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 624

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

_id	ecaadesigradi2019_514
id	ecaadesigradi2019_514
authors	de Miguel, Jaime, Villafa?e, Maria Eugenia, Piškorec, Luka and Sancho-Caparrini, Fernando
year	2019
title	Deep Form Finding - Using Variational Autoencoders for deep form finding of structural typologies
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 71-80
doi	https://doi.org/10.52842/conf.ecaade.2019.1.071
summary	In this paper, we are aiming to present a methodology for generation, manipulation and form finding of structural typologies using variational autoencoders, a machine learning model based on neural networks. We are giving a detailed description of the neural network architecture used as well as the data representation based on the concept of a 3D-canvas with voxelized wireframes. In this 3D-canvas, the input geometry of the building typologies is represented through their connectivity map and subsequently augmented to increase the size of the training set. Our variational autoencoder model then learns a continuous latent distribution of the input data from which we can sample to generate new geometry instances, essentially hybrids of the initial input geometries. Finally, we present the results of these computational experiments and lay out the conclusions as well as outlook for future research in this field.
keywords	artificial intelligence; deep neural networks; variational autoencoders; generative design; form finding; structural design
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:55

_id	acadia19_412
id	acadia19_412
authors	Del Campo, Matias; Manninger, Sandra; Carlson, Alexandra
year	2019
title	Imaginary Plans
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. 412-418
doi	https://doi.org/10.52842/conf.acadia.2019.412
summary	Artificial Neural Networks (NN) have become ubiquitous across disciplines due to their high performance in modeling the real world to execute complex tasks in the wild. This paper presents a computational design approach that uses the internal representations of deep vision neural networks to generate and transfer stylistic form edits to both 2D floor plans and building sections. The main aim of this paper is to demonstrate and interrogate a design technique based on deep learning. The discussion includes aspects of machine learning, 2D to 2D style transfers, and generative adversarial processes. The paper examines the meaning of agency in a world where decision making processes are defined by human/machine collaborations (Figure 1), and their relationship to aspects of a Posthuman design ecology. Taking cues from the language used by experts in AI, such as Hallucinations, Dreaming, Style Transfer, and Vision, the paper strives to clarify the position and role of Artificial Intelligence in the discipline of Architecture.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:55

_id	ecaadesigradi2019_135
id	ecaadesigradi2019_135
authors	Newton, David
year	2019
title	Deep Generative Learning for the Generation and Analysis of Architectural Plans with Small Datasets
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 21-28
doi	https://doi.org/10.52842/conf.ecaade.2019.2.021
summary	The field of generative architectural design has explored a wide range of approaches in the automation of design production, but these approaches have demonstrated limited artificial intelligence. Generative Adversarial Networks (GANs) are a leading deep generative model that use deep neural networks (DNNs) to learn from a set of training examples in order to create new design instances with a degree of flexibility and fidelity that outperform competing generative approaches. Their application to generative tasks in architecture, however, has been limited. This research contributes new knowledge on the use of GANs for architectural plan generation and analysis in relation to the work of specific architects. Specifically, GANs are trained to synthesize architectural plans from the work of the architect Le Corbusier and are used to provide analytic insight. Experiments demonstrate the efficacy of different augmentation techniques that architects can use when working with small datasets.
keywords	generative design; deep learning; artificial intelligence; generative adversarial networks
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_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
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.
doi	https://doi.org/10.52842/conf.acadia.2020.1.382
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	ecaade2021_203
id	ecaade2021_203
authors	Arora, Hardik, Bielski, Jessica, Eisenstadt, Viktor, Langenhan, Christoph, Ziegler, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas
year	2021
title	Consistency Checker - An automatic constraint-based evaluator for housing spatial configurations
source	Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 2, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 351-358
doi	https://doi.org/10.52842/conf.ecaade.2021.2.351
summary	The gradual rise of artificial intelligence (AI) and its increasing visibility among many research disciplines affected Computer-Aided Architectural Design (CAAD). Architectural deep learning (DL) approaches are being developed and published on a regular basis, such as retrieval (Sharma et al. 2017) or design style manipulation (Newton 2019; Silvestre et al. 2016). However, there seems to be no method to evaluate highly constrained spatial configurations for specific architectural domains (such as housing or office buildings) based on basic architectural principles and everyday practices. This paper introduces an automatic constraint-based consistency checker to evaluate the coherency of semantic spatial configurations of housing construction using a small set of design principles to evaluate our DL approaches. The consistency checker informs about the overall performance of a spatial configuration followed by whether it is open/closed and the constraints it didn't satisfy. This paper deals with the relation of spaces processed as mathematically formalized graphs contrary to existing model checking software like Solibri.
keywords	model checking, building information modeling, deep learning, data quality
series	eCAADe
email
last changed	2022/06/07 07:54

