{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:36:34Z","timestamp":1782261394908,"version":"3.54.5"},"reference-count":57,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The deterioration of civil infrastructure poses a significant threat to public safety, yet conventional manual inspections remain subjective, labor-intensive, and constrained by accessibility. To address these challenges, this paper presents a real-time robotic inspection system that integrates deep learning perception and autonomous navigation. The proposed framework employs a two-stage neural network: a U-Net for initial segmentation followed by a Pix2Pix conditional generative adversarial network (GAN) that utilizes adversarial residual learning to refine boundary accuracy and suppress false positives. When deployed on an Unmanned Ground Vehicle (UGV) equipped with an RGB-D camera and LiDAR, this framework enables simultaneous automated crack detection and collision-free autonomous navigation. Evaluated on the CrackSeg9k dataset, the two-stage model achieved a mean Intersection over Union (mIoU) of 73.9 \u00b1 0.6% and an F1-score of 76.4 \u00b1 0.3%. Beyond benchmark testing, the robotic system was further validated through simulation, laboratory experiments, and real-world campus hallway tests, successfully detecting micro-cracks as narrow as 0.3 mm. Collectively, these results demonstrate the system\u2019s potential for robust, autonomous, and field-deployable infrastructure inspection.<\/jats:p>","DOI":"10.3390\/s26020530","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:52:57Z","timestamp":1768319577000},"page":"530","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Real-Time Mobile Robotic System for Crack Detection in Construction Using Two-Stage Deep Learning"],"prefix":"10.3390","volume":"26","author":[{"given":"Emmanuella","family":"Ogun","sequence":"first","affiliation":[{"name":"Mechanical Engineering Department, Georgia Southern University, Statesboro, GA 30460, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7945-8965","authenticated-orcid":false,"given":"Yong Ann","family":"Voeurn","sequence":"additional","affiliation":[{"name":"Civil Engineering and Construction Department, Georgia Southern University, Statesboro, GA 30460, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0976-2488","authenticated-orcid":false,"given":"Doyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Civil Engineering and Construction Department, Georgia Southern University, Statesboro, GA 30460, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Farrar, C.R., and Keith, W. (2012). Introduction. Structural Health Monitoring, John Wiley & Sons, Ltd.","DOI":"10.1002\/9781118443118.ch1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1061\/(ASCE)1084-0702(2003)8:6(374)","article-title":"Updating Bridge Reliability Based on Bridge Management Systems Visual Inspection Results","volume":"8","author":"Estes","year":"2003","journal-title":"J. Bridge Eng."},{"key":"ref_3","unstructured":"American Society of Civil Engineers (2025). 2025 Report Card for America\u2019s Infrastructure, American Society of Civil Engineers."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.aei.2015.01.008","article-title":"A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure","volume":"29","author":"Koch","year":"2015","journal-title":"Adv. Eng. Inform."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Jayaram, M.A. (2023). Computer vision applications in construction material and structural health monitoring: A scoping review. Mater. Today Proc., in press.","DOI":"10.1016\/j.matpr.2023.06.031"},{"key":"ref_6","unstructured":"Percepto (2023). Perception 2023: The State of Visual Inspection, Percepto Ltd.. Available online: https:\/\/percepto.co\/wp-content\/uploads\/2023\/03\/2023-State-of-visual-inspection.pdf."},{"key":"ref_7","unstructured":"U.S. Bureau of Labor Statistics (2026, January 07). Employment Projections\u20142023\u20132033, Available online: https:\/\/www.bls.gov\/news.release\/archives\/ecopro_08292024.pdf."},{"key":"ref_8","unstructured":"U.S. Bureau of Labor Statistics (2026, January 07). Occupational Outlook Handbook: Construction Laborers and Helpers, Available online: https:\/\/www.bls.gov\/ooh\/construction-and-extraction\/construction-laborers-and-helpers.htm."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kaartinen, E., Dunphy, K., and Sadhu, A. (2022). LiDAR-Based Structural Health Monitoring: Applications in Civil Infrastructure Systems. Sensors, 22.","DOI":"10.3390\/s22124610"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Yuan, Q., Shi, Y., and Li, M. (2024). A Review of Computer Vision-Based Crack Detection Methods in Civil Infrastructure: Progress and Challenges. Remote Sens., 16.","DOI":"10.3390\/rs16162910"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ali, L., Alnajjar, F., Khan, W., Serhani, M.A., and Al Jassmi, H. (2022). Bibliometric Analysis and Review of Deep Learning-Based Crack Detection Literature Published between 2010 and 2022. Buildings, 12.","DOI":"10.3390\/buildings12040432"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"104939","DOI":"10.1016\/j.autcon.2023.104939","article-title":"Unsupervised domain adaptation for crack detection","volume":"153","author":"Weng","year":"2023","journal-title":"Autom. Constr."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"119453","DOI":"10.1016\/j.measurement.2025.119453","article-title":"Depth-aware RGB-D concrete crack segmentation and quantification using progressive cross-modal attention","volume":"258","author":"Wu","year":"2026","journal-title":"Measurement"},{"key":"ref_14","first-page":"18","article-title":"Lightweight Deep Learning Models For Edge Devices\u2014A Survey","volume":"17","author":"Musa","year":"2025","journal-title":"Int. J. Comput. Inf. Syst. Ind. Manag. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Halder, S., and Afsari, K. (2023). Robots in Inspection and Monitoring of Buildings and Infrastructure: A Systematic Review. Appl. Sci., 13.","DOI":"10.3390\/app13042304"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1016\/j.istruc.2020.08.085","article-title":"Structural damage identification based on modal frequency strain energy assurance criterion and flexibility using enhanced Moth-Flame optimization","volume":"28","author":"Huang","year":"2020","journal-title":"Structures"},{"key":"ref_17","first-page":"715","article-title":"Two-stage damage identification for bridge bearings based on sailfish optimization and element relative modal strain energy","volume":"86","author":"Huang","year":"2023","journal-title":"Struct. Eng. Mech. Int\u2019l J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4284381","DOI":"10.1155\/2020\/4284381","article-title":"Damage identification of a steel frame based on integration of time series and neural network under varying temperatures","volume":"2020","author":"Huang","year":"2020","journal-title":"Adv. Civ. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s41024-023-00371-6","article-title":"A survey on crack detection in concrete surface using image processing and machine learning","volume":"9","author":"Kirthiga","year":"2023","journal-title":"J. Build. Pathol. Rehabil."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Khan, M.A.-M., Kee, S.-H., Pathan, A.-S.K., and Nahid, A.-A. (2023). Image Processing Techniques for Concrete Crack Detection: A Scientometrics Literature Review. Remote Sens., 15.","DOI":"10.3390\/rs15092400"},{"key":"ref_21","first-page":"115","article-title":"Development of Automated Welding System for Construction: Focused on Robotic Arm Operation for Varying Weave Patterns","volume":"11","author":"Lee","year":"2022","journal-title":"Int. J. High-Rise Build."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"105710","DOI":"10.1016\/j.jobe.2022.105710","article-title":"Vision-based inspection of prefabricated components using camera poses: Addressing inherent limitations of image-based 3D reconstruction","volume":"64","author":"Lee","year":"2023","journal-title":"J. Build. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hamishebahar, Y., Guan, H., So, S., and Jo, J. (2022). A comprehensive review of deep learning-based crack detection approaches. Appl. Sci., 12.","DOI":"10.3390\/app12031374"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Navab, N., Hornegger, J., Wells, W.M., and Frangi, A.F. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Springer International Publishing.","DOI":"10.1007\/978-3-319-24553-9"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.autcon.2019.04.005","article-title":"Computer vision-based concrete crack detection using U-net fully convolutional networks","volume":"104","author":"Liu","year":"2019","journal-title":"Autom. Constr."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"9923704","DOI":"10.1155\/2021\/9923704","article-title":"Exploring the detection accuracy of concrete cracks using various CNN models","volume":"2021","author":"Mohammed","year":"2021","journal-title":"Adv. Mater. Sci. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1111\/mice.12334","article-title":"Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types","volume":"33","author":"Cha","year":"2018","journal-title":"Comput. Aided Civ. Infrastruct. Eng."},{"key":"ref_28","unstructured":"Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2250047","DOI":"10.1142\/S0218001422500471","article-title":"Automatic detection of bridge surface crack using improved Yolov5s","volume":"36","author":"Yang","year":"2022","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"8016","DOI":"10.1109\/TIE.2019.2945265","article-title":"SDDNet: Real-time crack segmentation","volume":"67","author":"Choi","year":"2019","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"104110","DOI":"10.1016\/j.autcon.2021.104110","article-title":"Semantic segmentation of cracks: Data challenges and architecture","volume":"135","author":"Panella","year":"2022","journal-title":"Autom. Constr."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"04023165","DOI":"10.1061\/JCEMD4.COENG-14135","article-title":"Automatic and Real-Time Joint Tracking and Three-Dimensional Scanning for a Construction Welding Robot","volume":"150","author":"Lee","year":"2024","journal-title":"J. Constr. Eng. Manag."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1428","DOI":"10.1177\/1475921720917227","article-title":"Deep super resolution crack network (SrcNet) for improving computer vision\u2013based automated crack detectability in in situ bridges","volume":"20","author":"Bae","year":"2021","journal-title":"Struct. Health Monit."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"115769","DOI":"10.1016\/j.measurement.2024.115769","article-title":"Residual Pyramidal GAN (RP-GAN) for crack detection and prediction of crack growth in engineered cementitious composites","volume":"242","author":"Amieghemen","year":"2025","journal-title":"Measurement"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Dai, R., Wang, R., Shu, C., Li, J., and Wei, Z. (2025). Crack Detection in Civil Infrastructure Using Autonomous Robotic Systems: A Synergistic Review of Platforms, Cognition, and Autonomous Action. Sensors, 25.","DOI":"10.3390\/s25154631"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"105344","DOI":"10.1016\/j.autcon.2024.105344","article-title":"Review of simultaneous localization and mapping (SLAM) for construction robotics applications","volume":"162","author":"Yarovoi","year":"2024","journal-title":"Autom. Constr."