki, Andrzej
year	2017
title	The Effect of Building Materials on LIDAR Measurements
doi	https://doi.org/10.52842/conf.ecaade.2017.2.269
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. 269-276
summary	This paper uses a Light Detection and Ranging (LIDAR) device with multiple building materials to provide guidance for developing an autonomous robotics-friendly environment. The results demonstrate various materials that not only provide missing data, such as for clear glass, but also can provide inaccurate data, a dangerous situation in the context of indoor autonomous mobility. Finally, the paper proposes ideas for how designers can compromise between the materials they would like to use while facilitating the necessary information for an autonomous vehicle.
keywords	Smart City; Autonomous Navigation; Indoor Navigation; Personal Mobility
series	eCAADe
email
last changed	2022/06/07 07:57

_id	acadia17_274
id	acadia17_274
authors	Hosseini, S. Vahab; Taron, Joshua M.; Alim, Usman R.
year	2017
title	Optically Illusive Architecture: Producing Depthless Objects Using Principles of Linear Perspective
doi	https://doi.org/10.52842/conf.acadia.2017.274
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. 274-283
summary	Architecture is a discipline with a long history of engagement with representational techniques borrowed from artforms such as painting and drawing. Historically, these techniques enable artists to translate three-dimensional space into a two-dimensional medium, while architecture tends to work in reverse, using the latter to express yet-to-be-realized projects in the former. This investigation leads to specific methods of linear perspectival representation that manipulate our perception of spatial depth, such as trompe l’oeil and anamorphic projection. Referencing these methods, we introduce the concept of an optically illusive architecture. While referencing a wide range of visually deceptive effects, we focus on synthesizing two-dimensional patterns into three-dimensional objects for the purpose of producing a depthless reading of three-dimensional space. In this paper, we outline optically illusive architecture and look at the initial stages of a design experiment that attempts to bring the perception of flatness into a three-dimensional object. This is achieved by building a simple algorithm that reverses linear perspectival projection to produce two-dimensional effects through a three-dimensional physical object. We analyze the results by comparing the two- and three-dimensional projections against one another from varying points of view in space, and speculate on the possible applications for such a design.
keywords	design methods; information processing; form finding; representation
series	ACADIA
email
last changed	2022/06/07 07:50

_id	acadia23_v3_71
id	acadia23_v3_71
authors	Vassigh, Shahin; Bogosian, Biayna
year	2023
title	Envisioning an Open Knowledge Network (OKN) for AEC Roboticists
source	ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 3: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-1-0]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 24-32.
summary	The construction industry faces numerous challenges related to productivity, sustainability, and meeting global demands (Hatoum and Nassereddine 2020; Carra et al. 2018; Barbosa, Woetzel, and Mischke 2017; Bock 2015; Linner 2013). In response, the automation of design and construction has emerged as a promising solution. In the past three decades, researchers and innovators in the Architecture, Engineering, and Construction (AEC) fields have made significant strides in automating various aspects of building construction, utilizing computational design and robotic fabrication processes (Dubor et al. 2019). However, synthesizing innovation in automation encounters several obstacles. First, there is a lack of an established venue for information sharing, making it difficult to build upon the knowledge of peers. First, the absence of a well-established platform for information sharing hinders the ability to effectively capitalize on the knowledge of peers. Consequently, much of the research remains isolated, impeding the rapid dissemination of knowledge within the field (Mahbub 2015). Second, the absence of a standardized and unified process for automating design and construction leads to the individual development of standards, workflows, and terminologies. This lack of standardization presents a significant obstacle to research and learning within the field. Lastly, insufficient training materials hinder the acquisition of skills necessary to effectively utilize automation. Traditional in-person robotics training is resource-intensive, expensive, and designed for specific platforms (Peterson et al. 2021; Thomas 2013).
series	ACADIA
type	field note
email
last changed	2024/04/17 13:59

