Embedded Files
The Construction Automation and Robotics Lab (CARL) conducts interdisciplinary research in autonomous robotics, artificial intelligence, computer vision, intelligent sensing, and infrastructure systems. Our research aims to improve automation, safety, productivity, and intelligent decision-making in construction and civil infrastructure through advanced robotic technologies and AI-driven systems.
AI-Enabled Robotic Inspection and Repair Systems for Thin Crack
AI-Enabled Robotic Inspection and Repair Systems for Thin Crack
Our research focuses on AI-enabled robotic inspection and repair systems for structural defect detection and infrastructure assessment. The lab develops advanced deep learning and computer vision algorithms for thin and branched crack detection, semantic segmentation, automated defect interpretation, and intelligent robotic inspection. Current work investigates generative AI, transfer learning, adversarial refinement, and vision-language model (VLM) techniques for real-time infrastructure condition assessment and automated repair applications.
Ogun, E., Voeurn, Y., and Lee, D. (2026). A Real-Time Mobile Robotic System for Crack Detection in Construction Using Two-Stage Deep Learning, Sensors: Special Issue on “Sensing and Control Technology of Intelligent Robots”, 26(2), Jan, 2026. https://doi.org/10.3390/s26020530
Park, K., Kweon, H., and Lee, D. (Under review). Enhanced Seam Segmentation for Automated Welding Robot in Construction Through Transfer Learning: Addressing Limitations of Bilateral Segmentation Network, IEEE Access.
Autonomous Mobile Robotic Welding Systems
Autonomous Mobile Robotic Welding Systems
The lab develops autonomous mobile robotic welding systems capable of real-time navigation, positioning, seam detection, trajectory planning, and automated welding operations in dynamic construction environments. Our research integrates robotic manipulators, unmanned ground vehicles (UGVs), computer vision systems, LiDAR sensing, and intelligent control algorithms to enable autonomous welding for construction and infrastructure applications. Current work focuses on autonomous navigation, collision avoidance, motion planning, target object detection, robotic control, and human-robot interaction for real-world construction environments.
Lee, D. and Han, K. (2025). Autonomous Navigation and Positioning of Real-time and Automated Mobile Robotic Welding System, Journal of Construction Engineering and Management, ASCE, 151(5), May, 2025. https://doi.org/10.1061/JCEMD4.COENG-16053
Lee, D. and Han, K. (2024). Vision-based construction robot for real-time automated welding with human-robot interaction, Automation in Construction, 168(A), Dec, 2024. https://doi.org/10.1016/j.autcon.2024.105782
Lee, D., Nie, G., and Han, K. (2024). Automatic and Real-time Joint Tracking and 3D Scanning for a Construction Welding Robot, Journal of Construction Engineering and Management, ASCE, 150(3), Mar, 2024. https://doi.org/10.1061/JCEMD4.COENG-14135
Lee, D., Nie, G., and Han, K. (2023). Vision-based Inspection of Prefabricated Components Using Camera Poses: Addressing Inherent Limitations of Image-based 3D Reconstruction, Journal of Building Engineering, 64. Apr, 2023. https://doi.org/10.1016/j.jobe.2022.105710
Lee, D., Nie, G., Ahmed, A., and Han, K. (2022). Development of Automated Welding System for Construction: Focused on Robotic Arm Operation for Weave Patterns, International Journal of High-Rise Buildings, 11(2), pp. 115-124. Jun, 2022. https://doi.org/10.21022/IJHRB.2022.11.2.115
UGV-UAV Collaborative Robotic Systems for Automated Indoor MEP Defect Detection and Inspection
UGV-UAV Collaborative Robotic Systems for Automated Indoor MEP Defect Detection and Inspection
The lab investigates collaborative unmanned aerial vehicle (UAV) and unmanned ground vehicle (UGV) robotic systems for automated indoor MEP inspection and intelligent infrastructure monitoring. Our research explores autonomous multi-robot coordination, real-time mapping, defect detection, semantic interpretation, and collaborative sensing systems for complex indoor environments. Current projects focus on integrating aerial-ground robotics with AI-enabled perception systems, computer vision, and intelligent navigation technologies for automated infrastructure inspection and monitoring.
Other Research Areas
Other Research Areas
Kim, J., Kim, J., and Lee, D. (2026). Hybrid Spectro-Temporal Fusion Framework for Structural Health Monitoring, arXiv preprint. https://doi.org/10.48550/arXiv.2604.16589
Albergo, N., Hwang, J., Lee, D., and Han, K. (2025). Motion-Based Communication as a Language: Formal Grammar Representation and Model-Free Decoding with Dense Optical Flow, Multidisciplinary Journal of Civil Engineering, ASCE, 3(1), Aug, 2025. https://doi.org/10.1061/AOMJAH.AOENG-0075
Voeurn, Y., Ogun, E., and Lee, D. (Under review). Bridging the Digital-Physical Decoupling: A Systematic Review of AI and Robotics in Industrialized Construction (2005–2025), Automation in Construction
Page updated
Report abuse