Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)

AI for Custom Floor Plan Generation

Authors
Vibhu Khera1, Amit Amit1, Rakshita Rakshita1, M. Mohan1, *
1Department of Computer Science & Engineering, SRM University Delhi-NCR, Sonepat, Haryana, India
*Corresponding author. Email: m.mohan@srmuniversity.ac.in
Corresponding Author
M. Mohan
Available Online 23 May 2025.
DOI
10.2991/978-94-6463-718-2_92How to use a DOI?
Keywords
Architectural Planning; Floor Plan Generation; 2D Floor Plans; Building Design Automation; Architectural Data Analysis; Floor Plan Suggestions
Abstract

The most important areas in architectural planning and design include floor plan optimization and prediction. The following research focuses on using machine learning for predicting and providing suggestions on multiple floor plans according to defined user parameters, which can include plot dimensions, number of floors, and number of bedrooms. We take a dataset containing the dimensions of 2D floor plans and extract meaningful features like plot area and room sizes using feature engineering and data pre-processing techniques. The proposed model makes use of Linear Regression to establish relationships between plot area, structural parameters, and room dimensions.

In furtherance of usability, an interactive system is developed to generate specific floor plans. The system offers predictions on room sizes from user inputs and applies variation techniques to achieve multiple realistic options for a floor plan. It also projects its results in a standardized format with room dimensions for easy applicability. Evaluating MSE for the model, it is exhibited that it can predict accurate room size.

The framework allows architects and planners to design preliminary floor plans on a scalable, data-driven level. It cuts down the time and effort in doing manual planning but still provides room for flexibility in customization. Future work would involve integrating more complex models and expanding datasets to further enhance prediction accuracy and accommodate a variety of architectural styles.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
Series
Advances in Computer Science Research
Publication Date
23 May 2025
ISBN
978-94-6463-718-2
ISSN
2352-538X
DOI
10.2991/978-94-6463-718-2_92How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Vibhu Khera
AU  - Amit Amit
AU  - Rakshita Rakshita
AU  - M. Mohan
PY  - 2025
DA  - 2025/05/23
TI  - AI for Custom Floor Plan Generation
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 1096
EP  - 1105
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_92
DO  - 10.2991/978-94-6463-718-2_92
ID  - Khera2025
ER  -