Autonomous Port Area Safety Inspection Using a Multimodal Sensor-Integrated UGV
Journal
Proceedings of the International Symposium on Automation and Robotics in Construction
Start Page
446
End Page
453
ISSN
2413-5844
ISBN (of the container)
978-064583223-5
ISBN
[9780645832235]
Date Issued
2026-06-22
Author(s)
Abstract
Traditional port inspections are highly dependent on manual labor and static sensors, leading to high operational costs and fragmented data. These limitations hinder effective data integration and advanced analysis, creating a critical need for an automated inspection framework to improve safety and efficiency. This paper proposes an automated safety inspection system that uses Unmanned Ground Vehicles (UGVs). The system implements a multimodal data integration platform that synchronizes heterogeneous sensor streams by aligning timeframes and unifying sampling frequencies. Data transmission is facilitated via a HyperText Transfer Protocol (HTTP)-based real-time streaming architecture, enabling a centralized interface for remote waypoint planning and mission execution. To ensure operational safety, UGVs incorporate dynamic obstacle avoidance and an object detection model to identify critical assets. The system also performs real-time thermal monitoring, triggering automated alarms when temperature thresholds are exceeded. Field tests demonstrate that the UGV achieves precise autonomous navigation in outdoor port environments, with a mean waypoint navigating error within 0.032 meters. The proposed framework offers a centralized and accessible solution for safety inspections in extensive port environments, effectively reducing operational complexity while enhancing overall efficiency and personnel safety.
Event(s)
43rd International Symposium on Automation and Robotics in Construction, ISARC 2026,22 June 2026 - 26 June 2026,Singapore
Subjects
Autonomous Navigation
Multimodal Data Integration
Port Safety Inspection
Real-time Monitoring
Unmanned Ground Vehicles (UGVs)
Publisher
International Association for Automation and Robotics in Construction (IAARC)
Type
conference paper