_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	acadia17_138
id	acadia17_138
authors	Berry, Jaclyn; Park, Kat
year	2017
title	A Passive System for Quantifying Indoor Space Utilization
doi	https://doi.org/10.52842/conf.acadia.2017.138
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. 138-145
summary	This paper presents the development of a prototype for a new sensing device for anonymously evaluating space utilization, which includes usage factors such as occupancy levels, congregation and circulation patterns. This work builds on existing methods and technology for measuring building performance, human comfort and occupant experience in post-occupancy evaluations as well as pre-design strategic planning. The ability to collect data related to utilization and occupant experience has increased significantly due to the greater accessibility of sensor systems in recent years. As a result, designers are exploring new methods to empirically verify spatial properties that have traditionally been considered more qualitative in nature. With this premise, this study challenges current strategies that rely heavily on manual data collection and survey reports. The proposed sensing device is designed to supplement the traditional manual method with a new layer of automated, unbiased data that is capable of capturing environmental and social qualities of a given space. In a controlled experiment, the authors found that the data collected from the sensing device can be extrapolated to show how layout, spatial interventions or other design factors affect circulation, congregation, productivity, and occupancy in an office setting. In the future, this sensing device could provide designers with real-time feedback about how their designs influence occupants’ experiences, and thus allow the designers to base what are currently intuition-based decisions on reliable data and evidence.
keywords	design methods; information processing; smart buildings; IoT
series	ACADIA
email
last changed	2022/06/07 07:52

_id	acadia17_284
id	acadia17_284
authors	Hu, Zhengrong; Park, Ju Hong
year	2017
title	HalO [Indoor Positioning Mobile Platform]: A Data-Driven, Indoor-Positioning System With Bluetooth Low Energy Technology To Datafy Indoor Circulation And Classify Social Gathering Patterns For Assisting Post Occupancy Evaluation
doi	https://doi.org/10.52842/conf.acadia.2017.284
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. 284-291
summary	Post-Occupancy Evaluation (POE) as an integrated field between architecture and sociology has created practical guidelines for evaluating indoor human behavior within a built environment. This research builds on recent attempts to integrate datafication and machine learning into POE practices that may one day assist Building Information Modeling (BIM) and multi-agent modeling. This research is based on two premises: 1) that the proliferation of Bluetooth Low Energy (BLE) technology allows us to collect a building user’s data cost-effectively and 2) that the growing application of machine learning algorithms allows us to process, analyze and synthesize data efficiently. This study illustrates that the mobile platform HalO can serve as a generic tool for datafication and automation of data analysis of the movement of a building user. In this research, the iOS mobile application HalO, combined with BLE beacons enable building providers (architects, developers, engineers and facility managers etc.) to collect the user’s indoor location data. Triangulation was used to pinpoint the user’s indoor positions, and k-means clustering was applied to classify users into different gathering groups. Through four research procedures—Design Intention Analysis, Data Collection, Data Storage and Data Analysis—the visualized and classified data helps building providers to better evaluate building performance, optimize building operations and improve the accuracy of simulations.
keywords	design methods; information processing; data mining; IoT; AI; machine learning
series	ACADIA
email
last changed	2022/06/07 07:49

_id	caadria2017_113
id	caadria2017_113
authors	Huang, Weixin, Lin, Yuming and Wu, Mingbo
year	2017
title	Spatial-Temporal Behavior Analysis Using Big Data Acquired by Wi-Fi Indoor Positioning System
doi	https://doi.org/10.52842/conf.caadria.2017.745
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. 745-754
summary	Understanding of people's spatial behavior is fundamental to architectural and urban design. However, traditional investigation methods applied in environmental behavior studies is highly limited regarding the amount of samples and regions it covers, which is not sufficient for the exploration of complex dynamic human behaviors and social activities in architectural space. Only recently the developments in indoor positioning system (IPS) and big data analysis technique have made it possible to conduct a full-time, full-coverage study on human environmental behavior. Among the variety IPS systems, the Wi-Fi IPS system is increasingly widely used because it is easy to be applied with acceptable cost. In this paper, we analyzed a 60-days anonymized data set, collected by a Wi-Fi IPS system with 110 Wi-Fi access points. The analysis revealed interesting patterns on people's behavior besides temporal spatial distribution, ranging from the cyclical fluctuation in human flow to behavioral patterns of sub-regions, some of which are not easy to be identified and interpreted by the traditional field observation. Through this case study, behavioral data from IPS system has exhibited great potential in bringing about profound changes in the study of environmental behavior.
keywords	environmental behavior study; Wi-Fi; indoor positioning system; big data; spatial temporal behavior; ski resort
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	acadia17_298
id	acadia17_298
authors	Johnson, Jason S.; Gardner, Guy
year	2017
title	Pareidolic Formations
doi	https://doi.org/10.52842/conf.acadia.2017.298
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. 298- 307
summary	The use of ornament in public space has been contested throughout history, and attitudes towards the articulation of building surfaces have shifted over time. Antoine Picon has argued that the use of ornament to communicate meaning and identity is returning to a place of cultural prominence. Well-established digital design and fabrication technologies have given rise to projects that integrate performance and aesthetics through the exploitation of form, pattern and ornament. These techniques allow the designer to inscribe and overlay data generated through performance simulation and environmental analysis, and formal relationships and fabrication processes onto materials and spatial fields, creating novel configurations and effects. Operating at a scale between object and building, public art, sculpture and architectural ornament allow for a particular type of interdisciplinary experimentation and hybrid practice. Three recent public art proposals illustrate an approach that composites multiple datasets to generate new relationships between aesthetic, environmental and functional considerations in order to activate public space. The proposals presented here put forward a set of tactics that can be deployed towards embedding overlapping data in public spaces. These proposals use pattern to form and form to pattern workflows as a way to produce multiple potential readings through pareidolia. This paper presents an investigation into how contemporary digital design and fabrication processes can bridge between performance and perception, and how ornament and pattern might be deployed for both formal and performative purposes to help foster a more personalized relationship with the urban spaces we occupy.
keywords	education, society & culture; data mining; form finding; education
series	ACADIA
email
last changed	2022/06/07 07:52

