Pub Date : 2026-02-01Epub Date: 2026-01-07DOI: 10.1016/j.autcon.2025.106746
Martin Urbieta , Matias Urbieta , Guillermo Burriel
BIM solutions require a digital model as a foundation to optimize processes such as maintenance, infrastructure renovation, or demolition. However, a vast number of analog building plans are archived by public entities managing urban development, and manually converting these plans into digital models, which is prohibitively expensive. To address this gap, the paper introduces an approach for organizations who need to convert large datasets of legacy electrical floorplans into a BIM. The approach leverages a Machine Learning model for instance segmentation to detect electrical features, and the line-segment detection model DeepLSD for extracting cable traces. To support model training, a new dataset, referred as IPVBA-ELEC, is provided. The approach assembles circuits by establishing semantic relationships between circuit components and wires, and store them in an IFC file. Case studies were evaluated using quantitative and qualitative techniques yielding promising results and encouraging further research of additional MEP domains.
{"title":"AI-driven extraction of electrical circuits from floorplans for BIM","authors":"Martin Urbieta , Matias Urbieta , Guillermo Burriel","doi":"10.1016/j.autcon.2025.106746","DOIUrl":"10.1016/j.autcon.2025.106746","url":null,"abstract":"<div><div>BIM solutions require a digital model as a foundation to optimize processes such as maintenance, infrastructure renovation, or demolition. However, a vast number of analog building plans are archived by public entities managing urban development, and manually converting these plans into digital models, which is prohibitively expensive. To address this gap, the paper introduces an approach for organizations who need to convert large datasets of legacy electrical floorplans into a BIM. The approach leverages a Machine Learning model for instance segmentation to detect electrical features, and the line-segment detection model DeepLSD for extracting cable traces. To support model training, a new dataset, referred as IPVBA-ELEC, is provided. The approach assembles circuits by establishing semantic relationships between circuit components and wires, and store them in an IFC file. Case studies were evaluated using quantitative and qualitative techniques yielding promising results and encouraging further research of additional MEP domains.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106746"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2025-12-30DOI: 10.1016/j.autcon.2025.106742
Junhyung Cho , Mingyu Shin , Joongheon Kim , Soyi Jung
Autonomous excavation systems face fundamental challenges balancing computational tractability with operational sophistication. This paper presents the collaborative learning for excavation framework (CLEF), resolving this trade-off through strategic decomposition: separating high-level planning from low-level execution while maintaining collaborative optimization. The framework’s key contributions include a bidirectional information flow between specialized modules consisting of reinforcement learning for strategic planning using polar coordinates, and attention-enhanced generative adversarial imitation learning (A-GAIL) with multi-head attention capturing phase-specific temporal dependencies. Unlike monolithic approaches suffering computational intractability, CLEF enables module specialization while coordinating through shared representations. Planning decisions condition trajectory generation while execution outcomes update environmental models, creating adaptive behavior without manual tuning. Validation demonstrates 90.8% success rate compared to 71.1% for monolithic approaches, with trajectory generation achieving 91.3% completion confirming superior performance essential for construction automation.
{"title":"Collaborative learning architecture for autonomous excavator planning and execution","authors":"Junhyung Cho , Mingyu Shin , Joongheon Kim , Soyi Jung","doi":"10.1016/j.autcon.2025.106742","DOIUrl":"10.1016/j.autcon.2025.106742","url":null,"abstract":"<div><div>Autonomous excavation systems face fundamental challenges balancing computational tractability with operational sophistication. This paper presents the collaborative learning for excavation framework (CLEF), resolving this trade-off through strategic decomposition: separating high-level planning from low-level execution while maintaining collaborative optimization. The framework’s key contributions include a bidirectional information flow between specialized modules consisting of reinforcement learning for strategic planning using polar coordinates, and attention-enhanced generative adversarial imitation learning (A-GAIL) with multi-head attention capturing phase-specific temporal dependencies. Unlike monolithic approaches suffering computational intractability, CLEF enables module specialization while coordinating through shared representations. Planning decisions condition trajectory generation while execution outcomes update environmental models, creating adaptive behavior without manual tuning. Validation demonstrates 90.8% success rate compared to 71.1% for monolithic approaches, with trajectory generation achieving 91.3% completion confirming superior performance essential for construction automation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106742"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145880900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-12DOI: 10.1016/j.autcon.2026.106763
Wei Tu , Yu Gu , Ruizhe Chen , Xing Zhang , Jiasong Zhu , Chisheng Wang , Qingquan Li
Urban sewer pipelines are prone to diverse faults, such as cracks, erosion, and root intrusion. Effective and efficient inspection methods are essential for large-scale urban sewer pipe networks. This paper presented a collaborative inspection approach to inspect urban sewer pipes, which integrates robotic pipe capsules (RPCs) with lightweight deep learning and spatial optimization. A bi-level network is built to represent diverse movements of workers and the RPCs and their collaboration. A specialized lightweight deep neural network is designed to identify faults with images captured by PRC in real time. The worker and RPC routes are spatially optimized with hybrid meta-heuristics. An experiment in Shenzhen, China, demonstrated that it achieves a balanced accuracy of 83.43% with 7.64 frames per second, which outperforms baseline methods. The presented method provides an alternative approach for large-scale urban sewer pipe networks.
