{"title":"Extrusion under material uncertainty with pressure-based closed-loop feedback control in robotic concrete additive manufacturing","authors":"Mahsa Rabiei, Reza Moini","doi":"10.1016/j.autcon.2025.106494","DOIUrl":"10.1016/j.autcon.2025.106494","url":null,"abstract":"<div><div>One of the main challenges in extrusion-based robotic concrete additive manufacturing process is material uncertainty under pressure which leads to geometric inaccuracies. Here, a real-time pressure-based closed-loop feedback control system is developed to address the geometric fidelity challenges that arise from the material uncertainty under extrusion. A robotic extrusion process is instrumented with a load sensor and assessed with and without activation of the pressure-based controller. The reliability and robustness of a pressure-based closed-loop control system is examined by introducing single- and double-perturbation of the extrusion and assessing the recovery of the geometry (width, height) of the extruded filaments to a baseline reference. The developed control system reacts to retrieve and maintain geometric fidelity among all experiments and repetitions, thereby highlighting the utility of pressure as a feedback parameter to handle material uncertainty that is common in extrusion-based robotic manufacturing process. Future directions include evaluating the control system in unseen conditions.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106494"},"PeriodicalIF":11.5,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144934152","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}
Yanyan Wang , Kechen Song , Yuyuan Liu , Tianze Li , Yunhui Yan , Gustavo Carneiro
{"title":"Bimodal defect segmentation with Geometric Prior-supported Anti-imbalance Learning for pavement defect evaluation and repair","authors":"Yanyan Wang , Kechen Song , Yuyuan Liu , Tianze Li , Yunhui Yan , Gustavo Carneiro","doi":"10.1016/j.autcon.2025.106497","DOIUrl":"10.1016/j.autcon.2025.106497","url":null,"abstract":"<div><div>Pavement defect segmentation benefits from integrating 2D images with 3D depth data, enabling more accurate evaluation and repair decisions. However, current methods suffer from indiscriminate feature extraction that overlooks severe class imbalance, limited adaptability to defects with diverse shapes and appearances, and a lack of publicly available bimodal datasets with multi-class annotations. To address these challenges, this paper proposes Geometric Prior-supported Anti-imbalance Learning (GPAL), a bimodal segmentation framework based on the Segment Anything Model (SAM). GPAL introduces: (1) Defect-centric Reinforcing (DR) prompting, which leverages geometric priors derived from depth flow to enhance the image encoder’s focus on defect details in a defect-oriented manner; and (2) Depth Prototype-support Uniform Prompting (DPUP), which extends SAM for bimodal, multi-class defect segmentation by learning class-balanced depth prototypes. Additionally, the Bimodal Multi-category Pavement Defect (BMPD) dataset is constructed, containing 5,059 samples across four defect categories. Experimental results demonstrate that the proposed method effectively highlights defects under imbalanced conditions and adapts to diverse defects, achieving an mF1 score of 86.01% on the BMPD dataset. This advancement supports reliable pavement assessment and repair decisions, while laying a foundation for addressing class imbalance in diverse tasks through geometric priors and prompting strategies.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106497"},"PeriodicalIF":11.5,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144933684","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}
{"title":"Leveraging digital enabling technologies for integrating climate adaptation and mitigation in urban design","authors":"Guglielmo Ricciardi , Guido Callegari , Mattia Federico Leone","doi":"10.1016/j.autcon.2025.106504","DOIUrl":"10.1016/j.autcon.2025.106504","url":null,"abstract":"<div><div>Integrating climate change adaptation (CCA) and mitigation (CCM) into urban design remains a challenge due to methodological fragmentation and lack of cross-scalar tools. The Fourth Industrial Revolution offers transformative potential. This paper explores which digital enabling technologies (DETs) are most effective in supporting urban design scenarios addressing both CCA and CCM. A systematic literature review of 84 empirical studies was conducted, evaluating 12 DETs based on their capabilities in urban design scenario and climate performance. Results show that Remote Sensing, Geographic Information Systems (GIS), and Cloud Services are the most coherent technologies for combining climate with design workflows. Conversely, widely used tools like Building Information Modelling (BIM) show limited capacity to support ecological or carbon goals. These findings emphasise the necessity of interoperable, hybrid DET frameworks to enable CCA and CCM urban design. The paper offers insights for practitioners, paving the way for digitally enabled climate strategies in urban environments.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"180 ","pages":"Article 106504"},"PeriodicalIF":11.5,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144934151","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}