_id	acadia17_366
id	acadia17_366
authors	Lin, Yuming; Huang, Weixin
year	2017
title	Behavior Analysis and Individual Labeling Using Data from Wi-Fi IPS
doi	https://doi.org/10.52842/conf.acadia.2017.366
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. 366- 373
summary	It is fairly important for architects and urban designers to understand how different people interact with the environment. However, traditional investigation methods for studying environmental behavior are quite limited in their coverage of samples and regions, which are not sufficient to delve into the behavioral differences of people. Only recently, the development of indoor positioning systems (IPS) and data-mining techniques has made it possible to collect full-time, full-coverage data for behavioral difference research and individualized identification. In our research, the Wi-Fi IPS system is chosen among the various IPS systems as the data source due to its extensive applicability and acceptable cost. In this paper, we analyzed a 60-day anonymized dataset from a ski resort, collected by a Wi-Fi IPS system with 110 Wi-Fi access points. Combining this with mobile phone data and questionnaires, we revealed some interesting characteristics of tourists from different origins through spatial-temporal behavioral data, and further conducted individual labeling through supervised learning. Through this case study, temporal-spatial behavioral data from an IPS system exhibited great potential in revealing individual characteristics besides exploring group differences, shedding light on the prospect of architectural space personalization.
keywords	design methods; information processing; data mining; big data
series	ACADIA
email
last changed	2022/06/07 07:59

_id	ijac201715104
id	ijac201715104
authors	Matalucci, Berardo; Kenton Phillips, Alicia A Walf, Anna Dyson and Joshua Draper
year	2017
title	An experimental design framework for the personalization of indoor microclimates through feedback loops between responsive thermal systems and occupant biometrics
source	International Journal of Architectural Computing vol. 15 - no. 1, 54-69
summary	How can building technologies accommodate different and often conflicting user preferences without dissolving the social cohesiveness, intrinsic of every architectural intervention? Individual thermal comfort has often been considered a negligible sensorial experience by modern heating and cooling technologies, and is often influenced by large-group norms. Alternatively, we propose that buildings are repositories of indoor microclimates that can be realized to provide personalized comfort, to create healthier environments, and to enhance the attributes of architectural interventions into haptic dimensions. In response, the goal of this study is to characterize an experimental framework that integrates responsive thermal systems with occupants’ direct and indirect experience, which includes stress response and biometric data. A computational model was used up to inform and analyze thermal perception of subjects, and later tested in a responsive physical installation. While results show that thermal comfort assessment is affected by individual differences including cognitive functions and biometrics, further computational efforts are needed to validate biometric indicators. Finally, the implications of personalized built environments are discussed with respect to future technology developments and possibilities of design driven by biometric data.
keywords	Personalized thermal comfort, interactive building technologies, bio-feedback loops, indoor microclimates
series	other
type	normal paper
email
last changed	2019/08/02 08:28

_id	ecaade2017_059
id	ecaade2017_059
authors	Narangerel, Amartuvshin, Lee, Ji-Hyun and Stouffs, Rudi
year	2017
title	Thermal and Daylighting Optimization of Complex 3D Faceted Façade for Office Building
doi	https://doi.org/10.52842/conf.ecaade.2017.1.209
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. 209-218
summary	Conventional façade design and its impact on building energy as well as indoor comfort is a well-researched topic in the architecture field. This paper examines the potential of a complex 3D shaped building envelope, elaborating on previous work by implementing energy simulation within the building façade optimization process. The multi-objective optimizations are conducted considering total thermal energy, electricity generation through BIPV, and daylighting in generic single person office rooms under meteorological data of Korea and Singapore. The performance of the non-dominants is analyzed and the results show an improvement in all objectives comparing with the preliminary study.
keywords	Parametric facade design; muli-objective optimization; energy optimization; daylighting; form finding
series	eCAADe
email
last changed	2022/06/07 07:58

