Automation in Construction最新文献

英文中文

Human–AI communication parameters for reproducible text-to-image workflows in AEC design across academia and practice 学术界和实践中AEC设计中可重复文本到图像工作流程的人类-人工智能通信参数

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

Automation in Construction

Pub Date : 2026-01-13 DOI: 10.1016/j.autcon.2026.106767

Pedro Meira-Rodríguez , Vicente López-Chao

Generative artificial intelligence (AI) is increasingly incorporated into architecture, engineering, and construction (AEC) workflows, yet its adoption has advanced faster than the development of robust communication frameworks that ensure reproducibility, controllability, and methodological transparency. Academic research often emphasizes exploratory prototypes or technical advances, whereas professional practice depends on empirically tested input combinations that seldom follow systematic documentation. This review examines 190 academic publications (2000–2025) and 812 practitioner cases to identify the core human–AI communication variables structuring image-based generative workflows across platforms such as Midjourney, DALL-E, and Stable Diffusion. By synthesizing these variables into a cross-platform taxonomy, the paper reframes them as design levers and reproducible parameters for AEC design at an early stage. In doing so, the paper advances the goals of automation, standardization, and traceability in AEC workflows by demonstrating that reproducibility in generative design depends not only on model performance but on the communicability and documentation of user–model interactions.

生成式人工智能（AI）越来越多地融入到架构、工程和施工（AEC）工作流程中，但它的采用比确保可重复性、可控性和方法透明度的健壮通信框架的发展更快。学术研究通常强调探索性原型或技术进步，而专业实践依赖于经验测试的输入组合，很少遵循系统文档。本文审查了190篇学术出版物（2000-2025）和812个实践案例，以确定跨平台（如Midjourney， DALL-E和Stable Diffusion）构建基于图像的生成工作流的核心人类-人工智能交流变量。通过将这些变量综合到跨平台分类中，本文将它们重新定义为AEC设计早期阶段的设计杠杆和可重复参数。在此过程中，本文通过证明生成式设计的再现性不仅取决于模型性能，还取决于用户模型交互的可沟通性和文档化，推进了AEC工作流程中自动化、标准化和可追溯性的目标。

{"title":"Human–AI communication parameters for reproducible text-to-image workflows in AEC design across academia and practice","authors":"Pedro Meira-Rodríguez , Vicente López-Chao","doi":"10.1016/j.autcon.2026.106767","DOIUrl":"10.1016/j.autcon.2026.106767","url":null,"abstract":"<div><div>Generative artificial intelligence (AI) is increasingly incorporated into architecture, engineering, and construction (AEC) workflows, yet its adoption has advanced faster than the development of robust communication frameworks that ensure reproducibility, controllability, and methodological transparency. Academic research often emphasizes exploratory prototypes or technical advances, whereas professional practice depends on empirically tested input combinations that seldom follow systematic documentation. This review examines 190 academic publications (2000–2025) and 812 practitioner cases to identify the core human–AI communication variables structuring image-based generative workflows across platforms such as Midjourney, DALL-E, and Stable Diffusion. By synthesizing these variables into a cross-platform taxonomy, the paper reframes them as design levers and reproducible parameters for AEC design at an early stage. In doing so, the paper advances the goals of automation, standardization, and traceability in AEC workflows by demonstrating that reproducibility in generative design depends not only on model performance but on the communicability and documentation of user–model interactions.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106767"},"PeriodicalIF":11.5,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145962616","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

Mapping digital twin applications in infrastructure and the built environment across research types, methods, sectors, phases, and scales 绘制跨研究类型、方法、部门、阶段和规模的基础设施和建筑环境中的数字孪生应用

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

Automation in Construction

Pub Date : 2026-01-13 DOI: 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.

数字孪生技术越来越多地用于基础设施和建筑环境，以创建物理资产和流程的动态数据驱动模型。本综述分析了隧道、桥梁、道路、建筑、施工管理和城市规划等领域的最新进展，涵盖了从设计到运营的所有生命周期阶段。将数字孪生与建筑信息模型、物联网传感器和人工智能相结合，增强实时监控、决策和资产绩效。关键方法包括监控、建模和仿真，这些方法可以改善资源利用和主动维护。然而，采用面临着诸如数据互操作性差、成本高以及合并多种技术时的技术复杂性等挑战。围绕数据隐私和安全的道德和治理问题也依然存在。该综述确定了未来在改进互操作性、扩展预测分析和评估大规模影响方面的研究需求。报告强调了数字孪生在提高韧性、效率和可持续性方面的潜力，强调了政策支持和利益相关者合作的必要性。

