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 632

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

_id	artificial_intellicence2019_147
id	artificial_intellicence2019_147
authors	Ding Wen Bao, Xin Yan, Roland Snooks, and Yi Min Xie
year	2020
title	Bioinspired Generative Architectural Design Form-Finding and Advanced Robotic Fabrication Based on Structural Performance
source	Architectural Intelligence Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2024)
doi	https://doi.org/https://doi.org/10.1007/978-981-15-6568-7_10
summary	Due to the potential to generate forms with high efficiency and elegant geometry, topology optimization is widely used in architectural and structural designs. This paper presents a working flow of form-finding and robotic fabrication based BESO (Bi-directional Evolutionary Structure Optimization) optimization method. In case there are some other functional requirements or condition limitations, some useful modifications are also implemented in the process. With this kind of working flow, it is convenient to foreknow or control the structural optimization direction before the optimization process. Furthermore, some fabrication details of the optimized model will be discussed because there are also many notable technical points between computational optimization and robotic fabrication.
series	Architectural Intelligence
email
last changed	2022/09/29 07:28

_id	cdrf2019_36
id	cdrf2019_36
authors	Dan Luo, Joseph M. Gattas, and Poah Shiun Shawn Tan
year	2020
title	Real-Time Defect Recognition and Optimized Decision Making for Structural Timber Jointing
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_4
summary	Non-structural or out-of-grade timber framing material contains a large proportion of visual and natural defects. A common strategy to recover usable material from these timbers is the marking and removing of defects, with the generated intermediate lengths of clear wood then joined into a single piece of fulllength structural timber. This paper presents a novel workflow that uses machine learning based image recognition and a computational decision-making algorithm to enhance the automation and efficiency of current defect identification and rejoining processes. The proposed workflow allows the knowledge of worker to be translated into a classifier that automatically recognizes and removes areas of defects based on image capture. In addition, a real-time optimization algorithm in decision making is developed to assign a joining sequence of fragmented timber from a dynamic inventory, creating a single piece of targeted length with a significant reduction in material waste. In addition to an industrial application, this workflow also allows for future inventory-constrained customizable fabrication, for example in production of non-standard architectural components or adaptive reuse or defect-avoidance in out-of-grade timber construction.
series	cdrf
email
last changed	2022/09/29 07:51

_id	ecaade2020_183
id	ecaade2020_183
authors	Zhao, Jiangyang, Lombardi, Davide and Agkathidis, Asterios
year	2020
title	Application of Robotic Technologies for the Fabrication Of Traditional Chinese Timber Joints
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 351-360
doi	https://doi.org/10.52842/conf.ecaade.2020.2.351
summary	The traditional Chinese building design was influenced by the climate and the sociogeographical conditions of the different regions in China. They were usually constructed out of wood relying on timber-joint based construction systems. Amongst the wide variety of the structural elements, the Dougong (bucket arch) is one of the most common components of traditional wooden framework buildings, presenting a high level of complexity. Parametric design and robotic technology enable new possibilities regarding its fabrication and application in contemporary architecture. Our paper will explore how the Dougong components could be reinvented through the use of parametric tools and robotic fabrication methods and thus applied to contemporary architectural structures. We will analyse and compare the properties of the original Dougong with the reinvented unit by using finite element analysis and digital optimization tools. Our findings will provide an insight into the traditional construction principles of the joint and how these can inform a design and fabrication framework for its application in contemporary buildings.
keywords	Dougong joint; timber structures; parametric design; robotic fabrication; optimization algorithm
series	eCAADe
email
last changed	2022/06/07 07:57