_id	ecaadesigradi2019_034
id	ecaadesigradi2019_034
authors	Chen, Dechen, Luo, Dan, Xu, Weiguo, Luo, Chen, Shen, Liren, Yan, Xia and Wang, Tianjun
year	2019
title	Re-perceive 3D printing with Artificial Intelligence
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 443-450
doi	https://doi.org/10.52842/conf.ecaade.2019.1.443
summary	How can machine learning be combined with intelligent construction, material testing and other related topics to develop a new method of fabrication? This paper presents a set of experiments on the dynamic control of the heat deflection of thermoplastics in searching for a new 3D printing method with the dynamic behaviour of PLA and with a comprehensive workflow utilizing mechanic automation, computer vision, and artificial intelligence. Additionally, this paper will discuss in-depth the performance of different types of neural networks used in the research and conclude with solid data on the potential connection between the structure of neural networks and the dynamic, complex material performance we are attempting to capture.
keywords	3D printing; AI; automation; material; fabrication
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:55

_id	caadria2019_553
id	caadria2019_553
authors	del Campo, Matias, Manninger, Sandra, Sanche, Marianne and Wang, Leetee
year	2019
title	The Church of AI - An examination of architecture in a posthuman design ecology
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 767-772
doi	https://doi.org/10.52842/conf.caadria.2019.2.767
summary	The Project, the Church of AI, taps into the opportunities of Artificial Intelligence as a device for Architecture Design in a twofold way: On the one side by employing a design technique that is based on the ability of Artificial Intelligence to generate form autonomously of human interaction, and on the other hand by speculating about the nature of devotion, the sublime and awe in a posthuman society.
keywords	Artificial Intelligence; Posthuman; Postdigital; Machine Learning; DeepDream
series	CAADRIA
email
last changed	2022/06/07 07:55

_id	ecaadesigradi2019_671
id	ecaadesigradi2019_671
authors	Jabi, Wassim, Chatzivasileiadi, Aikaterini, Wardhana, Nicholas Mario, Lannon, Simon and Aish, Robert
year	2019
title	The synergy of non-manifold topology and reinforcement learning for fire egress
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 85-94
doi	https://doi.org/10.52842/conf.ecaade.2019.2.085
summary	This paper illustrates the synergy of non-manifold topology (NMT) and a branch of artificial intelligence and machine learning (ML) called reinforcement learning (RL) in the context of evaluating fire egress in the early design stages. One of the important tasks in building design is to provide a reliable system for the evacuation of the users in emergency situations. Therefore, one of the motivations of this research is to provide a framework for architects and engineers to better design buildings at the conceptual design stage, regarding the necessary provisions in emergency situations. This paper presents two experiments using different state models within a simplified game-like environment for fire egress with each experiment investigating using one vs. three fire exits. The experiments provide a proof-of-concept of the effectiveness of integrating RL, graphs, and non-manifold topology within a visual data flow programming environment. The results indicate that artificial intelligence, machine learning, and RL show promise in simulating dynamic situations as in fire evacuations without the need for advanced and time-consuming simulations.
keywords	Non-manifold topology; Topologic; Reinforcement Learning; Fire egress
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:52

_id	cf2019_022
id	cf2019_022
authors	Koh, Immanuel and Jeffrey Huang
year	2019
title	Citizen Visual Search Engine:Detection and Curation of Urban Objects
source	Ji-Hyun Lee (Eds.) "Hello, Culture!" [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 170
summary	Increasingly, the ubiquity of satellite imagery has made the data analysis and machine learning of large geographical datasets one of the building blocks of visuospatial intelligence. It is the key to discover current (and predict future) cultural, social, financial and political realities. How can we, as designers and researchers, empower citizens to understand and participate in the design of our cities amid this technological shift? As an initial step towards this broader ambition, a series of creative web applications, in the form of visual search engines, has been developed and implemented to data mine large datasets. Using open sourced deep learning and computer vision libraries, these applications facilitate the searching, detecting and curating of urban objects. In turn, the paper proposes and formulates a framework to design truly citizen-centric creative visual search engines -- a contribution to citizen science and citizen journalism in spatial terms.
keywords	Deep Learning, Computer Vision, Satellite Imagery, Citizen Science, Artificial Intelligence
series	CAAD Futures
email
last changed	2019/07/29 14:08

_id	caadria2019_462
id	caadria2019_462
authors	Koh, Immanuel, Amorim, Pedro and Huang, Jeffrey
year	2019
title	Machinic Design Inference: from PokÃ©mon to Architecture - A Probabilistic Machine Learning Model for Generative Design using Game Levels Abstractions
source	M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 2, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 421-430
doi	https://doi.org/10.52842/conf.caadria.2019.2.421
summary	In this paper, we use a probabilistic machine learning model, trained with a corpus of existing game levels tile-maps, to study the potential of an inference design system for architectural design. Our system is able to extract implicit spatial patterns and generate new spatial configurations with similar semantics of perception and navigation.
keywords	Machine Learning; Artificial Intelligence; Generative Design
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	acadia19_404
id	acadia19_404
authors	Liu, Henan; Liao, Longtai; Srivastava, Akshay
year	2019
title	AN ANONYMOUS COMPOSITION
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. 404-411
doi	https://doi.org/10.52842/conf.acadia.2019.404
summary	Within the context of continuous technology transformations, the way scientists and designers process data is changing dramatically from simplification and explicit defined rules to searching and retrieving. Ideally, such a trending method can eliminate issues including deviation and ambiguity with the help of hypothetically unlimited computational power. To process data in this manner, artificial intelligence is necessary and needs to be integrated into the design process. An experiment of a design process that consists of a generative model, a data library, and a machine learning system (GAN) is introduced to demonstrate its effectiveness. The methodology is further evaluated by comparing its output with its input targets, which proves the possibility of employing machine learning systems to aggressively process data and automate the design process. Further improvement of such methodology, including judging criteria and possible applications, and the sensibility of the machine is also discussed at the end.
keywords	Machine Learning, Automation, Variables, Data Processing, Sensibility, Generative Design
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:59