_id	caadria2017_129
id	caadria2017_129
authors	Patt, Trevor Ryan
year	2017
title	Toward Temporal and Punctual Urban Redevelopment in Dynamic, Informal Contexts - An Adaptive Masterplan Driven by Architectural Interventions Using Multiagent Modeling
doi	https://doi.org/10.52842/conf.caadria.2017.221
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. 221-230
summary	This paper presents design research speculating on new planning approaches for informal urban sites that enables coordinated planning to operate within the realm of spontaneous, bottom-up redevelopment. In opposition to the /tabula rasa/ Modernist development, this project reacts to the dynamic metabolism of the village and engages with the rapid turnover of the built environment of the village as a mechanism through which to implement incremental redevelopment. A radical reorientation of the object of masterplanning, this replaces the singular image or document as the guiding authority with a collection of opportunistic adaptations, temporal sequences, and localized procedures. Enabling this approach is a computational approach that analyzes the morphology of the public space network to identify opportunities to address issues in the composition of the village. A multiagent system driven by weighted random walks through the circulation network conducts local analyses of the urban fabric while changes are made and proposes potential modifications to discrete areas. The model simulates the potential for such a planning tool to be used over a long time span and updated with empirically gathered data, having the benefit of flexibility and resilience in the face of the changing and unregulated conditions in the context of informal urbanism.
keywords	generative design; responsive masterplanning; informal urbanism; network analysis; agent-based modeling
series	CAADRIA
email
last changed	2022/06/07 07:59

_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
doi	https://doi.org/10.52842/conf.caadria.2017.663
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
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	caadria2017_080
id	caadria2017_080
authors	Suzuki, Seiichi and Knippers, Jan
year	2017
title	Topology-driven Form-finding - Implementation of an Evolving Network Model for Extending Design Spaces in Dynamic Relaxation
doi	https://doi.org/10.52842/conf.caadria.2017.489
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. 489-498
summary	This paper introduces a novel computational design methodology called topology-driven for the numerical form-finding of discrete networks and presents the essential building block for storing and processing information. Numerical form-finding focuses on computing the optimum geometric configuration of lightweight structures in which shape is the result of reciprocal dependencies between forces, material behaviors and structural performances. Among the design community, Dynamic Relaxation (DR) has gained in popularity given its capacity to support more flexible and interactive design spaces in form-finding. However, common implementations of networks models only focus on the interactive exploration of material and geometrical properties without further specification for topological dynamization. For facing this problematic, we propose an object-oriented approach to attach specific functionalities to particular pieces of data within the numerical schema. Here, we describe the implementation of a rule-based system for managing objects´ interactions in order to continuously track topological and geometrical changes. Based on this concept, larger design spaces can be developed for the interactive exploration of structural shapes.
keywords	Topology-driven; Form-Finding; Dynamic Relaxation; Object Structures; Design Spaces
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	caadria2017_081
id	caadria2017_081
authors	Yokoi, Kazuki, Fukuda, Tomohiro, Yabuki, Nobuyoshi and Motamedi, Ali
year	2017
title	Integrating BIM, CFD and AR for Thermal Assessment of Indoor Greenery
doi	https://doi.org/10.52842/conf.caadria.2017.085
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. 85-94
summary	The renovation projects to improve the thermal environment are gaining importance because of energy saving effects and occupants' health considerations. However, the indoor thermal design is not usu-ally performed in a very efficient manner by owners and designers because the architectural design data including the indoor thermal design is not centrally managed among all professional designers. Additionally, the visualizations of the CFD simulation results are difficult for the stakeholders to understand. On the other hand, greenery has been introduced to buildings as a method for adjusting the thermal condition. The research goal presented in this paper is to investigate a cooperative architectural design process for the thermal environment by developing a system in which BIM, CFD, and AR are integrated to provide interactive visualizations. Case studies are performed to verify the developed system and to assess the thermal effects of multiple indoor greenery design options.
keywords	Interdisciplinary Computational Design; Indoor Thermal Environment; Computational Fluid Dynamics (CFD); Augmented Reality (AR); Indoor Greenery
series	CAADRIA
email
last changed	2022/06/07 07:57