_id	acadia20_114p
id	acadia20_114p
authors	Zivkovic, Sasa; Havener, Brian; Battaglia, Christopher
year	2020
title	Log Knot
source	ACADIA 2020: Distributed Proximities / Volume II: Projects [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95253-6]. Online and Global. 24-30 October 2020. edited by M. Yablonina, A. Marcus, S. Doyle, M. del Campo, V. Ago, B. Slocum. 114-119.
summary	Log Knot, developed by the Robotic Construction Laboratory (RCL) at Cornell University, is a robotically fabricated architectural installation that establishes a method for variable compound timber curvature creation utilizing both regular and irregular roundwood geometries. Moreover, the project develops methods for minimal formwork assembly and moment force optimization of customized mortise and tenon joints. Following the logic of a figure-8 knot, the project consists of an infinite loop of roundwood, curving three-dimensionally along its length. There are a variety of techniques to generate single curvature in wood structures – such as steam bending (Wright et al., 2013) or glue lamination (Issa and Kmeid, 2005) – but only a few techniques to generate complex curvature from raw material within a single wooden structural element exist. To construct complex curvature, the research team developed a simple method that can easily be replicated. First, the log is compartmentalized, establishing a series of discrete parts. Second, the parts are reconfigured into a complex curvature “whole” by carefully manipulating the assembly angles and joints between the logs. Timber components reconfigured in such a manner can either follow planar curvature profiles or spatial compound curvature profiles. Based on knowledge gained from the initial joinery tests, the research team developed a custom tri-fold mortise and tenon joint, which is self-supportive during assembly and able to resist bending in multiple directions. Using the tri-fold mortise and tenon joint, a number of full-scale prototypes were created to test the structural capacity of the overall assembly. Various structural optimization protocols are deployed in the Log Knot project. While the global knot form is derived from spatial considerations – albeit within the structurally sound framework of a closed-loop knot structure – the project is structurally optimized at a local level, closely calibrating structural cross-sections, joinery details, and joint rotation in relation to prevailing load conditions.
series	ACADIA
type	project
email
last changed	2021/10/26 08:03

_id	acadia20_208p
id	acadia20_208p
authors	Bernier-Lavigne, Samuel
year	2020
title	Object-Field
source	ACADIA 2020: Distributed Proximities / Volume II: Projects [Proceedings of the 40th Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 978-0-578-95253-6]. Online and Global. 24-30 October 2020. edited by M. Yablonina, A. Marcus, S. Doyle, M. del Campo, V. Ago, B. Slocum. 208-213
summary	This project aims to continue the correlative study between two fundamental entities of digital architecture: the object and the field. Following periods of experimentations on the ""field"" (materialization of flows of data through animation), the ""field of objects"" (parametricism), the ""object"" (OOO), we investigate the last possible interaction remaining: the ""object-field,"" by merging the formal characteristics of the object with the structural flow of its internal field. This investigation is achieved by exploring the high-resolution features of 3d printing in the design of autonomous architectural objects expressing materiality through topological optimization. The objects are generated by an iterative process of volumetric reduction, resulting in an ensemble of monoliths. Four of them are selected and analyzed through topological optimization in order to extract their internal fields. Next, a series of high-resolution algorithmic systems translate the structural information into 3d printed materiality. Of the four object-fields, one materializes, close to identical, the result of the optimization, giving the keystone to understanding the others. The second one expresses the structural flow through a 1mm voxel system, informed by the optimization, having the effect of stiffening the structure where it is needed and thus generating a new topography on the object. The last two explore the blur that this high-resolution can paradoxically create, with complete integration of the optimal structure in a transparent monolith. This is achieved by a vertex displacement algorithm, and the dissolution of the formal data of the monolith and the structural flows, through the mereological assembly of simple linear elements. For each object-field, a series of drawings was developed using specific algorithmic procedures derived from the peculiarities of their complex geometry. The drawings aim to catalyze coherence throughout the project, where similarities, hitherto kept apart by the multiple materialities, begin to dialogue.
series	ACADIA
type	project
email
last changed	2021/10/26 08:08

_id	sigradi2020_615
id	sigradi2020_615
authors	Borges, Marina Ferreira
year	2020
title	Structural Flexibility and Space Articulation in Architectural Design Teaching
source	SIGraDi 2020 [Proceedings of the 24th Conference of the Iberoamerican Society of Digital Graphics - ISSN: 2318-6968] Online Conference 18 - 20 November 2020, pp. 615-620
summary	The separation between architectural design teaching and structural education corroborates the division of labor in professional practice that cannot support the development of dialectical relations between architects and engineers. Thus, the proposal of hybridization between architectural design teaching and structural education developed in this article presupposes a shift from the centrality given to the plastic and spatial principles of the architectural form to the development of approaches that are oriented towards the recognition of the material and constructive questions which aided by the parametric and structural behavior simulation tools allow the development of complex relationships based on tectonic procedural logic.
keywords	Architectural design teaching, Structural education, Parametric design, Performance-based design
series	SIGraDi
email
last changed	2021/07/16 11:52