{"title":"Heavy lifting localization system using sliding window filtering and sequential quadratic programming for safe modular integrated construction","authors":"Aimin Zhu, Zhiqian Zhang, Wei Pan","doi":"10.1016/j.autcon.2025.106473","DOIUrl":"10.1016/j.autcon.2025.106473","url":null,"abstract":"<div><div>Heavy lifting is crucial in Modular integrated Construction (MiC), where ultra-wideband (UWB) technology can accurately track the lifting process for safe module installation. However, UWB's potential on lifting remains underutilized, particularly under non-line-of-sight propagation. This paper aims to develop a UWB-based Heavy Lifting Localization (HeLLo) system designed for achieving safe MiC during module lifting. The system integrates two lifting-specific localization models: Sliding Window Filtering-(Weighted) and Sequential Quadratic Programming models for line-of-sight and non-line-of-sight conditions, respectively. The system was verified using lab tests and computer simulations and was validated using a real-life MiC project. Results demonstrated that the HeLLo system's models outperformed other models such as Newton and Powell in accuracy and efficiency, achieving 25.66 cm in line-of-sight and 36.05 cm in non-line-of-sight accuracies within 1 ms. The HeLLo system ensures centimeter-level accuracy and millisecond-level efficiency to prevent lifting collisions, enhancing safety in MiC. The findings should stimulate the adoption of modular construction globally.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"179 ","pages":"Article 106473"},"PeriodicalIF":11.5,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144925827","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}
Yuanyuan Tan , Hanbing Wang , Ruopeng Huang , Daniel Hall , Ad Straub , Queena K. Qian
{"title":"Beyond barriers: Stage-based and pathway-oriented conceptual model of resistance to BIM innovation","authors":"Yuanyuan Tan , Hanbing Wang , Ruopeng Huang , Daniel Hall , Ad Straub , Queena K. Qian","doi":"10.1016/j.autcon.2025.106503","DOIUrl":"10.1016/j.autcon.2025.106503","url":null,"abstract":"<div><div>Building Information Modeling (BIM) is regarded as a representative of digital innovation in the construction industry. However, the process of its innovation is often hindered by the resistance from stakeholders. Many studies view such resistance as a barrier or static outcome, overlooking both stage and pathway perspectives. Even when considered, existing discussions remain fragmented. To fill this gap, this paper integrates diffusion of innovation theory (DOI) and stimulus–organism–response (SOR) theory to build a theoretical framework that guides a systematic literature review of 55 journal articles. Based on the results, this study proposes a stage-based and pathway-oriented conceptual model to enhance the understanding of BIM innovation resistance. The conceptual model provides an intermediate theory, providing a theoretical basis for future knowledge development. It also offers stage-based practical references for managers and policymakers to identify and mitigate resistance in the process of BIM promotion.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"179 ","pages":"Article 106503"},"PeriodicalIF":11.5,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144925829","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}
Dongyoung Ko , Minsoo Park , Sujin Jin , Pa Pa Win Aung , Seunghee Park
{"title":"Vision-based automated cable tension monitoring using pixel tracking","authors":"Dongyoung Ko , Minsoo Park , Sujin Jin , Pa Pa Win Aung , Seunghee Park","doi":"10.1016/j.autcon.2025.106488","DOIUrl":"10.1016/j.autcon.2025.106488","url":null,"abstract":"<div><div>Traditional methods for monitoring cable tension rely on indirect measurements such as cable vibrations and often require specialized calibration. These approaches limit the efficiency, and non-contact capability of tension monitoring across various structures. This paper presents a vision-based framework for automated cable tension monitoring, which directly captures image data of internal steel strands. By leveraging advanced computer vision techniques — such as zero-shot segmentation, depth estimation, edge detection, and dense pixel tracking — critical geometric parameters are extracted and integrated into a kinematic-based model for tension estimation. A calibration-free method for estimating real-world pixel size, derived from the helical geometry of the strands, enables field deployment without the need for camera setup information. Experimental results show strong correlation with reference data, achieving a mean absolute error of 4.94% under elastic conditions. These findings pave the way for a promising alternative in vision-based structural health monitoring for prestressed structures.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"179 ","pages":"Article 106488"},"PeriodicalIF":11.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922491","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}
{"title":"AI applications for structural design automation","authors":"Hao Xie, Qipei Mei, Ying Hei Chui","doi":"10.1016/j.autcon.2025.106496","DOIUrl":"10.1016/j.autcon.2025.106496","url":null,"abstract":"<div><div>In recent years, there has been an increase in artificial intelligence (AI) applications in the field of structural engineering. With the rapid development of AI, new opportunities have emerged to use this technology to generate and check the structural design. Over the last few years, there has been a sharp increase in the number of publications relating to AI applications in structural design. This paper presents a systematic review of previous studies on the applications of AI in structural design. A total of 134 papers were analyzed. The review shows that AI techniques have benefited engineers in generating optimized structural design solutions that meet the requirements of building codes and design standards. Additionally, challenges and future opportunities are presented and discussed. This review will contribute to the body of knowledge by summarizing the state-of-the-art of using AI technologies in structural design and exploring future research opportunities in this area.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"179 ","pages":"Article 106496"},"PeriodicalIF":11.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922492","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}
Xinyu Chen , Yantao Yu , Yunpeng Wang , Zhen-Zhong Hu
{"title":"Multimodal data fusion for ergonomic assessment of construction workers in visually obstructed environments","authors":"Xinyu Chen , Yantao Yu , Yunpeng Wang , Zhen-Zhong Hu","doi":"10.1016/j.autcon.2025.106495","DOIUrl":"10.1016/j.autcon.2025.106495","url":null,"abstract":"<div><div>Work-related musculoskeletal disorders are the leading cause of nonfatal injuries in the construction industry. Ergonomic assessment methods can effectively prevent these disorders. Vision-based ergonomic risk assessment methods are widely applied in construction sites due to their cost-effectiveness and non-invasiveness. However, existing vision-based methods often face challenges in accurately estimating worker pose in real construction sites with visually obstructed environments, such as self-obstruction, object obstruction, and body parts out of view. Additionally, these methods lack consideration of external load factors for ergonomics. To overcome these issues, this paper proposes a multimodal ergonomic assessment method, combining visual data and pressure signals. Multimodal method integrates pressure and visual data in a unified feature space, improving pose estimation results and providing external load metrics for a more comprehensive ergonomic assessment. Field experiments show that the accuracy of pose estimation and risk assessment is enhanced, supporting the safety and health of construction workers.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"179 ","pages":"Article 106495"},"PeriodicalIF":11.5,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144917389","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}
{"title":"Natural language-extracted and BIM-referenced knowledge base for construction quality inspection via augmented reality","authors":"Han Liu , Donghai Liu , Junjie Chen","doi":"10.1016/j.autcon.2025.106500","DOIUrl":"10.1016/j.autcon.2025.106500","url":null,"abstract":"<div><div>Construction quality is of upmost importance for delivering well-performed civil structures. Inspection offers a critical means to ensure construction quality. However, its effective implementation relies on an excess of domain knowledge that usually takes years to accumulate, making inspection expensive and challenging to conduct. This paper introduces a construction quality inspection knowledge base that empowers inspectors with easily accessible and intuitive construction requirement information. Natural language processing (NLP) is applied to automatically extract knowledge from construction documents such as specification and regulatory files. The extracted knowledge is linked to the building information model (BIM) using proposed association methods and semantic similarity matching. The natural language-extracted and BIM-referenced knowledge base (NLBIM-KB) is integrated into an augmented reality (AR) interface, which provides a freehand tool to assist inspectors' decision-making via on-demand construction knowledge extraction.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"179 ","pages":"Article 106500"},"PeriodicalIF":11.5,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144913912","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}
Koi Xiaowen Guo , Peter Kok-Yiu Wong , Jack C.P. Cheng , Chak-Fu Chan , Pak-Him Leung , Xingyu Tao
{"title":"Enhancing visual-LLM for construction site safety compliance via prompt engineering and Bi-stage retrieval-augmented generation","authors":"Koi Xiaowen Guo , Peter Kok-Yiu Wong , Jack C.P. Cheng , Chak-Fu Chan , Pak-Him Leung , Xingyu Tao","doi":"10.1016/j.autcon.2025.106490","DOIUrl":"10.1016/j.autcon.2025.106490","url":null,"abstract":"<div><div>The escalating frequency of safety incidents on construction sites requires an effective safety management framework. Traditional computer vision systems are constrained by their static nature, limited generalization, and inadequate semantic comprehension. This paper integrates a multi-modal Visual Language Model (VLM) with our proposed Bi-stage Retrieval-Augmented Generation (BiRAG) framework, which enhances safety compliance monitoring based on construction site images, with high scalability and adaptiveness to evolving safety standards without tedious model fine-tuning. A TriPhased prompt (TPP) and a decision-tree-based compliance judgment prompt are designed to enhance the VLM's ability to interpret worker behaviors and safety compliance from site images. A context-aware chunking strategy and hybrid retrieval algorithm are developed to improve the analysis against relevant safety regulations. Experiments with images collected from a real construction site in Hong Kong demonstrated a 7.73 % increase in retrieval accuracy and an 11.66 % improvement in compliance analysis accuracy, offering a holistic construction safety management solution.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"179 ","pages":"Article 106490"},"PeriodicalIF":11.5,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144913908","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}