_id	sigradi2023_416
id	sigradi2023_416
authors	Machado Fagundes, Cristian Vinicius, Miotto Bruscato, Léia, Paiva Ponzio, Angelica and Chornobai, Sara Regiane
year	2023
title	Parametric environment for internalization and classification of models generated by the Shap-E tool
source	García Amen, F, Goni Fitipaldo, A L and Armagno Gentile, Á (eds.), Accelerated Landscapes - Proceedings of the XXVII International Conference of the Ibero-American Society of Digital Graphics (SIGraDi 2023), Punta del Este, Maldonado, Uruguay, 29 November - 1 December 2023, pp. 1689–1698
summary	Computing has been increasingly employed in design environments, primarily to perform calculations and logical decisions faster than humans could, enabling tasks that would be impossible or too time-consuming to execute manually. Various studies highlight the use of digital tools and technologies in diverse methods, such as parametric modeling and evolutionary algorithms, for exploring and optimizing alternatives in architecture, design, and engineering (Martino, 2015; Fagundes, 2019). Currently, there is a growing emergence of intelligent models that increasingly integrate computers into the design process. Demonstrating great potential for initial ideation, artificial intelligence (AI) models like Shap-E (Nichol et al., 2023) by OpenAI stand out. Although this model falls short of state-of-the-art sample quality, it is among the most efficient orders of magnitude for generating three-dimensional models through AI interfaces, offering practical balance for certain use cases. Thus, aiming to explore this gap, the presented study proposes an innovative design agency framework by employing Shap-E connected with parametric modeling in the design process. The generation tool has shown promising results; through generations of synthetic views conditioned by text captions, its final output is a mesh. However, due to the lack of topological information in models generated by Shap-E, we propose to fill this gap by transferring data to a parametric three-dimensional surface modeling environment. Consequently, this interaction's use aims to enable the transformation of the mesh into quantifiable surfaces, subject to collection and optimization of dimensional data of objects. Moreover, this work seeks to enable the creation of artificial databases through formal categorization of parameterized outputs using the K-means algorithm. For this purpose, the study methodologically orients itself in a four-step exploratory experimental process: (1) creation of models generated by Shap-E in a pressing manner; (2) use of parametric modeling to internalize models into the Grasshopper environment; (3) generation of optimized alternatives using the evolutionary algorithm (Biomorpher); (4) and classification of models using the K-means algorithm. Thus, the presented study proposes, through an environment of internalization and classification of models generated by the Shap-E tool, to contribute to the construction of a new design agency methodology in the decision-making process of design. So far, this research has resulted in the generation and classification of a diverse set of three-dimensional shapes. These shapes are grouped for potential applications in machine learning, in addition to providing insights for the refinement and detailed exploration of forms.
keywords	Shap-E, Parametric Design, Evolutionary Algorithm, Synthetic Database, Artificial Intelligence
series	SIGraDi
email
last changed	2024/03/08 14:09

_id	caadria2021_053
id	caadria2021_053
authors	Rhee, Jinmo and Veloso, Pedro
year	2021
title	Generative Design of Urban Fabrics Using Deep Learning
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 1, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 31-40
doi	https://doi.org/10.52842/conf.caadria.2021.1.031
summary	This paper describes the Urban Structure Synthesizer (USS), a research prototype based on deep learning that generates diagrams of morphologically consistent urban fabrics from context-rich urban datasets. This work is part of a larger research on computational analysis of the relationship between urban context and morphology. USS relies on a data collection method that extracts GIS data and converts it to diagrams with context information (Rhee et al., 2019). The resulting dataset with context-rich diagrams is used to train a Wasserstein GAN (WGAN) model, which learns how to synthesize novel urban fabric diagrams with the morphological and contextual qualities present in the dataset. The model is also trained with a random vector in the input, which is later used to enable parametric control and variation for the urban fabric diagram. Finally, the resulting diagrams are translated to 3D geometric entities using computer vision techniques and geometric modeling. The diagrams generated by USS suggest that a learning-based method can be an alternative to methods that rely on experts to build rule sets or parametric models to grasp the morphological qualities of the urban fabric.
keywords	Deep Learning; Urban Fabric; Generative Design; Artificial Intelligence; Urban Morphology
series	CAADRIA
email
last changed	2022/06/07 07:56

_id	ecaadesigradi2019_280
id	ecaadesigradi2019_280
authors	Rossi, Gabriella and Nicholas, Paul
year	2019
title	Haptic Learning - Towards Neural-Network-based adaptive Cobot Path-Planning for unstructured spaces
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 2, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 201-210
doi	https://doi.org/10.52842/conf.ecaade.2019.2.201
summary	Collaborative Robots, or Cobots, bring new possibilities for human-machine interaction within the fabrication process, allowing each actor to contribute with their specific capabilities. However creative interaction brings unexpected changes, obstacles, complexities and non-linearities which are encountered in real time and cannot be predicted in advance. This paper presents an experimental methodology for robotic path planning using Machine Learning. The focus of this methodology is obstacle avoidance. A neural network is deployed, providing a relationship between the robot's pose and its surroundings, thus allowing for motion planning and obstacle avoidance, directly integrated within the design environment. The method is demonstrated through a series of case-studies. The method combines haptic teaching with machine learning to create a task specific dataset, giving the robot the ability to adapt to obstacles without being explicitly programmed at every instruction. This opens the door to shifting to robotic applications for construction in unstructured environments, where adapting to the singularities of the workspace, its occupants and activities presents an important computational hurdle today.
keywords	Architectural Robotics; Neural Networks; Path Planning; Digital Fabrication; Artificial Intelligence; Data
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:56

_id	ecaadesigradi2019_308
id	ecaadesigradi2019_308
authors	Yetkin, Ozan and Gönenç Sorguç, Arzu
year	2019
title	Design Space Exploration of Initial Structural Design Alternatives via Artificial Neural Networks
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 55-60
doi	https://doi.org/10.52842/conf.ecaade.2019.1.055
summary	Increasing implementation of digital tools within a design process generates exponentially growing data in each phase, and inevitably, decision making within a design space with increasing complexity will be a great challenge for the designers in the future. Hence, this research aimed to seek potentials of captured data within a design space and solution space of a truss design problem for proposing an initial novel approach to augment capabilities of digital tools by artificial intelligence where designers are allowed to make a wise guess within the initial design space via performance feedbacks from the objective space. Initial structural design and modelling phase of a truss section was selected as a material of this study since decisions within this stage affect the whole process and performance of the end product. As a method, a generic framework was proposed that can help designers to understand the trade-offs between initial structural design alternatives to make informed decisions and optimizations during the initial stage. Finally, the proposed framework was presented in a case study, and future potentials of the research were discussed.
keywords	design space; objective space; structural design; artificial intelligence; machine learning; optimization
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:57

_id	acadia19_380
id	acadia19_380
authors	Özel, Güvenç; Ennemoser, Benjamin
year	2019
title	Interdisciplinary AI
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. 380- 391
doi	https://doi.org/10.52842/conf.acadia.2019.380
summary	Architecture does not exist in a vacuum. Its cultural, conceptual, and aesthetic agendas are constantly influenced by other visual and artistic disciplines ranging from film, photography, painting and sculpture to fashion, graphic and industrial design. The formal qualities of the cultural zeitgeist are perpetually influencing contemporary architectural aesthetics. In this paper, we aim to introduce a radical yet methodical approach toward regulating the relationship between human agency and computational form-making by using Machine Learning (ML) as a conceptual design tool for interdisciplinary collaboration and engagement. Through the use of a highly calibrated and customized ML systems that can classify and iterate stylistic approaches that exist outside the disciplinary boundaries of architecture, the technique allows for machine intelligence to design, coordinate, randomize, and iterate external formal and aesthetic qualities as they relate to pattern, color, proportion, hierarchy, and formal language. The human engagement in this design process is limited to the initial curation of input data in the form of image repositories of non-architectural disciplines that the Machine Learning system can extrapolate from, and consequently in regulating and choosing from the iterations of images the Artificial Neural Networks are capable of producing. In this process the architect becomes a curator that samples and streamlines external cultural influences while regulating their significance and weight in the final design. By questioning the notion of human agency in the design process and providing creative license to Artificial Intelligence in the conceptual design phase, we aim to develop a novel approach toward human-machine collaboration that rejects traditional notions of disciplinary autonomy and streamlines the influence of external aesthetic disciplines on contemporary architectural production.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:57

_id	acadia19_16
id	acadia19_16
authors	Hosmer, Tyson; Tigas, Panagiotis
year	2019
title	Deep Reinforcement Learning for Autonomous Robotic Tensegrity (ART)
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. 16-29
doi	https://doi.org/10.52842/conf.acadia.2019.016
summary	The research presented in this paper is part of a larger body of emerging research into embedding autonomy in the built environment. We develop a framework for designing and implementing effective autonomous architecture defined by three key properties: situated and embodied agency, facilitated variation, and intelligence.We present a novel application of Deep Reinforcement Learning to learn adaptable behaviours related to autonomous mobility, self-structuring, self-balancing, and spatial reconfiguration. Architectural robotic prototypes are physically developed with principles of embodied agency and facilitated variation. Physical properties and degrees of freedom are applied as constraints in a simulated physics-based environment where our simulation models are trained to achieve multiple objectives in changing environments. This holistic and generalizable approach to aligning deep reinforcement learning with physically reconfigurable robotic assembly systems takes into account both computational design and physical fabrication. Autonomous Robotic Tensegrity (ART) is presented as an extended case study project for developing our methodology. Our computational design system is developed in Unity3D with simulated multi-physics and deep reinforcement learning using Unity’s ML-agents framework. Topological rules of tensegrity are applied to develop assemblies with actuated tensile members. Single units and assemblies are trained for a series of policies using reinforcement learning in single-agent and multi-agent setups. Physical robotic prototypes are built and actuated to test simulated results.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:50

