GreenPlanner: Practical Floorplan Layout Generation via an Energy-Aware and Function-Feasible Generative Framework

2025-11-29

AI Summary

In automated architectural floor plan generation, balancing functional compliance with energy-efficiency regulations remains challenging; existing methods produce numerous invalid solutions due to the absence of automated, regulatory-aware evaluation. To address this, we propose GreenFlow—a novel end-to-end generative framework that jointly embeds learnable constraint priors and an automated assessment mechanism. Central to GreenFlow is the Practical Design Evaluator (PDE), a unified surrogate model that concurrently predicts energy performance and spatial feasibility. Trained and optimized on our proprietary GreenPD dataset, GreenFlow enables closed-loop generation. Compared to manual design, it improves design efficiency by 87%, accelerates evaluation by over five orders of magnitude, achieves >99% prediction accuracy, and eliminates invalid samples entirely. Its core innovation lies in the first deep integration of high-fidelity regulatory compliance checks—spanning both building codes and energy standards—directly into the generative process, thereby unifying controllability, efficiency, and strict regulatory adherence in green building design.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Building design directly affects human well-being and carbon emissions, yet generating spatial-functional and energy-compliant floorplans remains manual, costly, and non-scalable. Existing methods produce visually plausible layouts but frequently violate key constraints, yielding invalid results due to the absence of automated evaluation. We present GreenPlanner, an energy- and functionality-aware generative framework that unifies design evaluation and generation. It consists of a labeled Design Feasibility Dataset for learning constraint priors; a fast Practical Design Evaluator (PDE) for predicting energy performance and spatial-functional validity; a Green Plan Dataset (GreenPD) derived from PDE-guided filtering to pair user requirements with regulation-compliant layouts; and a GreenFlow generator trained on GreenPD with PDE feedback for controllable, regulation-aware generation. Experiments show that GreenPlanner accelerates evaluation by over $10^{5} imes$ with $>$99% accuracy, eliminates invalid samples, and boosts design efficiency by 87% over professional architects.

Problem

• Automates energy-efficient and functional floorplan generation
• Ensures compliance with spatial and energy regulations automatically
• Accelerates design evaluation while eliminating invalid layout samples

Innovation

• Unified generative framework for energy-aware floorplan design
• Fast evaluator predicts energy performance and functional validity
• Generator trained with filtered dataset for regulation-compliant layouts