{"title":"Collaborative inspection for large-scale urban sewer pipe networks by coupling multiple robotic pipe capsules and spatial optimization","authors":"Wei Tu , Yu Gu , Ruizhe Chen , Xing Zhang , Jiasong Zhu , Chisheng Wang , Qingquan Li","doi":"10.1016/j.autcon.2026.106763","DOIUrl":"10.1016/j.autcon.2026.106763","url":null,"abstract":"<div><div>Urban sewer pipelines are prone to diverse faults, such as cracks, erosion, and root intrusion. Effective and efficient inspection methods are essential for large-scale urban sewer pipe networks. This paper presented a collaborative inspection approach to inspect urban sewer pipes, which integrates robotic pipe capsules (RPCs) with lightweight deep learning and spatial optimization. A bi-level network is built to represent diverse movements of workers and the RPCs and their collaboration. A specialized lightweight deep neural network is designed to identify faults with images captured by PRC in real time. The worker and RPC routes are spatially optimized with hybrid meta-heuristics. An experiment in Shenzhen, China, demonstrated that it achieves a balanced accuracy of 83.43% with 7.64 frames per second, which outperforms baseline methods. The presented method provides an alternative approach for large-scale urban sewer pipe networks.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106763"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145956563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2025-12-22DOI: 10.1016/j.autcon.2025.106720
Yongqing Jiang , Jianze Wang , Xinyi Shen , Kaoshan Dai , Qingzi Ge
Rapid and accurate damage assessment of structures is critical for post-earthquake recovery and emergency response. Current evaluations are heavily reliant on on-site visual inspections conducted by engineering experts, which are time-consuming and resource-intensive. To this end, the large vision-language model (VLM) for multitask structural damage assessment chatbot (MT-SDAChat) is developed in this paper. It can perform both image-level and regional-level inference analysis, accurately locating and providing specific information about various structural components and damage locations. With the MT-SDAChat, a two-stage automated assessment framework that transitions from a global perspective to a component-specific perspective is proposed. A dataset containing 3348 image-text pairs of seismic structural damage with multiple attributes has been constructed. Experimental results show that MT-SDAChat performs well in multitask evaluation. It achieves a question-and-answer accuracy of 82.92 % and a localization accuracy of 78.6 %. These results highlight its strong zero-shot capability across various damage assessments in building construction.
{"title":"Multitask unified large vision-language model for post-earthquake structural damage assessment of buildings","authors":"Yongqing Jiang , Jianze Wang , Xinyi Shen , Kaoshan Dai , Qingzi Ge","doi":"10.1016/j.autcon.2025.106720","DOIUrl":"10.1016/j.autcon.2025.106720","url":null,"abstract":"<div><div>Rapid and accurate damage assessment of structures is critical for post-earthquake recovery and emergency response. Current evaluations are heavily reliant on on-site visual inspections conducted by engineering experts, which are time-consuming and resource-intensive. To this end, the large vision-language model (VLM) for multitask structural damage assessment chatbot (MT-SDAChat) is developed in this paper. It can perform both image-level and regional-level inference analysis, accurately locating and providing specific information about various structural components and damage locations. With the MT-SDAChat, a two-stage automated assessment framework that transitions from a global perspective to a component-specific perspective is proposed. A dataset containing 3348 image-text pairs of seismic structural damage with multiple attributes has been constructed. Experimental results show that MT-SDAChat performs well in multitask evaluation. It achieves a question-and-answer accuracy of 82.92 % and a localization accuracy of 78.6 %. These results highlight its strong zero-shot capability across various damage assessments in building construction.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106720"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145813790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-13DOI: 10.1016/j.autcon.2026.106778
Soheila Kookalani , Stephen Green , Peihang Luo , Hamidreza Alavi , Erika Parn , Zhaojie Sun , Ioannis Brilakis
Digital Twin technologies are increasingly used in infrastructure and the built environment to create dynamic, data-driven models of physical assets and processes. This review analyses recent advancements across sectors such as tunnels, bridges, roads, buildings, construction management, and urban planning, covering all life-cycle phases from design to operation. Integrating Digital Twins with Building Information Modelling, Internet of Things sensors, and Artificial Intelligence enhances real-time monitoring, decision-making, and asset performance. Key methods include monitoring, modelling, and simulation, which improve resource use and proactive maintenance. However, adoption faces challenges such as poor data interoperability, high costs, and technical complexity in merging multiple technologies. Ethical and governance issues around data privacy and security also persist. The review identifies future research needs in improving interoperability, expanding predictive analytics, and assessing large-scale impacts. It highlights Digital Twins' potential to improve resilience, efficiency, and sustainability, stressing the need for policy support and stakeholder collaboration.
{"title":"Mapping digital twin applications in infrastructure and the built environment across research types, methods, sectors, phases, and scales","authors":"Soheila Kookalani , Stephen Green , Peihang Luo , Hamidreza Alavi , Erika Parn , Zhaojie Sun , Ioannis Brilakis","doi":"10.1016/j.autcon.2026.106778","DOIUrl":"10.1016/j.autcon.2026.106778","url":null,"abstract":"<div><div>Digital Twin technologies are increasingly used in infrastructure and the built environment to create dynamic, data-driven models of physical assets and processes. This review analyses recent advancements across sectors such as tunnels, bridges, roads, buildings, construction management, and urban planning, covering all life-cycle phases from design to operation. Integrating Digital Twins with Building Information Modelling, Internet of Things sensors, and Artificial Intelligence enhances real-time monitoring, decision-making, and asset performance. Key methods include monitoring, modelling, and simulation, which improve resource use and proactive maintenance. However, adoption faces challenges such as poor data interoperability, high costs, and technical complexity in merging multiple technologies. Ethical and governance issues around data privacy and security also persist. The review identifies future research needs in improving interoperability, expanding predictive analytics, and assessing large-scale impacts. It highlights Digital Twins' potential to improve resilience, efficiency, and sustainability, stressing the need for policy support and stakeholder collaboration.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106778"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145962000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2025-12-14DOI: 10.1016/j.autcon.2025.106715
Hang Zhao , Vahidreza Gharehbaghi , Caroline Bennett , Rémy D. Lequesne , Jian Li
This paper presents PIL3D, an automated pixel-level image localization framework for maintaining up-to-date 3D digital twins of large-scale civil infrastructure, with a focus on dam structures. Unlike conventional 3D model updating approaches that require extensive manual data acquisition and labor-intensive processing, PIL3D automatically predicts the 3D coordinates of every pixel in an input image relative to an existing model, enabling fully automated dense pixel-to-point correspondences. Experimental validation on a real-world dam case demonstrates centimeter-level localization accuracy, significantly reducing manual intervention, data collection requirements, and computational demand. By integrating PIL3D into digital twin workflows, infrastructure inspection, monitoring, and maintenance can be streamlined into a continuous, automated process, advancing the state of automation in construction and asset management.
{"title":"Pixel-level image localization for updating 3D digital twins of dams using frequency convolutional networks","authors":"Hang Zhao , Vahidreza Gharehbaghi , Caroline Bennett , Rémy D. Lequesne , Jian Li","doi":"10.1016/j.autcon.2025.106715","DOIUrl":"10.1016/j.autcon.2025.106715","url":null,"abstract":"<div><div>This paper presents PIL3D, an automated pixel-level image localization framework for maintaining up-to-date 3D digital twins of large-scale civil infrastructure, with a focus on dam structures. Unlike conventional 3D model updating approaches that require extensive manual data acquisition and labor-intensive processing, PIL3D automatically predicts the 3D coordinates of every pixel in an input image relative to an existing model, enabling fully automated dense pixel-to-point correspondences. Experimental validation on a real-world dam case demonstrates centimeter-level localization accuracy, significantly reducing manual intervention, data collection requirements, and computational demand. By integrating PIL3D into digital twin workflows, infrastructure inspection, monitoring, and maintenance can be streamlined into a continuous, automated process, advancing the state of automation in construction and asset management.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106715"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145759776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2025-12-20DOI: 10.1016/j.autcon.2025.106736
Chenlong Feng , Quan Zhang , Jixin Wang , Xinxing Liu , Yuying Shen , Qingzheng Jia , Jiazhi Zhao
Excavator trajectory planning remains challenging due to dependence on expert skill, changing tasks, and complex environments. This paper integrates global probabilistic modeling of expert demonstrations with sampling-based optimization to enable flexible, efficient, and safe autonomous operation. A Global Modulated Movement Primitive (GMMP) model captures global evolution of expert demonstration trajectories in SE(3) space, the 3D rigid-body pose space that combines orientation and translation. A Bayesian update supports efficient task generalization by adjusting new via points. The workspace density of excavator is introduced to enable the transfer of GMMP across different excavator without retraining. A Guided Model Predictive Path Integral (GMPPI) method with SE(3)-consistency cost optimizes GMMP generated trajectories via sampling, handling obstacle avoidance and execution constraints. The method was validated on a full-size excavator and a scaled platform. Results show improved trajectory similarity, execution efficiency, and task adaptability, indicating strong practicality.
{"title":"Excavator trajectory planning via global probabilistic learning from expert demonstrations","authors":"Chenlong Feng , Quan Zhang , Jixin Wang , Xinxing Liu , Yuying Shen , Qingzheng Jia , Jiazhi Zhao","doi":"10.1016/j.autcon.2025.106736","DOIUrl":"10.1016/j.autcon.2025.106736","url":null,"abstract":"<div><div>Excavator trajectory planning remains challenging due to dependence on expert skill, changing tasks, and complex environments. This paper integrates global probabilistic modeling of expert demonstrations with sampling-based optimization to enable flexible, efficient, and safe autonomous operation. A Global Modulated Movement Primitive (GMMP) model captures global evolution of expert demonstration trajectories in SE(3) space, the 3D rigid-body pose space that combines orientation and translation. A Bayesian update supports efficient task generalization by adjusting new via points. The workspace density of excavator is introduced to enable the transfer of GMMP across different excavator without retraining. A Guided Model Predictive Path Integral (GMPPI) method with SE(3)-consistency cost optimizes GMMP generated trajectories via sampling, handling obstacle avoidance and execution constraints. The method was validated on a full-size excavator and a scaled platform. Results show improved trajectory similarity, execution efficiency, and task adaptability, indicating strong practicality.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106736"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2025-12-15DOI: 10.1016/j.autcon.2025.106719
Siheon Joo, Seokhwan Kim, Hongjo Kim
Structural crack analysis is vital for infrastructure safety, but existing segmentation models often miss fine cracks due to spectral bias in deep networks. This especially affects thin cracks, which are frequently underrepresented. This paper presents FACS-Net, a Frequency-Aware Crack Segmentation Network with Crack Topology Loss (CT-Loss), to mitigate spectral bias and enhance crack-specific representations. FACS-Net employs frequency-aware attention for decoding, while CT-Loss explicitly incorporates boundary accuracy and structural continuity into the learning objective. Given the high edge-to-area ratio of thin cracks, the proposed approach ensures accurate localization without sacrificing topological coherence. Evaluation on CrackVision12K shows that FACS-Net significantly improves detection of thin cracks (width 2 px), outperforming Hybrid-Segmentor by 0.306 IoU and 0.360 CTS. Overall, FACS-Net achieves state-of-the-art performance with 0.663 IoU and 0.651 CTS, demonstrating precise segmentation and robust structural preservation.
{"title":"Frequency-aware crack segmentation network (FACS-net) and crack topology loss (CT-loss) for thin cracks","authors":"Siheon Joo, Seokhwan Kim, Hongjo Kim","doi":"10.1016/j.autcon.2025.106719","DOIUrl":"10.1016/j.autcon.2025.106719","url":null,"abstract":"<div><div>Structural crack analysis is vital for infrastructure safety, but existing segmentation models often miss fine cracks due to spectral bias in deep networks. This especially affects thin cracks, which are frequently underrepresented. This paper presents FACS-Net, a Frequency-Aware Crack Segmentation Network with Crack Topology Loss (CT-Loss), to mitigate spectral bias and enhance crack-specific representations. FACS-Net employs frequency-aware attention for decoding, while CT-Loss explicitly incorporates boundary accuracy and structural continuity into the learning objective. Given the high edge-to-area ratio of thin cracks, the proposed approach ensures accurate localization without sacrificing topological coherence. Evaluation on CrackVision12K shows that FACS-Net significantly improves detection of thin cracks (width<span><math><mo>≤</mo></math></span> 2 px), outperforming Hybrid-Segmentor by 0.306 IoU and 0.360 CTS. Overall, FACS-Net achieves state-of-the-art performance with 0.663 IoU and 0.651 CTS, demonstrating precise segmentation and robust structural preservation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106719"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145787865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-06DOI: 10.1016/j.autcon.2025.106753
Tao Wu , Shitong Hou , Zhishen Wu , Xiaoyuan He , Gang Wu
Quantitative measurement of apparent defects using underwater vision-based techniques is essential for structural inspection of submerged bridge components. However, measurement accuracy is greatly limited by nonlinear imaging distortions caused by multi-medium refraction and viewport deformation under hydrostatic pressure. To overcome these challenges, this paper introduces a multi-refraction correction model that accounts for refractive interface deformation. A nonlinear underwater imaging framework is established by integrating a spatial coordinate transformation-based calibration method with deformation analysis of the viewport. The feasibility and accuracy of the proposed approach are validated through underwater checkerboard corner-detection experiments. Compared with traditional multi-plane refraction correction method, the proposed model enhances measurement precision by more than 40 %. Additional experiments on submerged bridge pier components show that the measurement errors for apparent defect dimensions consistently remain below 5 %, highlighting the strong potential of the method for practical implementation in underwater visual inspection of bridge infrastructure.
