Self-Organizing Floor Plans

eCAADe proceedings

radziszewski}@pg.edu.pl Tools and methods used by architects always had an impact on the way building were designed. With the change in design methods and new approaches towards creation process, they became more than ever before crucial elements of the creation process. The automation of architects work has started with computational functions that were introduced to traditional computer-aided design tools. Nowadays architects tend to use specified tools that suit their specific needs. In some cases, they use artificial intelligence. Despite many similarities, they have different advantages and disadvantages. Therefore the change in the design process is more visible and unseen before solution are brought in the discipline. The article presents methods of applying the selected artificial intelligence algorithms: swarm intelligence, neural networks and evolutionary algorithms in the architectural practice by authors. Additionally research shows the methods of analogue data input and output approaches, based on vision and robotics, which in future combined with intelligence based algorithms, might simplify architects everyday practice. Presented techniques allow new spatial solutions to emerge with relatively simple intelligent based algorithms, from which many could be only accomplished with dedicated software. Popularization of the following methods among architects, will result in more intuitive, general use design tools.

Blucher Design Proceedings, 2019

We present an approach for computer-aided generation of different variations of floor plans during the early phases of conceptual design in architecture. The early design phases are mostly characterized by the processes of inspiration gaining and search for contextual help in order to improve the building design at hand. The generation method described in this work uses the novel as well as established artificial intelligence methods, namely, generative adversarial nets and case-based reasoning, for creation of possible evolutions of the current design based on the most similar previous designs. The main goal of this approach is to provide the designer with information on how the current floor plan can evolve over time in order to influence the direction of the design process. The work described in this paper is part of the methodology FLEA (Find, Learn, Explain, Adapt) whose task is to provide a holistic structure for support of the early conceptual phases in architecture. The approach is implemented as the adaptation component of the framework MetisCBR that is based on FLEA.

Proceedings of the 2017 Symposium on Simulation for Architecture and Urban Design (SimAUD 2017), 2017

This paper describes a flexible workflow for generative design applied to architectural space planning. We describe this workflow through an application for the design of a new office space. First, we describe a computational design model that can create a variety of office layouts including locating all necessary programs and people using a small set of input parameters. We then describe six unique objectives that evaluate each layout based on architectural performance as well as worker-specific preferences. Finally, we show the use of a multi-objective genetic algorithm (MOGA) to search through the high-dimensional space of all possible designs, and describe several visualization tools that can help a designer to navigate through this design space and choose good designs. We conclude by discussing the future of such computational workflows in design and architecture. Our hope is that they go beyond basic automation to create an expanded role for the human designer and a more dynamic and collaborative interaction between computer design software and human designers in the future.

This survey methodically analyzes deep learning techniques used in generating floorplan layouts, summarizes current methodologies that shift from image-based to graph-based and multimodal-based methods, and discusses their advantages and drawbacks. The review includes primary datasets with floorplan layout generation tasks and addresses the issues related to geographic diversity, typological variations, and format consistency. Floorplan generation should be approached as an information transmission problem that allows the integration of graphbased methods with other techniques instead of viewing it solely as image generation. Critical opportunities include region-specific dataset development, external contextual factor integration, and enhanced long-range dependency management. The research presented outlines potential future research paths that aim to develop more practical and robust solutions for architectural design.

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Figure 1. The paper makes a breakthrough in the task of automated house layout generation. The right shows the mix of a ground-truth design made by an architect and our generated samples, based on the input bubble-diagram. Can you tell which one is the ground-truth? See the end of the caption for the answer. The paper proposes a novel generative adversarial layout refinement network, whose generator is trained to repeatedly apply and refine the design towards perfection. (The second sample from the right is the ground-truth.

This study aims to produce Andrea Palladio's architectural plan schemes autonomously with generative adversarial networks(GAN), and to evaluate the plan drawing productions of GAN as a generative plan layout tool. GAN is a class of deep neural nets which is a generative model. In deep learning models, repetitive processes can be automated. Architectural drawing is a repetitive process in the act of architecture and plan drawing process can be made automated. For the automation of plan production system we used deep convolutional generative adversarial network (DCGAN) which is a subset of GAN models. And we evaluated the outputs of the DCGAN Palladian Plan scheme productions. Results show that not geometric similarities (shapes), but probabilistic models are at the centre of the generative system of GAN. For this reason, it should be kept in mind that while GAN algorithms are used as a generative system, they will produce statistically close visual models rather than geometrically close models. Nonetheless, GAN can generate both statistically and geometrically close models to the dataset. In first section we introduced a brief description about the place of the drawing in architecture field and future foresight of architecture drawings. In the second section, we gave detailed information about the literature on autonomous plan drawing systems. In the following sections, we explained the methodology of this study and the process of creating the plan drawing dataset, the algorithm training procedure, at the end we evaluated the generated plan schemes with rapid scene categorization and Frechet inception score.

International Congress on Human-Computer Interaction, Optimization and Robotic Applications”, 2023

We live in the age of Artificial Intelligence (AI) which permeates all aspects of our lives, from spam filtering to image classification on social media. While it is already wellestablished in industries ranging from heavy manufacturing to the IT field, its impact on the design professions remains relatively unexplored. This essay explores the use of neural networks in architecture, which is arguably the first genuinely 21st-century design technique and discusses experiments with Generative Adversarial Networks (GANs) to generate unexplored futuristic possible noble forms in architecture. In this way this paper also raises the question if machine can generate noble forms through its creative data optimization process. In this process one of the most famous heritages building of Bangladesh 60 dome mosque (Shat Gombuj Moshjid) has been examined to get expected result. Furthermore, this paper discusses how AI can be used as a personalized tool for architects to generate and express design ideas. It evaluates popular datasets for architectural purposes and considers the potential outcomes of experiments. The input of AI in the design process could usher in a new era of architectural design. As data continues to grow, it is shaping our collective future. Therefore, this paper concludes that it is essential to prepare our trained datasets to accept the future which might open up an extraordinary new chapter in the architectural realm.

International Conference on Interdisciplinary Applications of Artificial Intelligence, 2021

As a result of the development in information technology, programming has become an inevitable attribute for its function and discipline. Its inclusion in the coding design process, which is the first step of programming and program development, has been achieved with the growth of computeraided design. Mass data-indexed progression of design has led the developments to bring new approaches to the process. These approaches help to shorten the analysis and processing time of the design and bring designers closer to data science-supported machine learning in the formation of architectural design. By working on Generative Adversarial Networks (GAN), which is an exemplary framework in machine learning, to learn and produce to feed alike. With GAN, similar and different new designs are created according to data inputs in architecture. The presence of an AI technology that can support this process is a big step forward for designers to have powerful techniques that can make better design decisions in space experience optimization. In this study, the potential of GAN technology and its better understanding and application in the field of architectural design is researched.

ACM Transactions on Graphics, 2010

We present a method for automated generation of building layouts for computer graphics applications. Our approach is motivated by the layout design process developed in architecture. Given a set of high-level requirements, an architectural program is synthesized using a Bayesian network trained on real-world data. The architectural program is realized in a set of floor plans, obtained through stochastic optimization. The floor plans are used to construct a complete three-dimensional building with internal structure. We demonstrate a variety of computer-generated buildings produced by the presented approach.

Harvard University, 2019

We build here upon a previous piece, where our emphasis revolved around the strict organization of floor plans and their generation, using Artificial intelligence, and more specifically Generative Adversarial Neural Networks (GANs). As we refine our ability to generate floor plans, we raise the question of the bias intrinsic to our models and offer here to extend our study beyond the simple imperative of organization. We investigate architectural style learning, by training and tuning an array of models on specific styles: Baroque, Row House, Victorian Suburban House, & Manhattan Unit. Beyond the simple gimmick of each style, our study reveals the deeper meaning of stylistic: more than its mere cultural significance, style carries a fundamental set of functional rules that defines a clear mechanic of space and controls the internal organization of the plan. In this new article, we will try to evidence the profound impact of architectural style on the composition of floor plans. ------------------------------------------------------------------------------------------------------------------------------------ Article: https://towardsdatascience.com/architecture-style-ded3a2c3998f