Automated Facility Enumeration for Building Compliance Checking using Door Detection and Large Language Models

2025-09-21

AI Summary

Automated enumeration of facility types and their spatial distributions in Building Code Compliance (BCC) checking has long been overlooked; manual verification remains inefficient and error-prone. Method: We propose the first facility enumeration framework integrating door detection with large language models (LLMs), innovatively incorporating Chain-of-Thought (CoT) reasoning to enable interpretable, semantics- and regulation-aware quantity validation from floor plans. Crucially, our method requires no facility-type-specific training. Contribution/Results: The framework demonstrates strong generalization across diverse datasets and multi-facility categories, alongside robustness to plan variations. Experiments on both real-world and synthetic floor plans show significant improvements in facility count accuracy, validating its effectiveness and practicality. This work establishes a novel paradigm for automated BCC, advancing toward fully interpretable, rule-grounded, and scalable compliance verification.

Technology Category

• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Building compliance checking (BCC) is a critical process for ensuring that constructed facilities meet regulatory standards. A core component of BCC is the accurate enumeration of facility types and their spatial distribution. Despite its importance, this problem has been largely overlooked in the literature, posing a significant challenge for BCC and leaving a critical gap in existing workflows. Performing this task manually is time-consuming and labor-intensive. Recent advances in large language models (LLMs) offer new opportunities to enhance automation by combining visual recognition with reasoning capabilities. In this paper, we introduce a new task for BCC: automated facility enumeration, which involves validating the quantity of each facility type against statutory requirements. To address it, we propose a novel method that integrates door detection with LLM-based reasoning. We are the first to apply LLMs to this task and further enhance their performance through a Chain-of-Thought (CoT) pipeline. Our approach generalizes well across diverse datasets and facility types. Experiments on both real-world and synthetic floor plan data demonstrate the effectiveness and robustness of our method.

Problem

• Automating facility enumeration for building compliance checking against regulations
• Validating facility quantities and spatial distribution using statutory requirements
• Integrating door detection with LLM reasoning to replace manual inspection

Innovation

• Integrates door detection with LLM-based reasoning
• Applies Chain-of-Thought pipeline to enhance LLMs
• Generalizes across diverse datasets and facility types