{"title":"Underwater defect measurement for bridge piers via non-planar refraction correction","authors":"Tao Wu , Shitong Hou , Zhishen Wu , Xiaoyuan He , Gang Wu","doi":"10.1016/j.autcon.2025.106753","DOIUrl":"10.1016/j.autcon.2025.106753","url":null,"abstract":"<div><div>Quantitative measurement of apparent defects using underwater vision-based techniques is essential for structural inspection of submerged bridge components. However, measurement accuracy is greatly limited by nonlinear imaging distortions caused by multi-medium refraction and viewport deformation under hydrostatic pressure. To overcome these challenges, this paper introduces a multi-refraction correction model that accounts for refractive interface deformation. A nonlinear underwater imaging framework is established by integrating a spatial coordinate transformation-based calibration method with deformation analysis of the viewport. The feasibility and accuracy of the proposed approach are validated through underwater checkerboard corner-detection experiments. Compared with traditional multi-plane refraction correction method, the proposed model enhances measurement precision by more than 40 %. Additional experiments on submerged bridge pier components show that the measurement errors for apparent defect dimensions consistently remain below 5 %, highlighting the strong potential of the method for practical implementation in underwater visual inspection of bridge infrastructure.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106753"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145903162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01Epub Date: 2026-01-05DOI: 10.1016/j.autcon.2026.106762
Pinsheng Duan , Xuehai Fu , Jinxin Hu , Jianliang Zhou , Ping Guo
Construction sites are dynamic, complex, high-risk environments, where Unmanned Aerial Vehicles (UAVs) are vital for enhancing safety inspection efficiency. As large-scale dynamic obstacles, tower cranes can interfere with effective UAV inspection paths. This paper proposes a safety inspection path planning method under the spatiotemporal interference of multiple tower cranes. First, a 3D model of the construction site is reconstructed, and inspection viewpoints for UAV flights are generated by optimizing safety inspection strategies. Then, a hierarchical path planning framework is established: the lower-level planner strictly enforces real-time safety obstacle avoidance strategies, while the higher-level planner focuses on global planning to meet inspection requirements. Finally, both simulation and real project studies are conducted to verify the feasibility of the method. Results from the real project show that the effective coverage area is increased by 39.01 % compared with traditional methods. This paper provides theoretical and practical support for UAV-assisted safety inspections in construction.
{"title":"Path planning for UAV-based construction safety inspection under spatiotemporal interference from tower cranes","authors":"Pinsheng Duan , Xuehai Fu , Jinxin Hu , Jianliang Zhou , Ping Guo","doi":"10.1016/j.autcon.2026.106762","DOIUrl":"10.1016/j.autcon.2026.106762","url":null,"abstract":"<div><div>Construction sites are dynamic, complex, high-risk environments, where Unmanned Aerial Vehicles (UAVs) are vital for enhancing safety inspection efficiency. As large-scale dynamic obstacles, tower cranes can interfere with effective UAV inspection paths. This paper proposes a safety inspection path planning method under the spatiotemporal interference of multiple tower cranes. First, a 3D model of the construction site is reconstructed, and inspection viewpoints for UAV flights are generated by optimizing safety inspection strategies. Then, a hierarchical path planning framework is established: the lower-level planner strictly enforces real-time safety obstacle avoidance strategies, while the higher-level planner focuses on global planning to meet inspection requirements. Finally, both simulation and real project studies are conducted to verify the feasibility of the method. Results from the real project show that the effective coverage area is increased by 39.01 % compared with traditional methods. This paper provides theoretical and practical support for UAV-assisted safety inspections in construction.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106762"},"PeriodicalIF":11.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145903172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号