_id	acadia17_164
id	acadia17_164
authors	Brugnaro, Giulio; Hanna, Sean
year	2017
title	Adaptive Robotic Training Methods for Subtractive Manufacturing
doi	https://doi.org/10.52842/conf.acadia.2017.164
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
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	acadia20_382
id	acadia20_382
authors	Hosmer, Tyson; Tigas, Panagiotis; Reeves, David; He, Ziming
year	2020
title	Spatial Assembly with Self-Play Reinforcement Learning
doi	https://doi.org/10.52842/conf.acadia.2020.1.382
source	ACADIA 2020: Distributed Proximities / Volume I: Technical Papers [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95213-0]. Online and Global. 24-30 October 2020. edited by B. Slocum, V. Ago, S. Doyle, A. Marcus, M. Yablonina, and M. del Campo. 382-393.
summary	We present a framework to generate intelligent spatial assemblies from sets of digitally encoded spatial parts designed by the architect with embedded principles of prefabrication, assembly awareness, and reconfigurability. The methodology includes a bespoke constraint-solving algorithm for autonomously assembling 3D geometries into larger spatial compositions for the built environment. A series of graph-based analysis methods are applied to each assembly to extract performance metrics related to architectural space-making goals, including structural stability, material density, spatial segmentation, connectivity, and spatial distribution. Together with the constraint-based assembly algorithm and analysis methods, we have integrated a novel application of deep reinforcement (RL) learning for training the models to improve at matching the multiperformance goals established by the user through self-play. RL is applied to improve the selection and sequencing of parts while considering local and global objectives. The user’s design intent is embedded through the design of partial units of 3D space with embedded fabrication principles and their relational constraints over how they connect to each other and the quantifiable goals to drive the distribution of effective features. The methodology has been developed over three years through three case study projects called ArchiGo (2017–2018), NoMAS (2018–2019), and IRSILA (2019-2020). Each demonstrates the potential for buildings with reconfigurable and adaptive life cycles.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	acadia17_552
id	acadia17_552
authors	Sjoberg, Christian; Beorkrem, Christopher; Ellinger, Jefferson
year	2017
title	Emergent Syntax: Machine Learning for the Curation of Design Solution Space
doi	https://doi.org/10.52842/conf.acadia.2017.552
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. 552- 561
summary	The expanding role of computational models in the process of design is producing exponential growth in parameter spaces. As designers, we must create and implement new methods for searching these parameter spaces, considering not only quantitative optimization metrics but also qualitative features. This paper proposes a methodology that leverages the pattern modeling properties of artificial neural networks to capture designers' inexplicit selection criteria and create user-selection-based fitness functions for a genetic solver. Through emulation of learned selection patterns, fitness functions based on trained networks provide a method for qualitative evaluation of designs in the context of a given population. The application of genetic solvers for the generation of new populations based on the trained network selections creates emergent high-density clusters in the parameter space, allowing for the identification of solutions that satisfy the designer’s inexplicit criteria. The results of an initial user study show that even with small numbers of training objects, a search tool with this configuration can begin to emulate the design criteria of the user who trained it.
keywords	design methods; information processing; AI; machine learning; generative system
series	ACADIA
email
last changed	2022/06/07 07:56

_id	caadria2017_131
id	caadria2017_131
authors	Abe, U-ichi, Hotta, Kensuke, Hotta, Akito, Takami, Yosuke, Ikeda, Hikaru and Ikeda, Yasushi
year	2017
title	Digital Construction - Demonstration of Interactive Assembly Using Smart Discrete Papers with RFID and AR codes
doi	https://doi.org/10.52842/conf.caadria.2017.075
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. 75-84
summary	This paper proposes and examines a new way of cooperation between human workers and machine intelligence in architectural scale construction. For the transfer of construction information between the physical and digital world, mature technologies such as Radio Frequency IDentifier (RFID), and emerging technologies like Augmented Reality (AR) are used in parallel to supplement each other. Dynamic data flow is implemented to synchronize digital and physical models by following the ID signatures of individual building parts. The contributions of this paper includes the demonstration of current technological limitations, and the proposal of a hybrid system between human and computer, which is tested in order to explore the possibilities of digitally enhanced construction methods.
keywords	Digital Construction; Augmented Reality; Human-Machine interaction
series	CAADRIA
email
last changed	2022/06/07 07:54

For more results click below: