“…Graph editors are a common interface paradigm within the DCC landscape, 2 , 3 so it is somewhat interesting that the work by Nauata et al (2020) presented one of only two graph editor interfaces in the reviewed literature. The work describes a framework for a node-graph–based floor plan generation tool.…”
Section: Discussionmentioning
confidence: 99%
“… Left: The interface for the HouseGAN system ( Nauata et al, 2020 ). The user describes a node-graph, with nodes representing rooms and edges the connections between them.…”
The future of work and workplace is very much in flux. A vast amount has been written about artificial intelligence (AI) and its impact on work, with much of it focused on automation and its impact in terms of potential job losses. This review will address one area where AI is being added to creative and design practitioners’ toolbox to enhance their creativity, productivity, and design horizons. A designer’s primary purpose is to create, or generate, the most optimal artifact or prototype, given a set of constraints. We have seen AI encroaching into this space with the advent of generative networks and generative adversarial networks (GANs) in particular. This area has become one of the most active research fields in machine learning over the past number of years, and a number of these techniques, particularly those around plausible image generation, have garnered considerable media attention. We will look beyond automatic techniques and solutions and see how GANs are being incorporated into user pipelines for design practitioners. A systematic review of publications indexed on ScienceDirect, SpringerLink, Web of Science, Scopus, IEEExplore, and ACM DigitalLibrary was conducted from 2015 to 2020. Results are reported according to PRISMA statement. From 317 search results, 34 studies (including two snowball sampled) are reviewed, highlighting key trends in this area. The studies’ limitations are presented, particularly a lack of user studies and the prevalence of toy-examples or implementations that are unlikely to scale. Areas for future study are also identified.
“…Graph editors are a common interface paradigm within the DCC landscape, 2 , 3 so it is somewhat interesting that the work by Nauata et al (2020) presented one of only two graph editor interfaces in the reviewed literature. The work describes a framework for a node-graph–based floor plan generation tool.…”
Section: Discussionmentioning
confidence: 99%
“… Left: The interface for the HouseGAN system ( Nauata et al, 2020 ). The user describes a node-graph, with nodes representing rooms and edges the connections between them.…”
The future of work and workplace is very much in flux. A vast amount has been written about artificial intelligence (AI) and its impact on work, with much of it focused on automation and its impact in terms of potential job losses. This review will address one area where AI is being added to creative and design practitioners’ toolbox to enhance their creativity, productivity, and design horizons. A designer’s primary purpose is to create, or generate, the most optimal artifact or prototype, given a set of constraints. We have seen AI encroaching into this space with the advent of generative networks and generative adversarial networks (GANs) in particular. This area has become one of the most active research fields in machine learning over the past number of years, and a number of these techniques, particularly those around plausible image generation, have garnered considerable media attention. We will look beyond automatic techniques and solutions and see how GANs are being incorporated into user pipelines for design practitioners. A systematic review of publications indexed on ScienceDirect, SpringerLink, Web of Science, Scopus, IEEExplore, and ACM DigitalLibrary was conducted from 2015 to 2020. Results are reported according to PRISMA statement. From 317 search results, 34 studies (including two snowball sampled) are reviewed, highlighting key trends in this area. The studies’ limitations are presented, particularly a lack of user studies and the prevalence of toy-examples or implementations that are unlikely to scale. Areas for future study are also identified.
“…An increasing number of designers and computer scientists are working together to develop new ways of creating automated methods to generate spatial solutions (among others, Eisenstadt et al, 2019;Goodman, 2019;Kalervo, 2019;Liu, 2017;Nauata, 2020;Phelan et al, 2017;Sandelin, 2019;Zeng et al, 2019).…”
Section: Self-organizing Floor Plan At Workmentioning
This article introduces and comments on some of the techniques currently used by designers to generate automatic building floor plans and spatial configurations in general, with emphasis on machine learning and neural networks models. This is a relatively new tendency in computational design that reflects a growing interest in advanced generative and optimization models by architects and building engineers.The first part of this work contextualizes self-organizing floor plans in architecture and computational design, highlighting their importance and potential for designers as well as software developers. The central part discusses some of the most common techniques with concrete examples, including Neuro Evolution of Augmenting Topologies (NEAT) and Generative Adversarial Networks (GAN). The final section of the article provides some general comments considering pitfalls and possible future developments, as well as speculating on the future of this trend.
“…There are three main approaches related to floorplan design via graph-based modeling, including graph transformations (Wang, Yang and Zhang, 2018), evolutionary approach (Wong and Chan, 2009;Strug, Grabska and Ślusarczyk, 2014), and deep learning approach (Nauata et al, 2020). The graph transformation approach is built upon input graphs representing the original floorplans, and then graph manipulations, such as node/edge addition and subtraction, are performed to produce the floorplan variations (Wang, Yang and Zhang, 2018).…”
Section: Graph Modeling In Construction Projectsmentioning
confidence: 99%
“…The graph transformation approach is built upon input graphs representing the original floorplans, and then graph manipulations, such as node/edge addition and subtraction, are performed to produce the floorplan variations (Wang, Yang and Zhang, 2018). The evolutionary approach introduces graph-based evolutionary operators, namely cross-over and mutation, in the floorplan generation process (Wong and Chan, 2009;Strug, Grabska and Ślusarczyk, 2014) The deep learning approach is achieved via a Generative Adversarial Networks (GAN), which takes a large dataset of pixel-based floorplans as inputs and generate novel ones by performing a generator and a discriminator on their graph representations (Nauata et al, 2020). Having graph-represented design solutions of floorplans, Strug and Ślusarczyk detected the frequent patterns via graph mining technique (Strug and Ślusarczyk, 2009).…”
Section: Graph Modeling In Construction Projectsmentioning
The use of prefabricated modules can benefit the construction industry with the economy of scales and production efficiency. However, the existing approach to develop module libraries is project-based, lacking the potential to reuse and manage in future projects. By taking the repeatability and manufacturability into account, this paper proposes a graph-based framework to identify possible modules automatically from multiple projects by frequent pattern mining. The results show that the repeated patterns share a degree of standardization and can be considered as module candidates. Finally, the framework is implemented as add-ons in the BIM environment to support module lifecycle management.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.