{"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":"2026-01-13","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}

引用次数: 0

AI-powered real-time system for automated concrete slump prediction via video analysis 人工智能驱动的实时系统，通过视频分析自动预测混凝土坍落度

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

Automation in Construction

Pub Date : 2026-01-13 DOI: 10.1016/j.autcon.2026.106777

Youngmin Kim , Giyeong Oh , Kwangsoo Youm , Youngjae Yu

Concrete workability is essential to construction quality, and the slump test remains the most widely used on-site method for its assessment. However, traditional slump testing is manual, time-consuming, and highly operator-dependent, limiting its suitability for continuous or real-time monitoring during placement. SlumpGuard is an AI-powered vision system that analyzes the natural discharge flow from a mixer-truck chute using a single fixed camera. The system performs automatic chute detection, pouring-event identification, and video-based slump classification, enabling quality monitoring without sensors, hardware installation, or manual intervention. The system design is presented, along with a site-replicated dataset comprising over 6000 video clips, and extensive evaluations demonstrating reliable chute localization, accurate pouring detection, and robust slump prediction under diverse field conditions. An expert study further reveals substantial disagreement in human visual estimates, underscoring the need for automated assessment. Demonstration videos are available at this URL.

混凝土和易性对施工质量至关重要，坍落度试验是目前现场应用最广泛的混凝土和易性评价方法。然而，传统的坍落度测试是手动的，耗时且高度依赖于操作人员，限制了其在放置过程中连续或实时监测的适用性。SlumpGuard是一种人工智能视觉系统，可以使用单个固定摄像头分析混合卡车溜槽的自然排出流。该系统可自动进行溜槽检测、倾倒事件识别和基于视频的滑塌度分类，无需传感器、硬件安装或人工干预即可实现质量监控。介绍了系统设计，以及包含6000多个视频片段的现场复制数据集，以及广泛的评估，证明了在不同现场条件下可靠的滑槽定位，准确的浇注检测和可靠的坍落度预测。一项专家研究进一步揭示了人类视觉评估的实质性分歧，强调了自动化评估的必要性。演示视频可在此URL获得。

{"title":"AI-powered real-time system for automated concrete slump prediction via video analysis","authors":"Youngmin Kim , Giyeong Oh , Kwangsoo Youm , Youngjae Yu","doi":"10.1016/j.autcon.2026.106777","DOIUrl":"10.1016/j.autcon.2026.106777","url":null,"abstract":"<div><div>Concrete workability is essential to construction quality, and the slump test remains the most widely used on-site method for its assessment. However, traditional slump testing is manual, time-consuming, and highly operator-dependent, limiting its suitability for continuous or real-time monitoring during placement. SlumpGuard is an AI-powered vision system that analyzes the natural discharge flow from a mixer-truck chute using a single fixed camera. The system performs automatic chute detection, pouring-event identification, and video-based slump classification, enabling quality monitoring without sensors, hardware installation, or manual intervention. The system design is presented, along with a site-replicated dataset comprising over 6000 video clips, and extensive evaluations demonstrating reliable chute localization, accurate pouring detection, and robust slump prediction under diverse field conditions. An expert study further reveals substantial disagreement in human visual estimates, underscoring the need for automated assessment. Demonstration videos are available at <span><span>this URL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106777"},"PeriodicalIF":11.5,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145962644","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

Collaborative inspection for large-scale urban sewer pipe networks by coupling multiple robotic pipe capsules and spatial optimization 基于多机器人管道胶囊耦合和空间优化的大型城市污水管网协同检测

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

Automation in Construction

Pub Date : 2026-01-12 DOI: 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.

城市污水管道容易出现裂缝、侵蚀、根部侵入等多种故障。有效和高效的检测方法是大型城市污水管网的必要条件。本文提出了一种将机器人管道胶囊（rpc）与轻量级深度学习和空间优化相结合的城市下水道管道协同检测方法。建立了一个双层网络，以代表不同的工人运动和rpc及其合作。设计了一种专门的轻量级深度神经网络，利用PRC捕获的图像实时识别故障。使用混合元启发式方法对worker和RPC路由进行空间优化。在中国深圳进行的实验表明，该方法以每秒7.64帧的速度达到了83.43%的平衡精度，优于基准方法。该方法为大规模城市污水管网提供了另一种方法。

引用次数: 0

UAV-based quantitative crack measurement for bridges integrating four-point laser metric calibration and mamba segmentation 基于无人机的桥梁裂缝定量测量，集成四点激光度量校准和曼巴分割

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

Automation in Construction

Pub Date : 2026-01-12 DOI: 10.1016/j.autcon.2026.106774

Jinghuan Zhang , Wang Chen , Jian Zhang

Crack width is an indicator of durability loss and serviceability in concrete bridges. Although UAV-based inspection is adopted, variable standoff distance and oblique imaging hinder valid, millimeter-level quantification. This paper presents a framework for crack identification and measurement. (1) A UAV-mounted four-point laser ranging device establishes a scale for each frame. Combined with homography and a Jacobian-based local length metric, the pixel-to-physical factor becomes a function of position and direction, which reduces scale drift across viewpoints. (2) CrackMamba-Net is designed to couple state space modeling with boundary sensitive representations, enhancing crack edge continuity and boundary clarity under fine and low contrast conditions. (3) Topology-preserving skeleton refinement with PCA-guided, distance-weighted linear correction estimates the local orientation; width is then measured along the refined normal and converted to physical units. Field and on-bridge experiments show linear agreement with references and low bias, supporting traceable, engineering-consistent crack quantification at the millimeter scale.

裂缝宽度是混凝土桥梁耐久性损失和使用性能的指标。虽然采用了基于无人机的检测，但可变距离和倾斜成像阻碍了有效的毫米级量化。本文提出了一种裂纹识别和测量的框架。(1)无人机上的四点激光测距装置为每一帧建立标尺。结合单应性和基于雅可比矩阵的局部长度度量，像素-物理因子成为位置和方向的函数，从而减少了视点之间的尺度漂移。(2) CrackMamba-Net旨在将状态空间建模与边界敏感表示相结合，在精细和低对比度条件下增强裂纹边缘的连续性和边界清晰度。(3)基于pca制导、距离加权线性修正的保持拓扑骨架优化估计局部方向；然后沿着精炼法线测量宽度，并转换为物理单位。现场和桥上实验表明，该方法与参考文献线性一致，且偏差低，支持可追溯的、工程上一致的毫米尺度裂纹量化。

{"title":"UAV-based quantitative crack measurement for bridges integrating four-point laser metric calibration and mamba segmentation","authors":"Jinghuan Zhang , Wang Chen , Jian Zhang","doi":"10.1016/j.autcon.2026.106774","DOIUrl":"10.1016/j.autcon.2026.106774","url":null,"abstract":"<div><div>Crack width is an indicator of durability loss and serviceability in concrete bridges. Although UAV-based inspection is adopted, variable standoff distance and oblique imaging hinder valid, millimeter-level quantification. This paper presents a framework for crack identification and measurement. (1) A UAV-mounted four-point laser ranging device establishes a scale for each frame. Combined with homography and a Jacobian-based local length metric, the pixel-to-physical factor becomes a function of position and direction, which reduces scale drift across viewpoints. (2) CrackMamba-Net is designed to couple state space modeling with boundary sensitive representations, enhancing crack edge continuity and boundary clarity under fine and low contrast conditions. (3) Topology-preserving skeleton refinement with PCA-guided, distance-weighted linear correction estimates the local orientation; width is then measured along the refined normal and converted to physical units. Field and on-bridge experiments show linear agreement with references and low bias, supporting traceable, engineering-consistent crack quantification at the millimeter scale.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106774"},"PeriodicalIF":11.5,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145962621","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

Early-stage architecture design assistance by LLMs and knowledge graphs 法学硕士和知识图谱的早期架构设计协助

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

Automation in Construction

Pub Date : 2026-01-10 DOI: 10.1016/j.autcon.2025.106756

Danrui Li , Yichao Shi , Mathew Schwartz , Mubbasir Kapadia

Early-stage architectural design relies heavily on precedent cases and domain knowledge, yet existing assistance methods struggle with the dominance of visual data and the linguistic diversity of design descriptions. In this paper, a retrieval-augmented generation framework with a custom knowledge graph tailored to architecture is proposed. The approach features: (1) a lightweight graph structure representing design logic; (2) a knowledge extraction pipeline for visual and textual data; and (3) aggregation and question answering methods that consolidate precedent knowledge for design support. Experiments show improved retrieval accuracy, more comprehensive precedent recommendations, and enhanced user experience, advancing precedent-based assistance for early design.

早期的建筑设计严重依赖于先例案例和领域知识，然而现有的辅助方法与视觉数据的主导地位和设计描述的语言多样性作斗争。本文提出了一种检索增强生成框架，该框架具有针对体系结构定制的知识图谱。该方法的特点是：(1)轻量级图结构表示设计逻辑；(2)可视化和文本数据的知识提取管道；(3)整合前人知识为设计提供支持的聚合与问答方法。实验表明，检索精度提高，先例推荐更全面，用户体验增强，为早期设计提供基于先例的帮助。

引用次数: 0

Dual-backbone fusion network for damage segmentation in cultural heritage buildings 双骨干融合网络在文物建筑损伤分割中的应用

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

Automation in Construction

Pub Date : 2026-01-10 DOI: 10.1016/j.autcon.2026.106769

Yunpeng Yue , Hai Liu , Marco Donà , Xiaoyu Liu , Elisa Saler , Jie Cui , Francesca da Porto

Cultural heritage (CH) buildings are vulnerable to damage due to aging and environmental factors, necessitating timely detection and maintenance. This paper proposes a lightweight dual-backbone segmentation model for damage detection in CH structures. The architecture integrates a Swin Transformer branch to capture global contextual information and a YOLOv8-Ghost branch to preserve fine-grained local details, with a Content-Guided Attention (CGA) fusion mechanism employed to enhance inter-channel feature interactions. A five-class Roman amphitheater damage dataset with 2010 images was constructed for training and evaluation. The proposed model is applied to damage detection in the Arena, Verona, Italy, which experienced local collapse accident on January 23, 2023. Experimental results demonstrate that the model achieves robust segmentation performance under challenging conditions such as low lighting, occlusions, and heterogeneous surface textures. The inspection results of both the exterior and interior facades of the Arena confirm the effectiveness and efficiency of the proposed dual-backbone fusion strategy.

文物建筑易受老化和环境因素的影响而受损，需要及时检测和维护。本文提出了一种轻型双骨干分割模型，用于CH结构的损伤检测。该体系结构集成了Swin Transformer分支来捕获全局上下文信息，YOLOv8-Ghost分支来保存细粒度的本地细节，并采用了内容引导注意（Content-Guided Attention， CGA）融合机制来增强通道间的功能交互。构建了一个包含2010张图像的5类罗马圆形剧场损伤数据集，用于训练和评估。将该模型应用于2023年1月23日发生局部坍塌事故的意大利Verona Arena的损伤检测。实验结果表明，该模型在低光照、遮挡和非均匀表面纹理等具有挑战性的条件下具有鲁棒的分割性能。对体育馆内外立面的检查结果证实了所提出的双主干融合策略的有效性和效率。

{"title":"Dual-backbone fusion network for damage segmentation in cultural heritage buildings","authors":"Yunpeng Yue , Hai Liu , Marco Donà , Xiaoyu Liu , Elisa Saler , Jie Cui , Francesca da Porto","doi":"10.1016/j.autcon.2026.106769","DOIUrl":"10.1016/j.autcon.2026.106769","url":null,"abstract":"<div><div>Cultural heritage (CH) buildings are vulnerable to damage due to aging and environmental factors, necessitating timely detection and maintenance. This paper proposes a lightweight dual-backbone segmentation model for damage detection in CH structures. The architecture integrates a Swin Transformer branch to capture global contextual information and a YOLOv8-Ghost branch to preserve fine-grained local details, with a Content-Guided Attention (CGA) fusion mechanism employed to enhance inter-channel feature interactions. A five-class Roman amphitheater damage dataset with 2010 images was constructed for training and evaluation. The proposed model is applied to damage detection in the Arena, Verona, Italy, which experienced local collapse accident on January 23, 2023. Experimental results demonstrate that the model achieves robust segmentation performance under challenging conditions such as low lighting, occlusions, and heterogeneous surface textures. The inspection results of both the exterior and interior facades of the Arena confirm the effectiveness and efficiency of the proposed dual-backbone fusion strategy.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106769"},"PeriodicalIF":11.5,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145956564","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

Safety-aware predictive motion planning for close-range human-UAV collaboration in construction 建筑中近距离人-无人机协同的安全感知预测运动规划

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

Automation in Construction

Pub Date : 2026-01-10 DOI: 10.1016/j.autcon.2026.106771

Tianyu Ren, Houtan Jebelli

Drones are increasingly used in construction for inspection and material transport, but their deployment in close-range collaboration with workers remains limited due to safety concerns and the difficulty of motion planning in dynamic environments. This paper introduces a predictive, risk-aware control framework integrating motion forecasting, probabilistic risk modeling, and hybrid planning to enable safe, efficient drone–worker interaction. Worker motion is captured with RGB-D input and forecasted 1.5 s ahead using PoseCastNet, a transformer-based network that outputs joint-wise 3D trajectories and confidence. Predictions are fused into a Bayesian-updated probabilistic safety map that informs global grid-based pathfinding and local actor-critic control with risk-sensitive rewards. Evaluations in simulation with occlusion and human motion yield a 96.5% success rate, over 40% improvement in minimum clearance, over 20% boost in task efficiency, and 8% reduction in joint prediction error compared to reactive and partially predictive baselines, demonstrating its effectiveness in enabling proactive, collaborative UAV operations.

无人机越来越多地用于建筑检查和材料运输，但由于安全问题和动态环境中运动规划的困难，它们在与工人近距离协作中的部署仍然有限。本文介绍了一种预测性、风险感知控制框架，该框架集成了运动预测、概率风险建模和混合规划，以实现安全、高效的无人机与工作人员交互。通过RGB-D输入捕获工人运动，并使用PoseCastNet提前1.5秒预测，PoseCastNet是一种基于变压器的网络，可输出关节三维轨迹和可信度。预测融合到一个贝叶斯更新的概率安全图中，通知全局基于网格的寻路和具有风险敏感奖励的局部行为者批评家控制。与被动基线和部分预测基线相比，遮挡和人体运动模拟评估的成功率为96.5%，最小间隙提高40%以上，任务效率提高20%以上，联合预测误差减少8%，证明了其在实现主动协作无人机操作方面的有效性。

{"title":"Safety-aware predictive motion planning for close-range human-UAV collaboration in construction","authors":"Tianyu Ren, Houtan Jebelli","doi":"10.1016/j.autcon.2026.106771","DOIUrl":"10.1016/j.autcon.2026.106771","url":null,"abstract":"<div><div>Drones are increasingly used in construction for inspection and material transport, but their deployment in close-range collaboration with workers remains limited due to safety concerns and the difficulty of motion planning in dynamic environments. This paper introduces a predictive, risk-aware control framework integrating motion forecasting, probabilistic risk modeling, and hybrid planning to enable safe, efficient drone–worker interaction. Worker motion is captured with RGB-D input and forecasted 1.5 s ahead using PoseCastNet, a transformer-based network that outputs joint-wise 3D trajectories and confidence. Predictions are fused into a Bayesian-updated probabilistic safety map that informs global grid-based pathfinding and local actor-critic control with risk-sensitive rewards. Evaluations in simulation with occlusion and human motion yield a 96.5% success rate, over 40% improvement in minimum clearance, over 20% boost in task efficiency, and 8% reduction in joint prediction error compared to reactive and partially predictive baselines, demonstrating its effectiveness in enabling proactive, collaborative UAV operations.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106771"},"PeriodicalIF":11.5,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145956586","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

Improving cross-site generalization in construction object detection via hard negative mining 利用硬负挖掘提高建筑目标检测的跨场地泛化

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

Automation in Construction

Pub Date : 2026-01-09 DOI: 10.1016/j.autcon.2026.106761

Jaehwan Seong, Hyung-soo Kim, Hyung-Jo Jung

This paper introduces Cross Hard Negative Mining (Cross-HNM), which reuses cross-site false positives as hard negatives for domain-generalizable construction-site object detection. By training per-site sub-models to extract false positives from other sites, Cross-HNM exploits cross-site structure to suppress dataset-specific noise. Evaluations across 11 sites and 5 unseen test sites show that a single Cross-HNM model achieves 57.58 % mAP, matching performance of 6-fold ensemble method without the inference overhead. Theoretical analysis using Ben-David bounds formalizes how cross-site negatives reduce domain divergence and the upper bound on generalization error. Optimal thresholds are selected via 2-D sensitivity analysis and an LS-CC plateau. Performance gains transfer across architectures, including YOLOv11, Faster R-CNN, and DETR. Since mining and LS-CC are one-off, offline steps, the final detector preserves baseline runtime. Cross-HNM thus provides a practical, scalable solution for intelligent construction safety monitoring in diverse, unseen environments.

本文介绍了交叉硬负挖掘（Cross- hnm），它重用跨站点假阳性作为硬负，用于可域推广的建筑站点目标检测。通过训练每个站点的子模型来从其他站点提取假阳性，Cross-HNM利用跨站点结构来抑制数据集特定的噪声。对11个站点和5个未见过的测试站点的评估表明，单个Cross-HNM模型达到57.58%的mAP，在没有推理开销的情况下达到6倍集成方法的性能。使用Ben-David界的理论分析形式化了跨站点负数如何减少域发散和泛化误差的上界。通过二维灵敏度分析和LS-CC平台选择最佳阈值。性能提升可以跨架构传输，包括YOLOv11、Faster R-CNN和DETR。由于挖掘和LS-CC是一次性的离线步骤，因此最终检测器保留基线运行时。因此，Cross-HNM为在各种看不见的环境中进行智能建筑安全监控提供了实用的、可扩展的解决方案。

引用次数: 0

Mixed-methods evaluation of automated personalised feedback in construction management training using RAG and LLMs 使用RAG和llm的建筑管理培训中自动化个性化反馈的混合方法评估

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

Automation in Construction

Pub Date : 2026-01-08 DOI: 10.1016/j.autcon.2025.106745

Xinping Hu , Yang Miang Goh , Juliana Tay

Construction project management programmes struggle to provide timely and personalised feedback at scale. This paper developed and evaluated an AI feedback system that combines a large language model (LLM) with retrieval-augmented generation (RAG) to deliver personalised messages. A design-based study trialled the feature in two settings, an in-person workshop and an online course, with 81 participants. Mixed methods were used through a perception questionnaire, interviews, and focus groups. Ratings were positive across constructs, with no significant differences between delivery modes. Regression analysis revealed that engagement and perceived fairness independently predicted the intention to continue using the tool. Thematic analysis identified five design considerations: clarity to reduce cognitive load, deeper diagnosis with actionable guidance, role-relevant personalisation, a motivational tone with reflective prompts, and transparency to sustain trust. This paper presents a practical LLM-RAG pipeline, provides evidence of acceptance, and offers practical guidance for practitioners on AI-generated feedback in construction management.

建设项目管理方案难以提供及时和个性化的大规模反馈。本文开发并评估了一种人工智能反馈系统，该系统将大型语言模型（LLM）与检索增强生成（RAG）相结合，以提供个性化消息。一项基于设计的研究在两种情况下测试了这一功能，一种是面对面的研讨会，另一种是在线课程，共有81名参与者。通过感知问卷、访谈和焦点小组使用了混合方法。在不同的结构中，评分都是积极的，在不同的交付模式之间没有显著差异。回归分析显示，参与和感知公平独立预测继续使用该工具的意图。主题分析确定了五个设计考虑因素：减少认知负荷的清晰度，可操作指导的更深入诊断，与角色相关的个性化，带有反思提示的激励语气，以及维持信任的透明度。本文提出了一个实用的LLM-RAG管道，提供了验收证据，并为从业者提供了施工管理中人工智能生成反馈的实践指导。

{"title":"Mixed-methods evaluation of automated personalised feedback in construction management training using RAG and LLMs","authors":"Xinping Hu , Yang Miang Goh , Juliana Tay","doi":"10.1016/j.autcon.2025.106745","DOIUrl":"10.1016/j.autcon.2025.106745","url":null,"abstract":"<div><div>Construction project management programmes struggle to provide timely and personalised feedback at scale. This paper developed and evaluated an AI feedback system that combines a large language model (LLM) with retrieval-augmented generation (RAG) to deliver personalised messages. A design-based study trialled the feature in two settings, an in-person workshop and an online course, with 81 participants. Mixed methods were used through a perception questionnaire, interviews, and focus groups. Ratings were positive across constructs, with no significant differences between delivery modes. Regression analysis revealed that engagement and perceived fairness independently predicted the intention to continue using the tool. Thematic analysis identified five design considerations: clarity to reduce cognitive load, deeper diagnosis with actionable guidance, role-relevant personalisation, a motivational tone with reflective prompts, and transparency to sustain trust. This paper presents a practical LLM-RAG pipeline, provides evidence of acceptance, and offers practical guidance for practitioners on AI-generated feedback in construction management.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"182 ","pages":"Article 106745"},"PeriodicalIF":11.5,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921090","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

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.

﹀