_id	acadia20_74
id	acadia20_74
authors	Bucklin, Oliver; Born, Larissa; Körner, Axel; Suzuki, Seiichi; Vasey, Lauren; T. Gresser, Götz; Knippers, Jan; Menges,
year	2020
title	Embedded Sensing and Control
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. 74-83.
doi	https://doi.org/10.52842/conf.acadia.2020.1.074
summary	This paper investigates an interactive and adaptive control system for kinetic architectural applications with a distributed sensing and actuation network to control modular fiber-reinforced composite components. The aim of the project was to control the actuation of a foldable lightweight structure to generate programmatic changes. A server parses input commands and geometric feedback from embedded sensors and online data to drive physical actuation and generate a digital twin for real-time monitoring. Physical components are origami-like folding plates of glass and carbon-fiber-reinforced plastic, developed in parallel research. Accelerometer data is analyzed to determine component geometry. A component controller drives actuators to maintain or move towards desired positions. Touch sensors embedded within the material allow direct control, and an online user interface provides high-level kinematic goals to the system. A hierarchical control system parses various inputs and determines actuation based on safety protocols and prioritization algorithms. Development includes hardware and software to enable modular expansion. This research demonstrates strategies for embedded networks in interactive kinematic structures and opens the door for deeper investigations such as artificial intelligence in control algorithms, material computation, as well as real-time modeling and simulation of structural systems.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2020_478
id	ecaade2020_478
authors	Han, Yoon J. and Kotnik, Toni
year	2020
title	A Tomographic computation of Spatial Dynamics
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 2, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 89-94
doi	https://doi.org/10.52842/conf.ecaade.2020.2.089
summary	Waning of vigorous discourses about the idea of space as essence in architectural design concurred with the emergence of digital architecture. The notion of space was replaced with the underlying notion of form facilitating optimization of performances and form-generation in digital design ever since. Within the context of digital architecture, the current research investigates a formal method to reintroduce spatial aspects, based on dynamics of architectural space in relation to form, into digital design processes. Accordingly, a computational framework is devised employing the idea of space as dynamic field conditions, in order to capture dynamic interrelation of architectural space with architectural form. That is, spatial dynamics are regarded as data embedded in architectural space, that can imply operational aspects of spatial experiences and / or stimulate corporeal engagements with experiential space, as concepts as action potentials and affordances do (Rasmussen 1964). As a result, the research aims to contribute to the body of knowledge that endeavour to systematize architectural sensibilities that are implicit in design processes by externalization utilizing computation.
keywords	spatial dynamics; dynamic field conditions; dynamic displacement
series	eCAADe
email
last changed	2022/06/07 07:50

_id	cdrf2021_13
id	cdrf2021_13
authors	Hao Wen, Pengcheng Gu, Yuchao Zhang, Shuai Zou, and Patrik Schumacher
year	2021
title	A Generative Approach to Social Ecologies in Project [Symbios]City
source	Proceedings of the 2021 DigitalFUTURES The 3rd International Conference on Computational Design and Robotic Fabrication (CDRF 2021)
doi	https://doi.org/https://doi.org/10.1007/978-981-16-5983-6_2
summary	The following paper talks about the studio project [Symbios]City, which is developed as a design research project in 2020–2021 Schumacher’ studio on social ecology of the graduate program in Architectural Association’s design research lab. The project aims to create an assemblage of social ecologies through a rich but cohesive multi-authored urban district. The primary ambition is to generate an urban area with a characterful, varied identity, that achieves a balanced order between unity and difference avoiding both the sterile and disorienting monotony of centrally planned modernist cities and the (equally disorienting) visual chaos of an agglomeration of utterly unrelated interventions as we find now frequently. Through a thorough research process, our project evolves mainly out of three principles that are taken into consideration for the development of our project: topological optimization, phenomenology, and ecology. By “ecology”, we understand it as a living network of information exchange. Therefore, every strategy we employ is not merely about reacting to the weather conditions, but instead it is an inquiry into the various ways we can exploit the latter, a translation of the weather conditions into spatial and programmatic properties. [Symbios]City therefore aims at developing a multi-authored urban area with a rich identity that achieves a balance between the various elements. [Symbios]City began formally from topological optimization, developed based on studies on ecology, and concluded the design following our phenomenological explorations, aiming at a complex design project that unifies the perception of all scales of design: from the platform to the skyscrapers.
series	cdrf
email
last changed	2022/09/29 07:53

