Dai Quoc Tran , Armstrong Aboah , Yuntae Jeon , Minh-Truyen Do , Mohamed Abdel-Aty , Minsoo Park , Seunghee Park
{"title":"Visual Question Answering-based Referring Expression Segmentation for construction safety analysis","authors":"Dai Quoc Tran , Armstrong Aboah , Yuntae Jeon , Minh-Truyen Do , Mohamed Abdel-Aty , Minsoo Park , Seunghee Park","doi":"10.1016/j.autcon.2025.106127","DOIUrl":"10.1016/j.autcon.2025.106127","url":null,"abstract":"<div><div>Despite advancements in computer vision techniques like object detection and segmentation, a significant gap remains in leveraging these technologies for hazard recognition through natural language processing. To address this gap, this paper proposes VQA-RESCon, an approach that combines Visual Question Answering (VQA) and Referring Expression Segmentation (RES) to enhance construction safety analysis. By leveraging the visual grounding capabilities of RES, our method not only identifies potential hazards through VQA but also precisely localizes and highlights these hazards within the image. The method utilizes a large “scenario-questions” dataset comprising 200,000 images and 16 targeted questions to train a vision-and-language transformer model. In addition, post-processing techniques were employed using the ClipSeg and Segment Anything Model. The validation results indicate that both the VQA and RES models demonstrate notable reliability and precision. The VQA model achieves an F1 score surpassing 90%, while the segmentation models achieve a Mean Intersection over Union of 57%.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106127"},"PeriodicalIF":9.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143704016","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":"Multi-scale GAN-driven GPR data inversion for monitoring urban road substructure","authors":"Feifei Hou , Xingyu Qian , Qiwen Meng , Jian Dong , Fei Lyu","doi":"10.1016/j.autcon.2025.106140","DOIUrl":"10.1016/j.autcon.2025.106140","url":null,"abstract":"<div><div>Accurate monitoring and visualization of urban road substructure and targets are impeded by challenges in inverting Ground Penetrating Radar (GPR) data, especially under multiple inversion objectives and complex road conditions. To address this challenge, a deep learning-based multi-scale inversion approach, termed MSInv-GPR, is proposed, which builds on the Pix2pix Generative Adversarial Network (Pix2pixGAN) framework. This approach introduces dual-channel inputs to improve inversion accuracy, integrates a multi-scale convolution module along with an Efficient Multi-scale Attention (EMA) module to better capture characteristic waveforms, and incorporates a loss function strategy to strengthen adversarial training and accelerate convergence. Ablation studies validate that MSInv-GPR achieves Structural Similarity Index (SSIM) of 99.75 %, Peak Signal-to-Noise Ratio (PSNR) of 47.9014, and Mean Squared Error (MSE) of 12.5825 for 8-bit images, with 51.69 % improvement in Power Supply Modulation Ratio (PSMR) and an increase in discriminator loss from 0.1132 to 1.1603 compared to a baseline.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106140"},"PeriodicalIF":9.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143704017","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}
Xinwei Zhuang , Pinru Zhu , Allen Yang , Luisa Caldas
{"title":"Machine learning for generative architectural design: Advancements, opportunities, and challenges","authors":"Xinwei Zhuang , Pinru Zhu , Allen Yang , Luisa Caldas","doi":"10.1016/j.autcon.2025.106129","DOIUrl":"10.1016/j.autcon.2025.106129","url":null,"abstract":"<div><div>Generative design has its roots in the 1990s and has become an intense research topic for bringing the power of artificial intelligence to various aspects of architecture practices. The recent advancements in artificial intelligence have made a methodological shift in innovative approaches to generative design, fueled by the proliferation of big data. This paper provides a comprehensive review of emerging machine learning algorithms and their applications in architecture. It investigates the concepts and principles behind machine learning, assesses the strengths and limitations of current algorithms, and examines their applications and exploratory uses with a data-centric approach. This work aims to assess current research, identify emerging opportunities and challenges, and suggest viable solutions for future investigations. This work contributes to a deeper understanding of the rapidly evolving landscape of machine learning in architecture, shedding light on how the field can adapt to and leverage these transformative changes.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106129"},"PeriodicalIF":9.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Bridging cross-domain and cross-resolution gaps for UAV-based pavement crack segmentation","authors":"Jinhuan Shan , Wei Jiang , Xiao Feng","doi":"10.1016/j.autcon.2025.106141","DOIUrl":"10.1016/j.autcon.2025.106141","url":null,"abstract":"<div><div>The acquisition of pavement distress images using UAVs presents unique challenges compared to ground-based methods due to differences in camera configurations, flight parameters, and lighting conditions. These factors introduce domain shifts that undermine the generalizability of segmentation models. To address these limitations, an interactive segmentation model, CDCR-ISeg, is proposed to bridge the gap between industrial requirements and existing methodologies. A dedicated dataset comprising 1500 pixel-wise annotated UAV images (UAV-CrackX4, X8, X16) was constructed, capturing various zoom levels and domain conditions to support the model's development. CDCR-ISeg incorporates super-resolution and domain adaptation techniques to enhance model generalization while reducing annotation efforts. Additionally, a vector map is introduced to improve boundary detection by embedding positive and negative clicks with reversed vector map directions. This approach effectively enables high-precision detection of pavement distress under diverse UAV parameter settings, addressing the critical challenges of adaptability and scalability in UAV-based pavement inspection.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106141"},"PeriodicalIF":9.6,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706358","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}
Zhengguo Hu , Shibin Lin , Xiuhua Long , Yong Pang , Xiwang He , Xueguan Song
{"title":"Excavation trajectory planning for unmanned mining electric shovel using B-spline curves and point-by-point incremental strategy under uncertainty","authors":"Zhengguo Hu , Shibin Lin , Xiuhua Long , Yong Pang , Xiwang He , Xueguan Song","doi":"10.1016/j.autcon.2025.106135","DOIUrl":"10.1016/j.autcon.2025.106135","url":null,"abstract":"<div><div>The intelligence of electric shovels plays a critical role in improving excavation efficiency and safety. A key challenge in intelligent excavation is generating an optimal excavation trajectory while considering material uncertainty. Therefore, an Unmanned mining Electric Shovel Trajectory Planning method based on the Point-by-point Incremental B-spline Curve under Uncertainty (UESTP-PIBCU) is proposed in this paper. The method establishes the dynamic model of the electric shovel working mechanism and the excavation resistance model, analyzes excavation resistance uncertainty parameters using interval possibility theory. Then, a multi-objective trajectory planning model considering excavation resistance uncertainty is established, and the optimal excavation trajectory is obtained through optimization. Experimental results demonstrate that UESTP-PIBCU outperforms commonly used methods in excavation efficiency and dipper fill ratio, and operational efficiency is effectively improved. Future research will explore the impact of multi-source uncertainties on excavation trajectories, to enhance the reliability and robustness of the intelligent electric shovel system.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106135"},"PeriodicalIF":9.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143697065","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}
Linjun Lu, Alix Marie d'Avigneau, Yuandong Pan, Zhaojie Sun, Peihang Luo, Ioannis Brilakis
{"title":"Modeling heterogeneous spatiotemporal pavement data for condition prediction and preventive maintenance in digital twin-enabled highway management","authors":"Linjun Lu, Alix Marie d'Avigneau, Yuandong Pan, Zhaojie Sun, Peihang Luo, Ioannis Brilakis","doi":"10.1016/j.autcon.2025.106134","DOIUrl":"10.1016/j.autcon.2025.106134","url":null,"abstract":"<div><div>Pavement preventive maintenance is one of the most fundamental use cases when deploying digital twins (DTs) for highway infrastructure management. To achieve this, it is essential to accurately predict the pavement conditions in future years. This paper developed a Spatial-Temporal Graph Attention network (STGAT) that can effectively capitalize on both spatial and temporal dependencies while addressing inherent heterogeneity in pavement data for more accurate condition predictions. On top of this, a structured assessment procedure was introduced to determine the need for preventive maintenance on road sections based on the STGAT predictions. A case study on the highway network in the United Kingdom was conducted to evaluate the method's performance. The results showed that the proposed method can achieve superior accuracy for pavement condition prediction and subsequent preventive maintenance assessment compared to existing methods, thus signifying its potential to improve the effectiveness of DTs for highway infrastructure management.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106134"},"PeriodicalIF":9.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Digital twin-enabled safety monitoring system for seamless worker-robot collaboration in construction","authors":"Xiao Lin, Ziyang Guo, Xinxiang Jin, Hongling Guo","doi":"10.1016/j.autcon.2025.106147","DOIUrl":"10.1016/j.autcon.2025.106147","url":null,"abstract":"<div><div>Worker-robot collaboration (WRC) has emerged as a transformative approach to augmenting the productivity of the construction industry. However, the development of a safety monitoring method or system for stopping robot operations in emergency is imperative, especially for seamless WRC on site. This paper presents a digital twin-enabled safety monitoring system for seamless WRC on site, characterized by its comprehensive perception of dynamic entities and dynamic calculation of protective separation distances during seamless WRC. The effectiveness of the proposed system is substantiated through a series of experiments, the result demonstrates its proficiency in mitigating collisions during robot operation in both static and dynamic WRC scenarios. The system achieves an average monitoring rate of 9.8 frames per second, an average reaction latency of 0.177 s, and a positional perception error of 0.09 m. It not only provides a practical tool for the implementation of seamless WRC on site, but also offers valuable insights for future WRC research.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106147"},"PeriodicalIF":9.6,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143696797","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}
Pengfei Wu , Han Yuan , Bingchuan Bai , Bo Lu , Weijie Li , Xuefeng Zhao
{"title":"Embedded machine vision sensor with portable imaging device and high durability","authors":"Pengfei Wu , Han Yuan , Bingchuan Bai , Bo Lu , Weijie Li , Xuefeng Zhao","doi":"10.1016/j.autcon.2025.106143","DOIUrl":"10.1016/j.autcon.2025.106143","url":null,"abstract":"<div><div>Machine vision sensors face challenges in automating the monitoring of internal structural damage and deformation, with limited lifespan and resolution accuracy. This paper develops a high-durable machine vision strain sensor, MISS-Silica. The sensor's durability is enhanced through materials, processes, and algorithms, ensuring its lifespan aligns with that of the structure. It combines an endoscope with a smartphone, eliminating the need for fixed camera positioning, and enables embedded strain measurement. With sub-pixel accuracy, the sensor reduces reliance on camera resolution and has a measurement range of 0.05<span><math><mi>ε</mi></math></span>, covering all stages from loading to failure. The results demonstrate that MISS-Silica provides a reliable, accurate, and durable solution for long-term structural health monitoring. Future research will explore its application in diverse environments, refine miniaturization, and improve real-time, large-scale monitoring capabilities.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106143"},"PeriodicalIF":9.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681366","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":"Safety-constrained Deep Reinforcement Learning control for human–robot collaboration in construction","authors":"Kangkang Duan , Zhengbo Zou","doi":"10.1016/j.autcon.2025.106130","DOIUrl":"10.1016/j.autcon.2025.106130","url":null,"abstract":"<div><div>Worker safety has become an increasing concern in human–robot collaboration (HRC) due to potential hazards and risks introduced by robots. Deep Reinforcement Learning (DRL) has demonstrated to be efficient in training robots to acquire complex construction skills. However, neural network policies for collision avoidance lack theoretical safety guarantees and face challenges with out-of-distribution scenarios. This paper proposes a biomimetic safety-constrained DRL control system, inspired by vertebrate decision-making systems. A neural network policy serves as the ”brain” for complex decision-making, while a reference governor layer functions like the spinal cord, enabling rapid responses to environmental stimuli and prioritizing safety. Theoretical safety guarantees related to robot dynamics including torque, joint angle, velocity, and distance were analyzed. Experimental results demonstrate that the proposed method achieves a 0% collision rate, providing a safe HRC mode in both static and dynamic construction scenarios.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106130"},"PeriodicalIF":9.6,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681494","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":"Thickness optimisation in 3D printed concrete structures","authors":"Romain Mesnil, Pedro Sarkis Rosa, Léo Demont","doi":"10.1016/j.autcon.2025.106076","DOIUrl":"10.1016/j.autcon.2025.106076","url":null,"abstract":"<div><div>Layer pressing in 3D concrete printing (3DCP) allows to continuously modify the thickness of printed laces by changing adequately the robot speed. However, most applications consider a constant thickness throughout the printing and do not leverage all the possibilities from robotic technologies. The aim of this paper is to demonstrate the potential offered by thickness variation to achieve higher structural efficiency and to lower the material usage. To do so, analytical solutions for stress and buckling of tapered heavy column are recalled and highlight a potential of reduction of 25% of material for simple geometries with materials with low structuration rate. Numerical optimisation based on a penalty method and on the finite element simulation with shell elements is then implemented to minimise the volume of printed components for more complex geometries. Promising results are observed and should encourage the 3DCP community to further study this previously unexplored dimension of the process.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"174 ","pages":"Article 106076"},"PeriodicalIF":9.6,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143681493","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}