What a Comfortable World: Ergonomic Principles Guided Apartment Layout Generation
2026-04-09 • Graphics
GraphicsMachine Learning
AI summaryⓘ
The authors noticed that current computer programs for creating floor plans often copy the same design problems found in real buildings. To fix this, they taught their program basic architectural rules about how rooms should be placed next to each other. Their method helps the program make floor plans that are easier and nicer to live in. Compared to other methods, their designs follow these rules better while still making realistic layouts.
floor plan generationtransformer modelarchitectural design principlesdifferentiable loss functionsroom adjacencyergonomic designlayout optimizationgenerative modelsstructural validity
Authors
Piotr Nieciecki, Aleksander Plocharski, Przemyslaw Musialski
Abstract
Current data-driven floor plan generation methods often reproduce the ergonomic inefficiencies found in real-world training datasets. To address this, we propose a novel approach that integrates architectural design principles directly into a transformer-based generative process. We formulate differentiable loss functions based on established architectural standards from literature to optimize room adjacency and proximity. By guiding the model with these ergonomic priors during training, our method produces layouts with significantly improved livability metrics. Comparative evaluations show that our approach outperforms baselines in ergonomic compliance while maintaining high structural validity.