_id	artificial_intellicence2019_207
id	artificial_intellicence2019_207
authors	Hao Zheng
year	2020
title	Form Finding and Evaluating Through Machine Learning: The Prediction of Personal Design Preference in Polyhedral Structures
source	Architectural Intelligence Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2025)
doi	https://doi.org/https://doi.org/10.1007/978-981-15-6568-7_13
summary	3D Graphic Statics (3DGS) is a geometry-based structural design and analysis method, helping designers to generate 3D polyhedral forms by manipulating force diagrams with given boundary conditions. By subdividing 3D force diagrams with different rules, a variety of forms can be generated, resulting in more members with shorter lengths and richer overall complexity in forms. However, it is hard to evaluate the preference toward different forms from the aspect of aesthetics, especially for a specific architect with his own scene of beauty and taste of forms. Therefore, this article proposes a method to quantify the design preference of forms using machine learning and find the form with the highest score based on the result of the preference test from the architect. A dataset of forms was firstly generated, then the architect was asked to keep picking a favorite form from a set of forms several times in order to record the preference. After being trained with the test result, the neural network can evaluate a new inputted form with a score from 0 to 1, indicating the predicted preference of the architect, showing the possibility of using machine learning to quantitatively evaluate personal design taste.
series	Architectural Intelligence
email
last changed	2022/09/29 07:28

_id	ecaade2024_4
id	ecaade2024_4
authors	Irodotou, Louiza; Gkatzogiannis, Stefanos; Phocas, Marios C.; Tryfonos, George; Christoforou, Eftychios G.
year	2024
title	Application of a Vertical Effective Crank–Slider Approach in Reconfigurable Buildings through Computer-Aided Algorithmic Modelling
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 1, pp. 421–430
doi	https://doi.org/10.52842/conf.ecaade.2024.1.421
summary	Elementary robotics mechanisms based on the effective crank–slider and four–bar kinematics methods have been applied in the past to develop architectural concepts of reconfigurable structures of planar rigid-bar linkages (Phocas et al., 2020; Phocas et al., 2019). The applications referred to planar structural systems interconnected in parallel to provide reconfigurable buildings with rectangular plan section. In enabling structural reconfigurability attributes within the spatial circular section buildings domain, a vertical setup of the basic crank–slider mechanism is proposed in the current paper. The kinematics mechanism is integrated on a column placed at the middle of an axisymmetric circular shaped spatial linkage structure. The definition of target case shapes of the structure is based on a series of numerical geometric analyses that consider certain architectural and construction criteria (i.e., number of structural members, length, system height, span, erectability etc.), as well as structural objectives (i.e., structural behavior improvement against predominant environmental actions) aiming to meet diverse operational requirements and lightweight construction. Computer-aided algorithmic modelling is used to analyze the system's kinematics, in order to provide a solid foundation and enable rapid adaptation for mechanisms that exhibit controlled reconfigurations. The analysis demonstrates the implementation of digital parametric design tools for the investigation of the kinematics of the system at a preliminary design stage, in avoiding thus time-demanding numerical analysis processes. The design process may further provide enhanced interdisciplinary performance-based design outcomes.
keywords	Reconfigurable Structures, Spatial Linkage Structures, Kinematics, Parametric Associative Design
series	eCAADe
email
last changed	2024/11/17 22:05

