Automation in Construction最新文献

英文中文

Distributed acoustic sensing-based real-time monitoring of far-field cracks in reinforced concrete bridge decks 基于分布式声传感的钢筋混凝土桥面远场裂缝实时监测

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-06 DOI: 10.1016/j.autcon.2026.106821

Yao Wang, Yi Bao

Monitoring cracks is critical for the safety and efficiency of the construction and operation of civil infrastructure. Distributed fiber optic sensors offer advantages for crack monitoring, but their applications are largely limited to near-field cracks. This paper presents an approach for in situ, real-time monitoring of far-field cracks using distributed acoustic sensing. The approach is developed through multi-physics modeling of a representative concrete highway bridge. The influence of key configuration parameters, including gauge length, channel spacing, and sampling rate, is evaluated for crack detection and localization. Results show that cracks located up to 6 m from a fiber optic cable are detected and localized with an average error of 0.94 m across 60 tests with varying crack scenarios and configurations. A cost-benefit analysis compares the proposed approach with state-of-the-art methods based on acoustic emission and distributed fiber optic sensing, demonstrating its benefits for far-field crack monitoring.

裂缝监测对民用基础设施建设和运行的安全性和效率至关重要。分布式光纤传感器为裂缝监测提供了优势，但其应用主要局限于近场裂缝。本文提出了一种利用分布式声传感技术对远场裂缝进行现场实时监测的方法。该方法是通过对一座具有代表性的混凝土公路桥进行多物理场建模而发展起来的。关键配置参数的影响，包括测量长度，通道间距，采样率，评估裂纹检测和定位。结果表明，在60次测试中，在不同的裂缝场景和结构下，检测到并定位了距离光缆6 m的裂缝，平均误差为0.94 m。成本效益分析将该方法与基于声发射和分布式光纤传感的最新方法进行了比较，证明了其在远场裂纹监测方面的优势。

引用次数: 0

Fusing enhanced YOLO and knowledge graph-based large language models for automatic risk perception in tower crane operations 融合增强的YOLO和基于知识图的大型语言模型进行塔机作业风险自动感知

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-05 DOI: 10.1016/j.autcon.2026.106823

Lingxiao Wang , Jingfeng Yuan , Shu Su , Hongxing Ding , Yu Bai , Miroslaw J. Skibniewski

Tower crane operations in construction are inherently hazardous due to complex and dynamic site environments. Enhancing operators' perceptual and cognitive capabilities is essential for ensuring safety and improving situational awareness. This paper presents an integrated framework that combines an improved YOLOv8 model with a Knowledge Graph (KG)-enhanced large language model to achieve proactive and intelligent safety management. The improved YOLOv8 incorporates attention-based optimization to improve detection accuracy for small targets in tower crane perspectives. A domain-specific safety KG is constructed to represent critical entities, relationships, and operational contexts, and is aligned with a fine-tuned GPT model, enabling semantic reasoning and context-aware hazard interpretation. The integrated system links visual perception with structured knowledge reasoning to provide real-time and interpretable safety feedback. This approach enhances the perception, understanding, and decision-making capabilities of tower crane operators, transforming safety management from reactive monitoring to proactive and intelligent control in complex construction environments.

由于施工现场环境复杂多变，塔式起重机作业本身就具有危险性。提高操作员的感知和认知能力对于确保安全和提高态势感知至关重要。本文提出了一个集成框架，将改进的YOLOv8模型与知识图（KG）增强的大型语言模型相结合，实现主动智能安全管理。改进的YOLOv8集成了基于注意力的优化，以提高塔吊视角下对小目标的检测精度。构建一个特定于领域的安全KG来表示关键实体、关系和操作上下文，并与精细调整的GPT模型保持一致，支持语义推理和上下文感知的危险解释。集成系统将视觉感知与结构化知识推理联系起来，提供实时和可解释的安全反馈。该方法增强了塔机操作员的感知、理解和决策能力，将复杂施工环境中的安全管理从被动监控转变为主动智能控制。

{"title":"Fusing enhanced YOLO and knowledge graph-based large language models for automatic risk perception in tower crane operations","authors":"Lingxiao Wang , Jingfeng Yuan , Shu Su , Hongxing Ding , Yu Bai , Miroslaw J. Skibniewski","doi":"10.1016/j.autcon.2026.106823","DOIUrl":"10.1016/j.autcon.2026.106823","url":null,"abstract":"<div><div>Tower crane operations in construction are inherently hazardous due to complex and dynamic site environments. Enhancing operators' perceptual and cognitive capabilities is essential for ensuring safety and improving situational awareness. This paper presents an integrated framework that combines an improved YOLOv8 model with a Knowledge Graph (KG)-enhanced large language model to achieve proactive and intelligent safety management. The improved YOLOv8 incorporates attention-based optimization to improve detection accuracy for small targets in tower crane perspectives. A domain-specific safety KG is constructed to represent critical entities, relationships, and operational contexts, and is aligned with a fine-tuned GPT model, enabling semantic reasoning and context-aware hazard interpretation. The integrated system links visual perception with structured knowledge reasoning to provide real-time and interpretable safety feedback. This approach enhances the perception, understanding, and decision-making capabilities of tower crane operators, transforming safety management from reactive monitoring to proactive and intelligent control in complex construction environments.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106823"},"PeriodicalIF":11.5,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134693","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}

引用次数: 0

Inertia effects matching for optimal attitude control in synchronous TBM considering human behavior 考虑人行为的同步TBM最优姿态控制惯性效应匹配

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-04 DOI: 10.1016/j.autcon.2026.106798

Yongsheng Li , Limao Zhang , Qixiang Yan , Jianjun Qin , Zhanpeng Luo

The paper addresses the general problem of unreliable excavation in synchronous tunnel boring machines (S-TBMs) caused by inertia effects and time-delay phenomenon. The specific research question is how to achieve robust inertia matching those accounts for both equipment dynamics and human operator response behavior. A Gaussian mixture model (GMM) and an encoder-decoder framework (EDF) are proposed to estimate the driver and S-TBM inertial response time. A dynamic expression of the S-TBM excavation system is formulated, taking into account both human response time and equipment inertia effects. The results demonstrate that the proposed method accurately fits driver response time, achieves high-precision estimation of system inertia, and significantly reduces attitude errors by over 86% compared to non-matched control. An important contribution of this study is the integration of human behavioral inertia into the field of engineering equipment control, providing theoretical support for human-machine collaboration and real-time sharing control.

本文研究了同步隧道掘进机由于惯性效应和时滞现象引起的掘进不可靠问题。具体的研究问题是如何实现鲁棒惯性匹配那些考虑设备动力学和人类操作员响应行为的因素。提出了高斯混合模型（GMM）和编码器-解码器框架（EDF）来估计驱动和S-TBM惯性响应时间。建立了考虑人的响应时间和设备惯性效应的S-TBM开挖系统的动态表达式。结果表明，该方法能准确拟合驾驶员响应时间，实现系统惯性的高精度估计，与非匹配控制相比，姿态误差显著降低86%以上。本研究的一个重要贡献是将人的行为惯性整合到工程设备控制领域，为人机协作和实时共享控制提供理论支持。

{"title":"Inertia effects matching for optimal attitude control in synchronous TBM considering human behavior","authors":"Yongsheng Li , Limao Zhang , Qixiang Yan , Jianjun Qin , Zhanpeng Luo","doi":"10.1016/j.autcon.2026.106798","DOIUrl":"10.1016/j.autcon.2026.106798","url":null,"abstract":"<div><div>The paper addresses the general problem of unreliable excavation in synchronous tunnel boring machines (S-TBMs) caused by inertia effects and time-delay phenomenon. The specific research question is how to achieve robust inertia matching those accounts for both equipment dynamics and human operator response behavior. A Gaussian mixture model (GMM) and an encoder-decoder framework (EDF) are proposed to estimate the driver and S-TBM inertial response time. A dynamic expression of the S-TBM excavation system is formulated, taking into account both human response time and equipment inertia effects. The results demonstrate that the proposed method accurately fits driver response time, achieves high-precision estimation of system inertia, and significantly reduces attitude errors by over 86% compared to non-matched control. An important contribution of this study is the integration of human behavioral inertia into the field of engineering equipment control, providing theoretical support for human-machine collaboration and real-time sharing control.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106798"},"PeriodicalIF":11.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146185055","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}

引用次数: 0

Computational Design Methods for geometry-driven upcycling of found objects in construction 建筑中发现物几何驱动升级回收的计算设计方法

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-04 DOI: 10.1016/j.autcon.2026.106803

Qiming Sun , Dominik Reisach , Silke Langenberg , Benjamin Dillenburger

Computational Design Methods (CDMs) have increasingly supported the use of Found Objects (FOs) for circular construction. These methods automate the geometric assignment of FOs to a target design, yet a comprehensive overview is lacking. In this context, this paper systematically reviews 142 publications on CDMs for upcycling FOs in construction. It categorizes existing workflows and identifies six key CDMs based on assignment logic and four geometric FO types. The review serves as a roadmap for future research and practical applications, aiding architects and engineers in informed decision-making. It emphasizes the potential of utilizing FOs’ inherent geometry as design drivers for economical and aesthetic architectural solutions. This paper also identifies challenges in scaling CDMs from prototypes to practical applications, such as structural performance and integration with existing workflows. Future research directions include developing AI-based methods, automating construction processes using CDMs, and advocating for sensitivity analysis to assess adaptability across design scenarios.

计算设计方法（CDMs）越来越多地支持在圆形建筑中使用发现对象（FOs）。这些方法自动地将fo分配到目标设计中，但缺乏全面的概述。在此背景下，本文系统地回顾了142篇关于清洁发展机制在建筑工程中升级利用的文献。它对现有工作流进行了分类，并根据分配逻辑和四种几何FO类型确定了六个关键cdm。该综述为未来的研究和实际应用提供了路线图，帮助建筑师和工程师做出明智的决策。它强调了利用FOs固有的几何形状作为经济和美学建筑解决方案的设计驱动力的潜力。本文还确定了将cdm从原型扩展到实际应用的挑战，例如结构性能和与现有工作流的集成。未来的研究方向包括开发基于人工智能的方法，使用cdm自动化施工过程，以及倡导敏感性分析以评估设计方案的适应性。

{"title":"Computational Design Methods for geometry-driven upcycling of found objects in construction","authors":"Qiming Sun , Dominik Reisach , Silke Langenberg , Benjamin Dillenburger","doi":"10.1016/j.autcon.2026.106803","DOIUrl":"10.1016/j.autcon.2026.106803","url":null,"abstract":"<div><div>Computational Design Methods (CDMs) have increasingly supported the use of Found Objects (FOs) for circular construction. These methods automate the geometric assignment of FOs to a target design, yet a comprehensive overview is lacking. In this context, this paper systematically reviews 142 publications on CDMs for upcycling FOs in construction. It categorizes existing workflows and identifies six key CDMs based on assignment logic and four geometric FO types. The review serves as a roadmap for future research and practical applications, aiding architects and engineers in informed decision-making. It emphasizes the potential of utilizing FOs’ inherent geometry as design drivers for economical and aesthetic architectural solutions. This paper also identifies challenges in scaling CDMs from prototypes to practical applications, such as structural performance and integration with existing workflows. Future research directions include developing AI-based methods, automating construction processes using CDMs, and advocating for sensitivity analysis to assess adaptability across design scenarios.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106803"},"PeriodicalIF":11.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146185056","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}

引用次数: 0

Deep learning-based computer vision methods for shield tunnel defect recognition 基于深度学习的盾构隧道缺陷识别方法

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-04 DOI: 10.1016/j.autcon.2026.106807

Ya-Dong Xue , Fei Jia , Wei Luo , Dong-Mei Zhang , Jie Liu , Yong-Fa Guo

With the rapid expansion of large-scale shield tunnel operations, deep learning has been extensively studied for automated defect recognition. This paper provides a comprehensive review of recent research in deep learning-based methods for tunnel defect recognition, organized into three key stages: dataset establishment, model development, and practical implementation. The review first details the acquisition and preprocessing of tunnel lining images obtained from various inspection equipment, followed by the establishment of defect datasets. It then provides a systematic overview of commonly used deep learning models for defect recognition, with a focus on three primary areas: defect detection, semantic, and instance segmentation, summarizing key innovations within each domain. Based on this analysis, current challenges are identified and future research directions are discussed for each stage. This review aims to promote the practical application of deep learning in tunnel engineering and to support the development of predictive and intelligent maintenance for shield tunnels.

随着大规模盾构隧道工程的迅速发展，深度学习在缺陷自动识别方面得到了广泛的研究。本文对基于深度学习的隧道缺陷识别方法的最新研究进行了全面综述，分为三个关键阶段：数据集建立、模型开发和实际实施。本文首先详细介绍了从各种检测设备获得的隧道衬砌图像的获取和预处理，然后建立了缺陷数据集。然后，它提供了一个用于缺陷识别的常用深度学习模型的系统概述，重点放在三个主要领域：缺陷检测、语义和实例分割，总结了每个领域内的关键创新。在此基础上，确定了当前面临的挑战，并对每个阶段的未来研究方向进行了讨论。本文综述旨在促进深度学习在隧道工程中的实际应用，支持盾构隧道预测和智能维修的发展。

{"title":"Deep learning-based computer vision methods for shield tunnel defect recognition","authors":"Ya-Dong Xue , Fei Jia , Wei Luo , Dong-Mei Zhang , Jie Liu , Yong-Fa Guo","doi":"10.1016/j.autcon.2026.106807","DOIUrl":"10.1016/j.autcon.2026.106807","url":null,"abstract":"<div><div>With the rapid expansion of large-scale shield tunnel operations, deep learning has been extensively studied for automated defect recognition. This paper provides a comprehensive review of recent research in deep learning-based methods for tunnel defect recognition, organized into three key stages: dataset establishment, model development, and practical implementation. The review first details the acquisition and preprocessing of tunnel lining images obtained from various inspection equipment, followed by the establishment of defect datasets. It then provides a systematic overview of commonly used deep learning models for defect recognition, with a focus on three primary areas: defect detection, semantic, and instance segmentation, summarizing key innovations within each domain. Based on this analysis, current challenges are identified and future research directions are discussed for each stage. This review aims to promote the practical application of deep learning in tunnel engineering and to support the development of predictive and intelligent maintenance for shield tunnels.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106807"},"PeriodicalIF":11.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146185058","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}

引用次数: 0

From geometry to graph: Automation of building performance modeling via convex graph encoding 从几何到图形：通过凸图编码实现建筑性能建模的自动化

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-04 DOI: 10.1016/j.autcon.2026.106815

Yihui Li , Jun Xiao , Hao Zhou , Borong Lin

Early-stage design decisions strongly influence a building’s lifetime energy performance, yet the transformation from architectural geometry to analysis-ready models remains fragmented. This paper presents CUGER, an automated framework that converts complex 3D building geometries into physically consistent heterogeneous graphs for building energy analysis. CUGER integrates a convex optimization-based segmentation algorithm with structured graph encoding to directly transform CAD geometries into simulation- and learning-ready representations. Evaluated on 266 architecturally diverse building models, the framework achieved an average geometric-to-graph conversion success rate above 80% with strong topological consistency (

R^{2} = 0.82

). Building on the generated graphs, a heterogeneous ZoneGNN model enables zone-level energy prediction of single building, achieving accurate and stable performance (

R^{2} = 0.88 \pm 0.01

) and outperforming MLP baselines, particularly under limited training data. Overall, CUGER establishes a topology-preserving and fully automatable bridge between architectural modeling, performance simulation, and data-driven prediction for early-stage building design.

早期阶段的设计决策强烈地影响着建筑的终身能源性能，然而从建筑几何到分析就绪模型的转变仍然是碎片化的。本文介绍了CUGER，这是一个自动化框架，可将复杂的3D建筑几何形状转换为物理上一致的异构图形，用于建筑能源分析。CUGER将基于凸优化的分割算法与结构化图形编码集成在一起，直接将CAD几何图形转换为仿真和学习准备的表示。通过对266个不同建筑模型的评估，该框架实现了80%以上的几何到图形的平均转换成功率，具有很强的拓扑一致性（R2=0.82）。在生成的图的基础上，异构ZoneGNN模型可以实现单个建筑的区域级能量预测，实现准确和稳定的性能（R2=0.88±0.01），并且优于MLP基线，特别是在有限的训练数据下。总的来说，CUGER在建筑建模、性能模拟和早期建筑设计的数据驱动预测之间建立了一个拓扑保持和完全自动化的桥梁。

{"title":"From geometry to graph: Automation of building performance modeling via convex graph encoding","authors":"Yihui Li , Jun Xiao , Hao Zhou , Borong Lin","doi":"10.1016/j.autcon.2026.106815","DOIUrl":"10.1016/j.autcon.2026.106815","url":null,"abstract":"<div><div>Early-stage design decisions strongly influence a building’s lifetime energy performance, yet the transformation from architectural geometry to analysis-ready models remains fragmented. This paper presents CUGER, an automated framework that converts complex 3D building geometries into physically consistent heterogeneous graphs for building energy analysis. CUGER integrates a convex optimization-based segmentation algorithm with structured graph encoding to directly transform CAD geometries into simulation- and learning-ready representations. Evaluated on 266 architecturally diverse building models, the framework achieved an average geometric-to-graph conversion success rate above 80% with strong topological consistency (<span><math><mrow><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo><mn>0</mn><mo>.</mo><mn>82</mn></mrow></math></span>). Building on the generated graphs, a heterogeneous ZoneGNN model enables zone-level energy prediction of single building, achieving accurate and stable performance (<span><math><mrow><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo><mn>0</mn><mo>.</mo><mn>88</mn><mo>±</mo><mn>0</mn><mo>.</mo><mn>01</mn></mrow></math></span>) and outperforming MLP baselines, particularly under limited training data. Overall, CUGER establishes a topology-preserving and fully automatable bridge between architectural modeling, performance simulation, and data-driven prediction for early-stage building design.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106815"},"PeriodicalIF":11.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146185054","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}

引用次数: 0

Real-time robotic teleoperation for pavement pothole segmentation, quantification, and localization using multimodal sensing and efficient multi-scale attention-enhanced edge deep learning 利用多模态传感和高效的多尺度注意力增强边缘深度学习进行路面坑洼分割、量化和定位的实时机器人远程操作

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-04 DOI: 10.1016/j.autcon.2026.106806

Xi Hu , Rayan H. Assaad

This paper proposes a robotic teleoperation pipeline to automate the segmentation, quantification, localization, and visualization of pavement potholes in real-time. The pipeline includes a new attention-based deep learning (DL) model and integrates a 4WD robot, teleoperation workstation, multimodal RGBD sensing fusion and point cloud processing on the edge, and interactive web application through cloud services. The DL model was developed by incorporating an efficient multi-scale attention (EMA) mechanism and transfer learning, which was trained and tested on a pavement dataset with 9472 images. The pipeline was validated through real-world field tests. The new EMA-based DL model yielded a 0.611 mAP50–95(B) and a 0.613 mAP50–95(M), outperforming the YOLOv9 baseline by 8.33% and 6.98%, respectively. The findings also showed that the proposed pipeline successfully automates pothole inspection and generates an interactive map, enabling remote access to the robot's trajectory and detailed pothole information, including pothole area, volume, average and maximum depth.

本文提出了一种机器人远程操作流水线，实现路面坑洼的实时分割、量化、定位和可视化。该管道包括一个新的基于注意力的深度学习（DL）模型，集成了一个四轮驱动机器人、远程操作工作站、多模态RGBD传感融合和边缘点云处理，以及通过云服务的交互式web应用程序。DL模型结合了高效的多尺度注意（EMA）机制和迁移学习，并在9472张图像的路面数据集上进行了训练和测试。该管道通过实际现场测试进行了验证。新的基于ema的DL模型产生了0.611 mAP50-95 (B)和0.613 mAP50-95 (M)，分别比YOLOv9基线高8.33%和6.98%。研究结果还表明，拟议的管道成功地实现了坑洼检测的自动化，并生成了交互式地图，可以远程访问机器人的轨迹和详细的坑洼信息，包括坑洼面积、体积、平均和最大深度。

{"title":"Real-time robotic teleoperation for pavement pothole segmentation, quantification, and localization using multimodal sensing and efficient multi-scale attention-enhanced edge deep learning","authors":"Xi Hu , Rayan H. Assaad","doi":"10.1016/j.autcon.2026.106806","DOIUrl":"10.1016/j.autcon.2026.106806","url":null,"abstract":"<div><div>This paper proposes a robotic teleoperation pipeline to automate the segmentation, quantification, localization, and visualization of pavement potholes in real-time. The pipeline includes a new attention-based deep learning (DL) model and integrates a 4WD robot, teleoperation workstation, multimodal RGBD sensing fusion and point cloud processing on the edge, and interactive web application through cloud services. The DL model was developed by incorporating an efficient multi-scale attention (EMA) mechanism and transfer learning, which was trained and tested on a pavement dataset with 9472 images. The pipeline was validated through real-world field tests. The new EMA-based DL model yielded a 0.611 mAP50–95(B) and a 0.613 mAP50–95(M), outperforming the YOLOv9 baseline by 8.33% and 6.98%, respectively. The findings also showed that the proposed pipeline successfully automates pothole inspection and generates an interactive map, enabling remote access to the robot's trajectory and detailed pothole information, including pothole area, volume, average and maximum depth.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106806"},"PeriodicalIF":11.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146185057","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}

引用次数: 0

Graph-driven embedding reinforcement and traceable LLM agent for reliable element alignment in construction report generation 图驱动的嵌入增强和可跟踪的LLM代理在施工报告生成中可靠的元素对齐

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-03 DOI: 10.1016/j.autcon.2026.106816

Zhenzhao Xia , Botao Zhong , Shuai Zhang , Tonghui Zhao , Miroslaw J. Skibniewski

Engineering report generation from construction-site Internet of Things (IoT) data using large language models (LLMs) remains challenging due to hallucinations. Ensuring traceability and reliability in information retrieval and multi-step reasoning is essential within retrieval-augmented generation (RAG) for LLM. This paper formalizes the RAG-LLM pipeline and proposes a dual-stream enhancement combining knowledge graph (KG) construction with reinforcement learning (RL)-based retriever tuning. The graph-guided module extracts structured engineering elements, while RL improves semantic alignment and tokenization of critical terms. Leveraging this dual-stream RAG, a traceable reporting agent is developed, providing end-to-end traceability of retrieval and reasoning, along with inter-step similarity measures. When collaborating with existing on-site IoT systems, the agent can extend automated monitoring to decision-making support. This paper presents a reliable approach for construction report generation and advances human-AI collaboration in construction management.

由于存在幻觉，使用大型语言模型（llm）从建筑工地物联网（IoT）数据生成工程报告仍然具有挑战性。在LLM的检索增强生成（RAG）中，确保信息检索和多步推理的可追溯性和可靠性至关重要。本文形式化了RAG-LLM管道，并提出了一种结合知识图（KG）构建和基于强化学习（RL）的检索器调谐的双流增强方法。图引导模块提取结构化工程元素，而强化学习改进了关键术语的语义对齐和标记化。利用这个双流RAG，开发了一个可跟踪的报告代理，提供端到端检索和推理的可跟踪性，以及步骤间的相似性度量。当与现有的现场物联网系统协作时，代理可以将自动监控扩展到决策支持。本文提出了一种可靠的施工报告生成方法，并推进了人工智能在施工管理中的协作。

{"title":"Graph-driven embedding reinforcement and traceable LLM agent for reliable element alignment in construction report generation","authors":"Zhenzhao Xia , Botao Zhong , Shuai Zhang , Tonghui Zhao , Miroslaw J. Skibniewski","doi":"10.1016/j.autcon.2026.106816","DOIUrl":"10.1016/j.autcon.2026.106816","url":null,"abstract":"<div><div>Engineering report generation from construction-site Internet of Things (IoT) data using large language models (LLMs) remains challenging due to hallucinations. Ensuring traceability and reliability in information retrieval and multi-step reasoning is essential within retrieval-augmented generation (RAG) for LLM. This paper formalizes the RAG-LLM pipeline and proposes a dual-stream enhancement combining knowledge graph (KG) construction with reinforcement learning (RL)-based retriever tuning. The graph-guided module extracts structured engineering elements, while RL improves semantic alignment and tokenization of critical terms. Leveraging this dual-stream RAG, a traceable reporting agent is developed, providing end-to-end traceability of retrieval and reasoning, along with inter-step similarity measures. When collaborating with existing on-site IoT systems, the agent can extend automated monitoring to decision-making support. This paper presents a reliable approach for construction report generation and advances human-AI collaboration in construction management.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106816"},"PeriodicalIF":11.5,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110225","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}

引用次数: 0

Dependency-aware indoor 3D scene graph prediction via multimodal feature learning 基于多模态特征学习的依赖感知室内3D场景图预测

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-03 DOI: 10.1016/j.autcon.2026.106817

Shengnan Ke , Shibin Li , Jun Gong , Lingxiang Liu , Jianjun Luo , Bing Wang , Shengjun Tang

Accurate semantic understanding of indoor 3D point clouds is essential for constructing semantically rich architectural models and enabling component-level monitoring in smart building environments. This paper proposes a dependency-aware indoor 3D scene graph prediction framework that addresses two major limitations in existing methods. To address this, a Dependency-Aware Graph Reasoning Network (DAGRN) is introduced, integrating attention and message-passing mechanisms to learn context-dependent representations of objects and their relationships. Accordingly, a multimodal feature-enhanced learning module is proposed to align point cloud and image features and incorporate textual semantics from image–text models into a unified training scheme with triplet-level constraints ensuring semantic consistency. Extensive experiments on the 3RScan dataset demonstrate that the proposed method significantly outperforms existing approaches, achieving a 3.95% improvement in overall prediction metrics, laying a foundation for advanced semantic modeling in building automation.

在智能建筑环境中，对室内3D点云的准确语义理解对于构建语义丰富的建筑模型和实现组件级监控至关重要。本文提出了一种依赖感知的室内3D场景图预测框架，解决了现有方法的两个主要局限性。为了解决这个问题，引入了依赖感知图推理网络（DAGRN），集成了注意力和消息传递机制，以学习对象及其关系的上下文相关表示。为此，提出了一种多模态特征增强学习模块，将点云和图像特征对齐，并将图像-文本模型的文本语义整合到统一的训练方案中，采用三重约束保证语义一致性。在3RScan数据集上的大量实验表明，该方法显著优于现有方法，总体预测指标提高了3.95%，为建筑自动化领域的高级语义建模奠定了基础。

{"title":"Dependency-aware indoor 3D scene graph prediction via multimodal feature learning","authors":"Shengnan Ke , Shibin Li , Jun Gong , Lingxiang Liu , Jianjun Luo , Bing Wang , Shengjun Tang","doi":"10.1016/j.autcon.2026.106817","DOIUrl":"10.1016/j.autcon.2026.106817","url":null,"abstract":"<div><div>Accurate semantic understanding of indoor 3D point clouds is essential for constructing semantically rich architectural models and enabling component-level monitoring in smart building environments. This paper proposes a dependency-aware indoor 3D scene graph prediction framework that addresses two major limitations in existing methods. To address this, a Dependency-Aware Graph Reasoning Network (DAGRN) is introduced, integrating attention and message-passing mechanisms to learn context-dependent representations of objects and their relationships. Accordingly, a multimodal feature-enhanced learning module is proposed to align point cloud and image features and incorporate textual semantics from image–text models into a unified training scheme with triplet-level constraints ensuring semantic consistency. Extensive experiments on the 3RScan dataset demonstrate that the proposed method significantly outperforms existing approaches, achieving a 3.95% improvement in overall prediction metrics, laying a foundation for advanced semantic modeling in building automation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106817"},"PeriodicalIF":11.5,"publicationDate":"2026-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110227","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}

引用次数: 0

Semantic naming convention-based automated BIM generation of precast concrete components from 2D CAD drawings 基于语义命名约定的2D CAD图纸自动生成预制混凝土构件的BIM

IF 11.5 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction

Pub Date : 2026-02-03 DOI: 10.1016/j.autcon.2026.106804

Eunbeen Jeong , Seoyoung Jung , Insu Jung , Kyujin Ko , Junyoung Jang

The manual conversion of 2D CAD drawings to 3D BIM objects for Precast Concrete (PC) components is a time-consuming, error-prone bottleneck that hinders project efficiency. Existing automation studies have struggled with the complex, non-standard geometries typical of PC components. This paper presents a framework that automates BIM generation using a Semantic Naming Convention (SNC) to encode design information into 2D CAD attributes. Developed in the Dynamo visual programming environment, the system automatically creates fabrication-level BIM objects for PC columns, beams, and slabs. The framework's versatility was validated by successfully processing 100% of production drawings from three different manufacturers. A Charrette test showed the automated approach reduced modeling time by an average of 78.9%, improved model accuracy by 12.3, and cut human errors by over 90% compared to manual methods. This framework provides a practical solution to enhance productivity and model quality in the PC construction sector.

手工将2D CAD图纸转换为3D BIM对象用于预制混凝土（PC）组件是一个耗时且容易出错的瓶颈，阻碍了项目效率。现有的自动化研究一直在努力解决PC组件典型的复杂、非标准几何形状问题。本文提出了一个框架，该框架使用语义命名约定（SNC）自动生成BIM，将设计信息编码为2D CAD属性。该系统在Dynamo可视化编程环境中开发，可自动为PC柱、梁和板创建制造级BIM对象。通过成功处理来自三个不同制造商的100%生产图纸，验证了该框架的多功能性。Charrette测试表明，与手动方法相比，自动化方法平均减少了78.9%的建模时间，提高了12.3的模型精度，并将人为错误减少了90%以上。该框架提供了一个实用的解决方案，以提高生产力和模型质量的PC建设部门。

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Automation in Construction

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