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"877","DOI":"10.3390\/architecture4040046","article-title":"Generative AI Applications in Architecture, Engineering, and Construction: Trends, Implications for Practice, Education & Imperatives for Upskilling\u2014A Review","volume":"4","author":"Onatayo","year":"2024","journal-title":"Architecture"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Sampath, V., Maurtua, I., Aguilar Mart\u00edn, J.J., Iriondo, A., Lluvia, I., and Aizpurua, G. (2023). Intraclass Image Augmentation for Defect Detection Using Generative Adversarial Neural Networks. Sensors, 23.","DOI":"10.3390\/s23041861"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"107537","DOI":"10.1016\/j.engappai.2023.107537","article-title":"Real-time assessment of surface cracks in concrete structures using integrated deep neural networks with autonomous unmanned aerial vehicle","volume":"129","author":"Kim","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"100868","DOI":"10.1016\/j.jobe.2019.100868","article-title":"Robotics and automated systems in construction: Understanding industry-specific challenges for adoption","volume":"26","author":"Delgado","year":"2019","journal-title":"J. Build. Eng."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"104591","DOI":"10.1016\/j.autcon.2022.104591","article-title":"Recent advancements of robotics in construction","volume":"144","author":"Xiao","year":"2022","journal-title":"Autom. Constr."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"105782","DOI":"10.1016\/j.autcon.2024.105782","article-title":"Vision-Based Construction Robot for Automated Welding in Real-Time: Proposing Fully Automated and Human-Robot Interaction","volume":"168","author":"Lee","year":"2024","journal-title":"Autom. Constr."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"04025033","DOI":"10.1061\/JCEMD4.COENG-16053","article-title":"Autonomous Navigation and Positioning of a Real-Time and Automated Mobile Robotic Welding System","volume":"151","author":"Lee","year":"2025","journal-title":"J. Constr. Eng. Manag."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Zhu, H., Leighton, B., Chen, Y., Ke, X., Liu, S., and Zhao, L. (2019). Indoor navigation system using the fetch robot. Proceedings of the International Conference on Intelligent Robotics and Applications, Springer.","DOI":"10.1007\/978-3-030-27538-9_59"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Kulkarni, S., Singh, S., Balakrishnan, D., Sharma, S., Devunuri, S., and Korlapati, S.C.R. (2022). CrackSeg9k: A Collection and Benchmark for Crack Segmentation Datasets and Frameworks. arXiv.","DOI":"10.1007\/978-3-031-25082-8_12"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., and Kalinin, A.A. (2020). Albumentations: Fast and Flexible Image Augmentations. Information, 11.","DOI":"10.3390\/info11020125"},{"key":"ref_49","unstructured":"Lee, D. (2026, January 07). Real-Time Automated Mobile Robotic Crack Detection System_Gazebo Simulation. Available online: https:\/\/youtu.be\/TNtV2WLi4f8."},{"key":"ref_50","unstructured":"Lee, D. (2026, January 07). Real-Time Automated Mobile Robotic Crack Detection System_Floor Experiment_Lab-Controlled. Available online: https:\/\/youtu.be\/tSlldbQ8O78."},{"key":"ref_51","unstructured":"Lee, D. (2026, January 07). Real-Time Automated Mobile Robotic Crack Detection System_Wall Experiment_Lab-Controlled. Available online: https:\/\/youtu.be\/2fDa-pLnY50."},{"key":"ref_52","unstructured":"Lee, D. (2026, January 07). Real-Time Automated Mobile Robotic Crack Detection System_2nd Floor in ERB at GSU. Available online: https:\/\/youtu.be\/S_Qddbrxurk."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Ogun, E., Kim, J., and Lee, D. (2025). Advanced Crack Detection in Building Structures Using Pix2Pix and U-Net Architectures. Proceedings of the Smart Materials, Adaptive Structures and Intelligent Systems, American Society of Mechanical Engineers.","DOI":"10.1115\/SMASIS2025-166103"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Noh, J., Jang, J., Jo, J., and Yang, H. (2025). Crack Segmentation Using U-Net and Transformer Combined Model. Appl. Sci., 15.","DOI":"10.3390\/app151910737"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Li, Y., Ma, R., Liu, H., and Cheng, G. (2023). Hrsegnet: Real-time high-resolution neural network with semantic guidance for crack segmentation. arXiv.","DOI":"10.1016\/j.autcon.2023.105112"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Zhang, T., Qin, L., Zou, Q., Zhang, L., Wang, R., and Zhang, H. (2024). CrackScopeNet: A Lightweight Neural Network for Rapid Crack Detection on Resource-Constrained Drone Platforms. Drones, 8.","DOI":"10.20944\/preprints202407.0705.v2"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1111\/mice.12412","article-title":"Automatic Pixel-Level Crack Detection and Measurement Using Fully Convolutional Network","volume":"33","author":"Yang","year":"2018","journal-title":"Comput. Aided Civ. Infrastruct. Eng."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/530\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T06:14:31Z","timestamp":1768544071000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/530"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,13]]},"references-count":57,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26020530"],"URL":"https:\/\/doi.org\/10.3390\/s26020530","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,13]]}}}