Intelligent Inspection and Warning Robotic System for Onsite Construction Safety Monitoring Using Computer Vision and Unmanned Ground Vehicle

• DOI: 10.1061/9780784485293.063
• Publication Date: 2024-03-18T10:03:57Z
• Authors: Xi Hu; Rayan H. Assaad
• Keywords: Unmanned ground vehicle

Worker safety is a critical factor to construction success and should be properly monitored managed at jobsites. While many vision-based worker inspection/monitoring systems were developed by previous studies, they commonly suffer from low mobility of stationary cameras the lack taking real-time actions. To address these challenges, this paper proposes an intelligent inspection warning robotic system using unmanned ground vehicle (UGV). This (1) automatically movably detects workers personal protective equipment (PPE) state-of-the-art YOLOv8 architecture deep learning-based computer vision model, (2) dynamically warns/reminds wearing undetected required PPE. The includes prototype provide mobility, high-resolution camera collect visual data, (3) speaker for auditory warning/reminder information, (4) single board data processing. proposed was tested real site. Field test results showed that it can reliably detect their PPE then play voice messages remind them wear when not detected. Ultimately, contributes body knowledge developing UGV-based improving onsite management.