_id	acadia19_298
id	acadia19_298
authors	Leach, Neil
year	2019
title	Do Robots Dream of Digital Sleep?
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. 298-309
doi	https://doi.org/10.52842/conf.acadia.2019.298
summary	AI is playing an increasingly important role in everyday life. But can AI actually design? This paper takes its point of departure from Philip K Dick’s novel, Do Androids Dream of Electric Sheep? and refers to Google’s DeepDream software, and other AI techniques such as GANs, Progressive GANs, CANs and StyleGAN, that can generate increasingly convincing images, a process often described as ‘dreaming’. It notes that although generative AI does not possess consciousness, and therefore cannot literally dream, it can still be a powerful design tool that becomes a prosthetic extension to the human imagination. Although the use of GANs and other deep learning AI tools is still in its infancy, we are at the dawn of an exciting – but also potentially terrifying – new era for architectural design. Most importantly, the paper concludes, the development of AI is also helping us to understand human intelligence and 'creativity'.
series	ACADIA
type	normal paper
email
last changed	2022/06/07 07:52

_id	ecaadesigradi2019_602
id	ecaadesigradi2019_602
authors	Toulkeridou, Varvara
year	2019
title	Steps towards AI augmented parametric modeling systems for supporting design exploration
source	Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 81-90
doi	https://doi.org/10.52842/conf.ecaade.2019.1.081
summary	Dataflow parametric modeling environments have become popular as exploratory tools due to them allowing the variational exploration of a design by controlling the parameters of its parametric model schema. However, the nature of these systems requires designers to prematurely commit to a structure and hierarchy of geometric relationships, which makes them inflexible when it comes to design exploration that requires topological changes to the parametric modeling graph. This paper is a first step towards augmenting parametric modeling systems via the use of machine learning for assisting the user towards topological exploration. In particular, this paper describes an approach where Long Short-Term Memory recurrent neural networks, trained on a data set of parametric modeling graphs, are used as generative systems for suggesting alternative dataflow graph paths to the parametric model under development.
keywords	design exploration; visual programming; machine learning
series	eCAADeSIGraDi
email
last changed	2022/06/07 07:58

_id	artificial_intellicence2019_15
id	artificial_intellicence2019_15
authors	Antoine Picon
year	2020
title	What About Humans? Artificial Intelligence in Architecture
source	Architectural Intelligence Selected Papers from the 1st International Conference on Computational Design and Robotic Fabrication (CDRF 2019)
doi	https://doi.org/https://doi.org/10.1007/978-981-15-6568-7_2
summary	Artificial intelligence is about to reshape the architectural discipline. After discussing the relations between artificial intelligence and the broader question of automation in architecture, this article focuses on the future of the interaction between humans and intelligent machines. The way machines will understand architecture may be very different from the reading of humans. Since the Renaissance, the architectural discipline has defined itself as a conversation between different stakeholders, the designer, but also the clients and the artisans in charge of the realization of projects. How can this conversation be adapted to the rise of intelligent machines? Such a question is not only a matter of design effectiveness. It is inseparable from expressive and artistic issues. Just like the fascination of modernist architecture for industrialization was intimately linked to the quest for a new poetics of the discipline, our contemporary interest for artificial intelligence has to do with questions regarding the creative core of the architectural discipline.
series	Architectural Intelligence
email
last changed	2022/09/29 07:28

For more results click below: