Conference paper 2025

VR and Deep Learning Based Digital Twin System for Visual Inspection Training of Road Bridge

WK
Wakabayashi, Kyohei
 OT
Oda, Tetsuya
 ST
Sato, Takeharu
 ST
Sato, Toshiyuki
 HM
Hirota, Masaharu
 SH
Shimada, Hideyuki
2025 1st International Conference on Consumer Technology, ICCT-Pacific 2025
Conference
Abstract

Road bridges constitute critical infrastructure that ensures safe and efficient transportation. However, they are susceptible to damage caused by aging and external factors. For example, cracking, corrosion of members, surface delamination and various other types of deterioration progress depending on the material and structural type. Beyond the degradation of structural functionality and durability, such damage heightens risks to vehicles and pedestrians. Consequently, effective inspection and maintenance strategies are imperative. In this paper, we propose a digital twin system based on virtual reality and deep learning to train inspection engineers for various bridge types and maintenance management. The proposed system enables bridge inspection training within a virtual environment using a three-dimensional bridge model and provides real-time feedback to the trainees. Furthermore, the effectiveness of the proposed system is evaluated through its application to a road bridge on National Route 2, a critical transportation artery in Japan with high traffic volumes. © 2025 IEEE.

Keywords

Author Keywords

Virtual reality Deep learning technical training digital twin Road Bridge Inspection

Index Keywords

Learning systems Virtual reality Digital twin Deep learning Inspection Corrosion Critical infrastructures Deterioration Highway administration Highway bridges Nondestructive examination Roads and streets Transportation routes Aging factors Bridge inspection External factors Material's type Road bridge Road bridge inspection Structural type Technical training Visual inspection
Author Affiliations
Graduate School of Science and Engineering, Okayama University of Science, Okayama, Okayama, Japan
Department of Information and Computer Engineering, Okayama University of Science, Okayama, Okayama, Japan
Department of Biosphere-Geosphere Science, Okayama University of Science, Okayama, Okayama, Japan
Department of Information Science and Engineering, Okayama University of Science, Okayama, Okayama, Japan
Funding & Acknowledgements
Ministry of Land, Infrastructure, Transport and Tourism, MLIT
This work was supported by Yakumo Foundation for Environmental Science, JST Program for Co-creating Startup Ecosystem, Grant Number JPMJSF2316 and JSPS KAKENHI Grant Number JP24K07993. The authors express their deepest gratitude to the Okayama National Highway Office, Chugoku Regional Development Bureau, Ministry of Land, Infrastructure, Transport and Tourism (MLIT), for their invaluable support and cooperation throughout this work.
Chugoku Regional Development Bureau, CRDB
This work was supported by Yakumo Foundation for Environmental Science, JST Program for Co-creating Startup Ecosystem, Grant Number JPMJSF2316 and JSPS KAKENHI Grant Number JP24K07993. The authors express their deepest gratitude to the Okayama National Highway Office, Chugoku Regional Development Bureau, Ministry of Land, Infrastructure, Transport and Tourism (MLIT), for their invaluable support and cooperation throughout this work.
Japan Science and Technology Agency, JST
Grant: JPMJSF2316
This work was supported by Yakumo Foundation for Environmental Science, JST Program for Co-creating Startup Ecosystem, Grant Number JPMJSF2316 and JSPS KAKENHI Grant Number JP24K07993. The authors express their deepest gratitude to the Okayama National Highway Office, Chugoku Regional Development Bureau, Ministry of Land, Infrastructure, Transport and Tourism (MLIT), for their invaluable support and cooperation throughout this work.
Japan Science and Technology Agency, JST
This work was supported by Yakumo Foundation for Environmental Science, JST Program for Co-creating Startup Ecosystem, Grant Number JPMJSF2316 and JSPS KAKENHI Grant Number JP24K07993. The authors express their deepest gratitude to the Okayama National Highway Office, Chugoku Regional Development Bureau, Ministry of Land, Infrastructure, Transport and Tourism (MLIT), for their invaluable support and cooperation throughout this work.
Japan Society for the Promotion of Science, JSPS
Grant: JP24K07993
This work was supported by Yakumo Foundation for Environmental Science, JST Program for Co-creating Startup Ecosystem, Grant Number JPMJSF2316 and JSPS KAKENHI Grant Number JP24K07993. The authors express their deepest gratitude to the Okayama National Highway Office, Chugoku Regional Development Bureau, Ministry of Land, Infrastructure, Transport and Tourism (MLIT), for their invaluable support and cooperation throughout this work.
Japan Society for the Promotion of Science, JSPS
This work was supported by Yakumo Foundation for Environmental Science, JST Program for Co-creating Startup Ecosystem, Grant Number JPMJSF2316 and JSPS KAKENHI Grant Number JP24K07993. The authors express their deepest gratitude to the Okayama National Highway Office, Chugoku Regional Development Bureau, Ministry of Land, Infrastructure, Transport and Tourism (MLIT), for their invaluable support and cooperation throughout this work.
References 9 References
1 Ali, Luqman, Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures, Sensors, 21, 5, pp. 1-22, (2021)
2 Wang, Yuchen, A deep learning-based approach for assessment of bridge condition through fusion of multi-type inspection data, Engineering Applications of Artificial Intelligence, 128, (2024)
3 Li, Yue, RDD-YOLO: Road Damage Detection Algorithm Based on Improved You Only Look Once Version 8, Applied Sciences (Switzerland), 14, 8, (2024)
4 Grasso, Nives, LiDAR and SfM-MVS Integrated Approach to Build a Highly Detailed 3D Virtual Model of Urban Areas, International Conference on Geographical Information Systems Theory, Applications and Management, GISTAM - Proceedings, 2023-April, pp. 128-135, (2023)
5 Inzerillo, Laura, Image-based 3D reconstruction using traditional and UAV datasets for analysis of road pavement distress, Automation in Construction, 96, pp. 457-469, (2018)
6 Liao, Jianghua, Comparing LiDAR and SfM digital surface models for three land cover types, Open Geosciences, 13, 1, pp. 497-504, (2021)
7 Lu, Yihan, Virtual Reality Architecture Teaching Application Based on Unity Platform—Taking a Small Architect's Metaverse Application as an Example, Computational Design and Robotic Fabrication, Part F2072, pp. 180-189, (2024)
8 Mulders, Miriam, Virtual Reality in Vocational Training: A Study Demonstrating the Potential of a VR-based Vehicle Painting Simulator for Skills Acquisition in Apprenticeship Training, Technology, Knowledge and Learning, 29, 2, pp. 697-712, (2024)
9 Ma, Chenfei, A Bi-Directional LSTM Network for Estimating Continuous Upper Limb Movement from Surface Electromyography, IEEE Robotics and Automation Letters, 6, 4, pp. 7217-7224, (2021)
Quick Actions
Full Text via DOI
Citation Metrics
0
Times Cited (Scopus)
References 9
Document Identifiers