Autonomous Construction-Site Safety Inspection Using Mobile Robots: A Multilayer VLM-LLM Pipeline

TL;DR

This paper presents a multi-layer AI and robotics framework enabling autonomous construction-site safety inspections, automatically generating safety reports by connecting robot perceptions to safety rules, validated in simulated hazard scenarios.

Contribution

Introduces a transparent, multi-layer VLM-LLM pipeline that links robotic scene understanding with safety rule assessment and report generation, moving beyond black-box models.

Findings

High recall in hazard detection

Competitive precision compared to state-of-the-art models

Validated in simulated construction hazards

Abstract

Construction safety inspection remains mostly manual, and automated approaches still rely on task-specific datasets that are hard to maintain in fast-changing construction environments due to frequent retraining. Meanwhile, field inspection with robots still depends on human teleoperation and manual reporting, which are labor-intensive. This paper aims to connect what a robot sees during autonomous navigation to the safety rules that are common in construction sites, automatically generating a safety inspection report. To this end, we proposed a multi-layer framework with two main modules: robotics and AI. On the robotics side, SLAM and autonomous navigation provide repeatable coverage and targeted revisits via waypoints. On AI side, a Vision Language Model (VLM)-based layer produces scene descriptions; a retrieval component powered grounds those descriptions in OSHA and site policies; Another VLM-based layer assesses the safety situation based on rules; and finally Large Language Model (LLM) layer generates safety reports based on previous outputs. The framework is validated with a proof-of-concept implementation and evaluated in a lab environment that simulates common hazards across three scenarios. Results show high recall with competitive precision compared to state-of-the-art closed-source models. This paper contributes a transparent, generalizable pipeline that moves beyond black-box models by exposing intermediate artifacts from each layer and keeping the human in the loop. This work provides a foundation for future extensions to additional tasks and settings within and beyond construction context.