The synthesis of architectural floor plans represents a complex interplay between spatial functionality, aesthetic sensibility, and user requirements. Traditionally reliant on manual drafting and professional intuition, the process is undergoing a transformative shift through the integration of data-driven intelligence and algorithmic design methodologies. This paper explores the convergence of computational algorithms, machine learning models, and human-centric design principles to generate efficient, adaptable, and creative floor plan solutions. By leveraging architectural datasets, generative algorithms, and optimization techniques, automated systems can assist architects in creating layout variations that adhere to structural, environmental, and user-defined constraints. At the same time, the role of human creativity remains indispensable in guiding form, flow, and context-sensitive decisions. The study highlights key technologies, frameworks, and collaborative workflows that bridge artificial intelligence and architectural design, offering a new paradigm for intelligent space planning and architectural innovation.

Architectural design, floor plan synthesis, algorithmic design

United Nations Human Settlements Programme. Priorities 2022–2023: Adequate housing, cities and climate change and localising the sustainable development goals. UN-Habitat. Available at: https://unhabitat.org/priorities-2022-2023-adequate-housing-cities-and-climate-change-and-localising-the-sustainable (2024, accessed 21 June 2024).

Bahrehmand A, Batard T, Marques R, et al. Optimizing layout using spatial quality metrics and user preferences. Graph Models 2017; 93: 25–38.

AIA ETN. Design to construction. https://www.aiaetn.org/find-an-architect/design-to-construction/ (2022).

Arora JS. Computational design optimization: A review and future directions. Struct Saf 1990; 7: 131–148.

Goodfellow I, Bengio Y, Courville A. Deep learning. MIT Press, 2016.

Topuz B, Çakici Alp N. Machine learning in architecture. Autom ConStruct 2023; 154: 105012.

Deng W, Liu Q, Zhao F, et al. Learning by doing: A dual-loop implementation architecture of deep active learning and human-machine collaboration for smart robot vision. Robot Comput Integrated Manuf 2024; 86: 102673.

Genkin M, McArthur JJ. B-SMART: A reference architecture for artificially intelligent autonomic smart buildings. Eng Appl Artif Intell 2023; 121: 106063.

Vrachliotis G. Architecture and design in the age of cybernetics. Berlin, Boston, MA: Birkhäuser, 2022.

Friedman Y. Toward a scientific architecture. Cambridge, MA: MIT Press, 1980.

Luo Z, Huang W. FloorplanGAN: Vector residential floorplan adversarial generation. Autom ConStruct 2022; 142: 104470.

Nauata N, Chang K, Cheng C, et al. House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation. CVPR, 2020.

Sun J, Wu W, Zhang G, et al. WallPlan: Synthesizing floorplans by learning to generate wall graphs. ACM Trans Graph; 41: 1–14.

Pizarro PN, Hitschfeld N, Sipiran I, et al. Automatic floor plan analysis and recognition. Autom ConStruct 2022; 140: 104348.

Sharma D, Gupta N, Chattopadhyay C, et al. DANIEL: A deep architecture for automatic analysis and retrieval of building floor plans. Proceedings of the International Conference on Document Analysis and Recognition (ICDAR) 2017; 1: 420–425.

Li T, Ho D, Li C, et al. HouseExpo: A large-scale 2D indoor layout dataset for learning-based algorithms on mobile robots. In: IEEE International Conference on Intelligent Robots and Systems, Las Vegas, NV, 24 October 2020–24 January 2021: 5839–5846.

Wu W, Fu XM, Tang R, et al. Data-driven interior plan generation for residential buildings. ACM Trans Graph; 38: 1–12.

Hu R, Huang Z, Tang Y, et al. Graph2Plan: Learning floorplan generation from layout graphs. ACM Trans Graph; 39. Epub ahead of print 27 April 2020.

Nauata N, Hosseini S, Chang K-H, et al. House-GAN++: Generative adversarial layout refinement networks. CVPR, 2021.

Shabani MA, Hosseini S, Furukawa Y. HouseDiffusion: Vector floorplan generation via a diffusion model with discrete and continuous denoising. https://aminshabani.github.io/housediffusion (2022, accessed 16 October 2023).

Hosseini S, Shabani MA, Irandoust S, et al. PuzzleFusion: Unleashing the power of diffusion models for spatial puzzle solving. https://www.magicplan.app/ (2023, accessed 17 October 2023).

Upadhyay A, Dubey A, Arora V, et al. FLNet: Graph constrained floor layout generation. In: ICMEW 2022 - IEEE International Conference on Multimedia and Expo Workshops 2022, Taipei City, Taiwan, 18–22 July 2022.

Standfest M, Franzen M, Schröder Y, et al. Swiss Dwellings: A large dataset of apartment models including aggregated geolocation-based simulation results. Zenodo, 2023.

Bielik M, Zhang L, Schneider S. Big data, good data, and residential floor plans: Feature selection for maximizing the information value and minimizing redundancy in residential floor plan data sets. In: Computer-Aided Architectural Design. INTERCONNECTIONS. Cham: Springer Nature Switzerland, 2023, Vol. 1819, pp. 607–622.

Mostafavi F, Khademi S. Micro-climate building context visualization: A pipeline for generating buildings’ environmental context maps using numerical simulation data. In: 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe), 2023, Graz, Austria, pp. 9–18.

Merrell P, Schkufza E, Koltun V. Computer-generated residential building layouts. ACM Trans Graph 2010; 29: 181.

Peng C-H, Yang Y-L, Wonka P. Computing layouts with deformable templates. ACM Trans Graph 2014; 33: 1–11.

Szeliski R. Computer vision: Algorithms and applications. London: Springer London, 2011.

Tang H, Zhang Z, Shi H, et al. Graph transformer GANs for graph-constrained house generation. https://arxiv.org/abs/2303.08225 (2023).

Abu-Aisheh Z, Raveaux R, Ramel J-Y, et al. An exact graph edit distance algorithm for solving pattern recognition problems. In: 4th International Conference on Pattern Recognition Applications and Methods, 2015.

Van Engelenburg CCJ, Khademi S, Van Gemert JC. SSIG: A visually-guided graph edit distance for floor plan similarity. IEEE Xplore, 2023.

Van Engelenburg C, Mostafavi F, Kuhn E, et al. MSD: A benchmark dataset for floor plan generation of building complexes. arXiv, 2024.

CVAAD. ICCV23 Challenge. https://github.com/cvaad-workshop/iccv23-challenge (2023).

Jeon Y, Tran DQ, Park S. Skip-connected neural networks with layout graphs for floor plan auto-generation. https://arxiv.org/abs/2309.13881v2 (2023, accessed 6 December 2023).

Weng W, Zhu X. U-Net: Convolutional networks for biomedical image segmentation. IEEE Access 2015; 9: 16591–16603.

Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations (ICLR), 2017. https://arxiv.org/abs/1609.02907v4 (accessed 13 December 2023).

Kirillov A, Mintun E, Ravi N, et al. Segment Anything. https://arxiv.org/abs/2304.02643v1 (2023, accessed 5 December 2023).

Kuhn E. Adapting HouseDiffusion for conditional floor plan generation on modified Swiss Dwellings dataset. https://arxiv.org/abs/2312.03938v1 (2023, accessed 11 December 2023).

Veličković P, Casanova A, Liò P, et al. Graph Attention Networks. In: 6th International Conference on Learning Representations (ICLR), 2018. Epub ahead of print 30 October 2017.

Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics 1977; 33: 159–174.

Black K, Janner M, Du Y, et al. Training diffusion models with reinforcement learning. https://rl-diffusion.github.io (accessed 12 January 2024).

Brown N, Garland A, Fadel G, et al. Deep reinforcement learning for engineering design through topology optimization of elementally discretized design domains. https://www.aaai.org (2022, accessed 3 January 2024).