_id	cdrf2019_217
id	cdrf2019_217
authors	Jinghua Song and Sirui Sun
year	2020
title	Research on Architectural Form Optimization Method Based on Environmental Performance-Driven Design
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_21
summary	In the context of contemporary environment and society, the architectural form optimization based on Environmental performance-driven design is a method by using environmental performance data to optimize the architectural form. Its value lies in dealing with the interaction between architecture and environment, and developing architecture with environmental sustainability. This thesis summarizes the similarities and differences between performance-driven form design and traditional bionic form design. The traditional bionic design separates the bionic object from its complex living environment, and its simple imitation tends to fall into the local rather than the global optimum. However, performancedriven design is different from bionic design. It advocates environmental factors as a driving factor rather than a confrontational factor. It is a systematic global optimal method for studying architectural form. This paper puts forward the specific architectural form optimization simulation process based on the performance-driven thought. Taking the multilayer parking building design of the riparian zone on the south bank of Chongqing as an example, the parametric design method is used to obtain architectural optimization form adapted to the environment.
series	cdrf
email
last changed	2022/09/29 07:51

_id	acadia20_506
id	acadia20_506
authors	Khalilbeigi Khameneh, Arman; Mottaghi, Esmaeil; Ghazvinian, Ali; Kalantari, Saeede
year	2020
title	Con-Create
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. 506-515.
doi	https://doi.org/10.52842/conf.acadia.2020.1.506
summary	Net structures, because of their minimal material waste and intuitive aesthetics, are gaining more interest recently. There are various efforts to redesign the tensile- and compression-only structures, as the computational tools and novel materials have broadened the scope of geometries possible to construct. However, the fabrication process of these structures faces different challenges, especially for mass construction. Some of these challenges are related to the technology and equipment utilized for materializing these complicated forms and geometries. Working with concrete as a quickly forming material for these irregular forms seems promising. Nevertheless, using this material has difficulties, including the preparation of formworks and joints, material reinforcement, structural behavior in the fresh state, and the assembly procedure. This paper introduces a method based on computational design and geometrical solutions to address some of these challenges. The goal is to shift the complexity of construction from the high-tech equipment used in the fabrication stage to integrating design and fabrication through a hierarchical system made entirely by affordable 2D CNC laser cutters. The stages of developing the method and the process of designing and building an architectural size proof-of-concept prototype by the proposed method are discussed. The efficiency of the method has been shown by comparing the designed prototype with the Con-Create Pavilion.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	caadria2020_064
id	caadria2020_064
authors	Liu, Yige, Chai, Hua and Yuan*, Philip F.
year	2020
title	Knitted Composites Tower - Design Research for Knitted Fabric Reinforced Composites Based on Advanced Knitting Technology
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 55-64
doi	https://doi.org/10.52842/conf.caadria.2020.1.055
summary	Faced with growing urbanization demands of developing countries and global shortages of construction materials, this research looks for an innovative light-weight high-performance material system for architectural applications. The knitted composites tower is a 7.2-meter, 260-kilogram and self-supported prototype that uses 2mm thick knitted fabric reinforced composites. The result is lightweight and strong. It demonstrates the design potentials of knitted fabric reinforced composites. This article takes knitted composites tower as an example to illustrate a design method for knitted fabric reinforced composites. The design method covers three aspects of structural form selection, structure arrangement, and microscopic configuration. At last, the complete fabrication and construction process will be discussed with a full-scale physical prototype.
keywords	Knitting; Composites; Architectural Design
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	caadria2020_035
id	caadria2020_035
authors	Pereira, InÃªs, BelÃ©m, Catarina and LeitÃ£o, AntÃ³nio
year	2020
title	Escaping Evolution - A Study on Multi-Objective Optimization
source	D. Holzer, W. Nakapan, A. Globa, I. Koh (eds.), RE: Anthropocene, Design in the Age of Humans - Proceedings of the 25th CAADRIA Conference - Volume 1, Chulalongkorn University, Bangkok, Thailand, 5-6 August 2020, pp. 295-304
doi	https://doi.org/10.52842/conf.caadria.2020.1.295
summary	The architectural field is currently experiencing a paradigm shift towards a more environmentally-aware design process. In this new paradigm, known as Performance-Based Design (PBD), building performance emerges as a guiding principle. Unfortunately, PBD entails several problems, for instance, building design is often associated with the simultaneous assessment of multiple performance criteria, which dramatically increases the complexity of the problem. In this vein, recent works claim that coupling optimization tools with PBD approaches allows for more efficient and optima-oriented strategies. This approach, known as Algorithmic Optimization, is based on the use of an optimization tool combined with a parametric model of a design to iteratively generate more efficient design alternatives. This paper focus on evaluating and comparing different classes of Multi-Objective Optimization (MOO) algorithms, namely, metaheuristics and model-based ones. In addition, in order to try to better understand the algorithms' suitability to different optimization problems, this research analyses two different MOO design problems.
keywords	Performance-Based Design; Algorithmic Optimization; Multi-Objective Optimization
series	CAADRIA
email
last changed	2022/06/07 08:00

_id	acadia20_248
id	acadia20_248
authors	Saha, Nirvik; Haymaker, John; Shelden, Dennis
year	2020
title	Space Allocation Techniques (SAT)
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. 248-257.
doi	https://doi.org/10.52842/conf.acadia.2020.1.248
summary	Architects and urban designers use space allocation to develop layouts constrained by project-specific attributes of spaces and relations between them. The space allocation problem (SAP) is a general class of computable problems that eluded automation due to combinatorial complexity and diversity of architectural forms. In this paper, we propose a solution to the space allocation problem using reinforcement learning (RL). In RL, an artificial agent interacts with a simulation of the design problem to learn the optimal spatial organization of a layout using a feedback mechanism based on project-specific constraints. Compared to supervised learning, where the scope of the design problem is restricted by the availability of prior samples, we developed a general approach using RL to address novel design problems, represented as SAP. We integrated the proposed solution to SAP with numerous geometry modules, collectively defined as the space allocation techniques (SAT). In this implementation, the optimization and generative modules are decoupled such that designers can connect the modules in various ways to generate layouts with desired geometric and topological attributes. The outcome of this research is a user-friendly, freely accessible Rhino Grasshopper (C#) plugin, namely, the Design Optimization Toolset or DOTs, a compilation of the proposed SAT. DOTs allows designers to interactively develop design alternatives that reconcile project-specific constraints with the geometric complexity of architectural forms. We describe how professional designers have applied DOTs in space planning, site parcellation, massing, and urban design problems that integrate with performance analysis to enable a holistic, semi-automated design exploration.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	ecaade2020_015
id	ecaade2020_015
authors	Yazici, Sevil
year	2020
title	A machine-learning model driven by geometry, material and structural performance data in architectural design process
source	Werner, L and Koering, D (eds.), Anthropologic: Architecture and Fabrication in the cognitive age - Proceedings of the 38th eCAADe Conference - Volume 1, TU Berlin, Berlin, Germany, 16-18 September 2020, pp. 411-418
doi	https://doi.org/10.52842/conf.ecaade.2020.1.411
summary	Artificial Intelligence (AI), based on interpretation of data, influences various professions including architectural design today. Although research on integrating conceptual design with Machine Learning (ML) algorithms as a subset of the AI has been investigated previously, there is not a framework towards integration of architectural geometry with material properties and structural performance data towards decision making in the early-design phase. Undertaking performance simulations require significant amount of computation power and time. The aim of this research is to integrate ML algorithms into design process to achieve time efficiency and improve design results. The proposed workflow consists of three stages, including generation of the parametric model; running structural performance simulations to collect the data, and operating the ML algorithms, including Artificial Neural Network (ANN), Non-Linear Regression (NLR) and Gaussian Mixture (GM) for undertaking different tasks. The results underlined that the system generates relatively fast solutions with accuracy. Additionally, ML algorithms can assist generative design processes.
keywords	Machine-learning; performance simulation; data-driven design; early-design phase
series	eCAADe
email
last changed	2022/06/07 07:57

_id	ecaade2024_409
id	ecaade2024_409
authors	Zarzycki, Andrzej
year	2024
title	BIM-Driven Curriculum for Integrated Design Studios: Maintaining data interoperability and design flexibility
source	Kontovourkis, O, Phocas, MC and Wurzer, G (eds.), Data-Driven Intelligence - Proceedings of the 42nd Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2024), Nicosia, 11-13 September 2024, Volume 2, pp. 27–36
doi	https://doi.org/10.52842/conf.ecaade.2024.2.027
summary	This paper presents a curricular model for an integrated design studio focused on BIM-driven processes, satisfying the NAAB 2020's student performance criteria SC.5 and SC6. These criteria emphasize quantifiable, evidence-based design thinking by requiring the provision of "measurable environmental impacts" and "measurable outcomes of building performance." The studio, serving as a capstone project, integrates accessible design, user and regulatory requirements into building assemblies, structural and environmental systems, and life safety, underscoring the importance of measurable building performance outcomes. The adoption of computational design tools, particularly Building Information Modeling (BIM), facilitates engagement in environmental and user-focused simulations and ensures data interoperability throughout the design and post-occupancy phases. Utilizing a comprehensive set of tools, including life-cycle assessment (LCA) and energy modeling, the curriculum advances beyond simple simulations to support decision-making and multi-objective optimizations. This approach enables a new form of design thinking that incorporates a broader set of variables and considerations, encouraging students to meet various environmental impact and performance benchmarks, including LEED v.5 Certification points and Architecture 2030 energy standards. The integration of scenario simulation tools empowers students to autonomously advance their projects within a framework of constraints, marking a pedagogical shift towards faculty acting as learning facilitators and promoting student autonomy in design evaluation.
keywords	building information modeling, BIM, building performance simulations, design education
series	eCAADe
email
last changed	2024/11/17 22:05

_id	acadia20_238
id	acadia20_238
authors	Zhang, Hang
year	2020
title	Text-to-Form
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. 238-247.
doi	https://doi.org/10.52842/conf.acadia.2020.1.238
summary	Traditionally, architects express their thoughts on the design of 3D architectural forms via perspective renderings and standardized 2D drawings. However, as architectural design is always multidimensional and intricate, it is difficult to make others understand the design intention, concrete form, and even spatial layout through simple language descriptions. Benefiting from the fast development of machine learning, especially natural language processing and convolutional neural networks, this paper proposes a Linguistics-based Architectural Form Generative Model (LAFGM) that could be trained to make 3D architectural form predictions based simply on language input. Several related works exist that focus on learning text-to-image generation, while others have taken a further step by generating simple shapes from the descriptions. However, the text parsing and output of these works still remain either at the 2D stage or confined to a single geometry. On the basis of these works, this paper used both Stanford Scene Graph Parser (Sebastian et al. 2015) and graph convolutional networks (Kipf and Welling 2016) to compile the analytic semantic structure for the input texts, then generated the 3D architectural form expressed by the language descriptions, which is also aided by several optimization algorithms. To a certain extent, the training results approached the 3D form intended in the textual description, not only indicating the tremendous potential of LAFGM from linguistic input to 3D architectural form, but also innovating design expression and communication regarding 3D spatial information.
series	ACADIA
type	paper
email
last changed	2023/10/22 12:06

_id	cdrf2019_134
id	cdrf2019_134
authors	Zhen Han, Wei Yan, and Gang Liu
year	2020
title	A Performance-Based Urban Block Generative Design Using Deep Reinforcement Learning and Computer Vision
source	Proceedings of the 2020 DigitalFUTURES The 2nd International Conference on Computational Design and Robotic Fabrication (CDRF 2020)
doi	https://doi.org/https://doi.org/10.1007/978-981-33-4400-6_13
summary	In recent years, generative design methods are widely used to guide urban or architectural design. Some performance-based generative design methods also combine simulation and optimization algorithms to obtain optimal solutions. In this paper, a performance-based automatic generative design method was proposed to incorporate deep reinforcement learning (DRL) and computer vision for urban planning through a case study to generate an urban block based on its direct sunlight hours, solar heat gains as well as the aesthetics of the layout. The method was tested on the redesign of an old industrial district located in Shenyang, Liaoning Province, China. A DRL agent - deep deterministic policy gradient (DDPG) agent - was trained to guide the generation of the schemes. The agent arranges one building in the site at one time in a training episode according to the observation. Rhino/Grasshopper and a computer vision algorithm, Hough Transform, were used to evaluate the performance and aesthetics, respectively. After about 150 h of training, the proposed method generated 2179 satisfactory design solutions. Episode 1936 which had the highest reward has been chosen as the final solution after manual adjustment. The test results have proven that the method is a potentially effective way for assisting urban design.
series	cdrf
email
last changed	2022/09/29 07:51

For more results click below: