HAVEN: A Review of An AI assisted House Planning and Construction Cost Estimation System

Author

Prof. Heena Kachhela, Bhavesh Hatwar, Bhuvan Bhonde, Vansh Giradkar, Chetan Kolhe, Akansha Kawale

Abstract

 Computational methods are increasingly being explored to support different aspects of residential building planning. This paper reviews twenty-two studies covering architectural layout generation, multi-criteria decision-support methods, and data-driven construction cost analysis. The review compares the principal techniques, reported outcomes, evaluation settings, and limitations described in the selected studies. In architectural design, graph-based optimization and deep generative models have expanded the ways in which spatial layouts can be represented, generated, and reconstructed. Decision-support research offers established methods for handling competing criteria, while cost-analysis studies report growing use of machine-learning models, including ensemble and neural-network approaches. Despite these developments, recurring challenges include geometric inconsistencies, dependence on structured input, limited diversity in datasets, and variation in model performance across evaluation settings. The paper consolidates these findings and highlights general research needs related to usability, reliability, data quality, and external validation in computational approaches to residential planning.

Keywords

computational architecture, architectural layout generation, generative models, decision-support methods, machine learning, built-environment analysis

Full Text:

Download Paper PDF

References

[1] R. Yu, N. Gu, G. Lee, and A. Khan, "A systematic review of architectural design collaboration in immersive virtual environments," Buildings, vol. 12, no. 3, 2022.

[2] "Least to most range (LMR): A novel consistent weighting multicriteria method applied to green supplier selection," IEEE Access, 2023.

[3] "A comprehensive framework for supplier selection using subjective, objective, and hybrid multi-criteria decision-making techniques with sensitivity analysis," 2023.

[4] B. Tajziyehchi, "Construction cost growth prediction: A feature selection and machine learning approach," M.S. thesis, Univ. of Alberta, 2020.

[5] G. K. Sepúlveda et al., "Semi-automatic building layout generation for virtual environments," IEEE Access, vol. 12, 2024.

[6] H. Zhang et al., "MaskPLAN: Masked generative layout planning from partial input," in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2024.

[7] N. Nauata, K.-H. Chang, C.-Y. Cheng, G. Mori, and Y. Furukawa, "House-GAN++: Generative adversarial layout refinement network towards intelligent computational agent for professional architects," in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2021.

[8] Y. Du et al., "GA-optimized BP neural network model for architectural engineering cost estimation," 2017.

[9] "Automated semantics and topology representation of residential-building space using floor-plan raster maps," IEEE journal article.

[10] Y. Takeuchi, Q. An, and A. Yamashita, "Single-stage graph-based floorplan generation," IEEE Access, vol. 14, 2026.

[11] "ActFloor-GAN: Activity-guided adversarial networks for human-centric floorplan design," IEEE journal article.

[12] "LayoutGMN: Neural graph matching for structural layout similarity," conference paper.

[13] C. Xu et al., "GoodFloorplan: A reinforcement learning framework for chip floorplanning," 2022.

[14] "Construction cost estimation using hybrid stacking of Random Forest and XGBoost," in Proc. INOCON, 2024.

[15] "BP neural network construction cost prediction model with Adam/SGD/Adadelta optimization," conference/book chapter.

[16] "Effective replenishment planning and inventory control under multiple suppliers and stochastic lead times," in Proc. CODIT, 2024.

[17] L. Simonsen et al., "Graph neural network-based door detection from CAD floor plans," 2021.

[18] Y. Wei and X. Li, "Graph-augmented text-based floorplan generation," in Proc. Int. Conf. Automation in Manufacturing, Transportation and Logistics (ICaMaL), 2024.

[19] Z. Zhang, J. Liu, X. Li, C. Hu, F. Dunkin, and S. Zhang, "A novel framework for structure descriptors-guided hand-drawn floor plan reconstruction," in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS), 2024.

[20] Vincy R and E. G. M. Kanaga, "AI-based construction cost estimation using adaptive machine learning," in Proc. Int. Conf. Inventive Computation Technologies (ICICT), 2026.

[21] Q. Xu, J. Liu, Y. Tang, and Z. Zhang, "Research on construction project cost prediction based on BP neural network," in Proc. Int. Conf. Software, Systems and Information Technology (SSITCON), 2025.

[22] Q. Jin, "Research on construction cost control system of project management based on computer BIM technology," in Proc. Int. Conf. Electrical Drives, Power Electronics & Engineering (EDPEE), 2024.

Note: bibliographic details above are transcribed from the source manuscripts as supplied; authors, venues, and years should be cross-verified against the original publisher records prior to final submission.

 

 

Share your valuable work from Social Media Buttons