Automation in Construction最新文献_第3页

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

Automation in Construction Pub Date : 2026-03-01 Epub Date: 2026-02-03 DOI: 10.1016/j.autcon.2026.106816

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

{"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":"2026-03-01","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

Digital twins in offsite construction: Current implementations, challenges, and future pathways 非现场建设中的数字孪生：当前实现、挑战和未来途径

IF 11.5 1区工程技术

Automation in Construction Pub Date : 2026-03-01 Epub Date: 2026-02-02 DOI: 10.1016/j.autcon.2026.106820

Nima Moghimi, Oldouz Arshang, Farook Hamzeh

引用次数: 0

GPS-free automated registration of UAV-captured façade image sequences to BIM using semantic key points 使用语义关键点将无人机捕获的farade图像序列自动注册到BIM中，无需gps

IF 11.5 1区工程技术

Automation in Construction Pub Date : 2026-03-01 Epub Date: 2026-01-23 DOI: 10.1016/j.autcon.2026.106788

Cong Chen, Shenghan Zhang

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

Automation in Construction Pub Date : 2026-03-01 Epub Date: 2026-02-04 DOI: 10.1016/j.autcon.2026.106803

Qiming Sun , Dominik Reisach , Silke Langenberg , Benjamin Dillenburger

{"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":"2026-03-01","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

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

Automation in Construction Pub Date : 2026-03-01 Epub 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

{"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":"2026-03-01","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

Efficient UAV trajectory optimization for fine-detailed 3D building reconstruction 面向精细三维建筑重建的高效无人机轨迹优化

IF 11.5 1区工程技术

Automation in Construction Pub Date : 2026-03-01 Epub Date: 2026-01-14 DOI: 10.1016/j.autcon.2026.106775

Tianrui Shen, Lai Kang, Yingmei Wei, Shanshan Wan, Haixuan Wang, Chao Zuo

{"title":"Efficient UAV trajectory optimization for fine-detailed 3D building reconstruction","authors":"Tianrui Shen, Lai Kang, Yingmei Wei, Shanshan Wan, Haixuan Wang, Chao Zuo","doi":"10.1016/j.autcon.2026.106775","DOIUrl":"10.1016/j.autcon.2026.106775","url":null,"abstract":"<div><div>Using images captured by UAVs for high-fidelity 3D building reconstruction in architectural engineering is popular and effective nowadays; however, planning a flight trajectory that maximizes reconstruction quality with minimal flight time remains a critical challenge. This paper proposes a universal co-optimization framework that bridges reconstruction objectives with flight dynamics through an integrated planning paradigm. The proposed approach performs initial flight planning by solving a Traveling Salesman Problem over candidate viewpoints and updating them according to the unit-length contribution criterion. The adaptive radius is determined, and subsequently, the sphere-based corridor is constructed to enforce the trajectory passing all updated viewpoints within the corresponding spatial tolerances. Next, an optimal control problem is formulated and solved using a nonlinear solver to obtain the final flight trajectory satisfying both dynamic and safety constraints. Experimental comparisons with state-of-the-art methods on three public scenes and two real scenes captured by ourselves demonstrate that the proposed approach significantly improves flight efficiency, reducing travel distance and flight duration by approximately 10% to 40% with comparable or superior reconstruction quality.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106775"},"PeriodicalIF":11.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976062","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

Construction site fall hazard identification and automated captioning using adapted vision-language models 使用自适应视觉语言模型的建筑工地坠落危险识别和自动字幕

IF 11.5 1区工程技术

Automation in Construction Pub Date : 2026-03-01 Epub Date: 2026-01-19 DOI: 10.1016/j.autcon.2026.106790

Yongshuang Li, Feng Xu, Zhipeng Zhang, Xinyu Mei, He Huang

{"title":"Construction site fall hazard identification and automated captioning using adapted vision-language models","authors":"Yongshuang Li, Feng Xu, Zhipeng Zhang, Xinyu Mei, He Huang","doi":"10.1016/j.autcon.2026.106790","DOIUrl":"10.1016/j.autcon.2026.106790","url":null,"abstract":"<div><div>Falls are the primary safety hazard in construction, with traditional manual inspections being inefficient and error-prone, and existing computer vision methods lacking generalization in complex scenarios. This paper presents the Construction Safety Vision-Language Model (CS-VLM), a framework for construction site fall hazard identification and automated captioning, which integrates ModelScope Swift (MS-Swift) adapters and Low-Rank Adaptation (LoRA) technology for efficient fine-tuning of the Qwen2.5-7B-Instruct model. To support model training, a standardized image-text dataset for fall hazards is constructed using a Bidirectional Encoder Representations from Transformers (BERT) -based natural language conversion method. Experimental results demonstrate that CS-VLM achieves a Consensus-based Image Description Evaluation (CIDEr) score of 1.324, Semantic Propositional Image Caption Evaluation (SPICE) score of 0.391, and hazard identification F1-score of 90.2%, outperforming state-of-the-art methods in complex scenario adaptability while reducing computational costs. This research enables precise, standardized hazard description generation, facilitating proactive safety management and accident prevention in construction environments.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106790"},"PeriodicalIF":11.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146000932","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

Generic optimization of cross-layer pavement compaction quality using multi-domain intelligent compaction measurement values 基于多域智能压实测量值的跨层路面压实质量通用优化

IF 11.5 1区工程技术

Automation in Construction Pub Date : 2026-03-01 Epub Date: 2026-01-19 DOI: 10.1016/j.autcon.2026.106764

Xuefei Wang , Jiaxue Yuan , Jiale Li , Jianmin Zhang , Guowei Ma

{"title":"Generic optimization of cross-layer pavement compaction quality using multi-domain intelligent compaction measurement values","authors":"Xuefei Wang , Jiaxue Yuan , Jiale Li , Jianmin Zhang , Guowei Ma","doi":"10.1016/j.autcon.2026.106764","DOIUrl":"10.1016/j.autcon.2026.106764","url":null,"abstract":"<div><div>As a critical indicator for evaluating road compaction quality, the Intelligent Compaction Measurement Value (ICMV) still suffers from significant scene dependency and the absence of a unified material-structure coupled evaluation framework, particularly in cross-layer compaction assessment. This paper develops a multi-domain analytical framework that integrates vibration signal time, frequency, and time-frequency features based on field data collected from typical road structures, including soil subgrade, cement-stabilized base layer, and asphalt layers. Rolling pass tracking, compactness prediction modeling, and Shapley additive explanations (SHAP) are employed to identify the generic ICMV applicable to pavement structural layers. Furthermore, comparative analyses are conducted to examine the numerical characteristics and vibration response behaviors of the generic ICMV across various structural layers. Finally, a statistically driven stepwise method is applied to determine the engineering ranges of the generic ICMV, thereby establishing a theoretical paradigm for multi-layer intelligent compaction standards and contributing to the digital transformation of pavement engineering.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106764"},"PeriodicalIF":11.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146000933","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

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

Automation in Construction Pub Date : 2026-03-01 Epub Date: 2026-02-06 DOI: 10.1016/j.autcon.2026.106821

Yao Wang, Yi Bao

引用次数: 0

AI-driven decision support system for construction cost forecasting and consultation using optimized deep learning and language models 人工智能驱动的建筑成本预测和咨询决策支持系统，使用优化的深度学习和语言模型

IF 11.5 1区工程技术

Automation in Construction Pub Date : 2026-03-01 Epub Date: 2026-01-28 DOI: 10.1016/j.autcon.2026.106797

Jui-Sheng Chou, Mei-Yuan Lin, Nguyen-Ngan-Hanh Pham

{"title":"AI-driven decision support system for construction cost forecasting and consultation using optimized deep learning and language models","authors":"Jui-Sheng Chou, Mei-Yuan Lin, Nguyen-Ngan-Hanh Pham","doi":"10.1016/j.autcon.2026.106797","DOIUrl":"10.1016/j.autcon.2026.106797","url":null,"abstract":"<div><div>Fluctuations in construction material prices significantly affect project budgets and bidding strategies via the Construction Cost Index (CCI). This paper develops an AI-driven decision-support system for construction cost forecasting and consultation, integrating deep learning and Large Language Models (LLMs) to enable intelligent CCI prediction. A multi-source data framework combines historical CCI records, macroeconomic indicators, and sentiment extracted from Traditional Chinese construction news. Time-series forecasting employs an Extended Long Short-Term Memory (xLSTM) network, while sentiment models are fine-tuned using Quantized Low-Rank Adaptation (QLoRA). Model hyperparameters for both the QLoRA-fine-tuned LLMs and the xLSTM forecasting models are optimized via the Pilgrimage Walk Optimization (PWO) algorithm, yielding two horizon-specific configurations for short- and medium-term forecasting. Experimental results demonstrate that integrating sentiment features and PWO-based tuning consistently improves forecasting accuracy relative to baseline models. The deployed platform integrates CCI forecasting, sentiment analytics, and retrieval-augmented consultation to provide interpretable forecasts that enhance cost control and decision-making in construction management.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"183 ","pages":"Article 106797"},"PeriodicalIF":11.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071938","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