Computer-Aided Civil and Infrastructure Engineering最新文献

{"title":"A Point Cloud Dataset and Deep Learning Framework for Semantic Segmentation of Construction Site Point Clouds","authors":"Hongzhe Yue, Qian Wang, Maggie Y. Gao, Tao Yang, Luping Li, Keyu Chen, Mingzhu Wang","doi":"10.1016/j.cacaie.2026.100050","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100050","url":null,"abstract":"Deep learning (DL)-based semantic segmentation of point clouds for construction site holds great promise for improving site management and progress monitoring. However, there is currently a scarcity of publicly available benchmarks that specifically capture the unstructured and dynamic characteristics of active construction phases (e.g., temporary facilities and partially built structures). To bridge this gap, this study constructs an expert-annotated ConSite dataset, which contains 13 categories of structural and temporary components commonly found on construction sites. Building on this dataset, this paper proposes SiteNet, a DL model designed specifically for semantic segmentation of point clouds in construction scenes. SiteNet integrates several key modules, including an adaptive transfer learning strategy, a Directional Feature Encoding Module, a video-based point cloud augmentation method, and a smoothed focal loss function. Experimental results show that SiteNet achieves an overall accuracy of 95.73% and a mean Intersection over Union of 86.32%, outperforming representative DL baselines such as Point Transformer. Ablation experiments and cross-validation further confirm the effectiveness and generalization ability of the proposed model. This study contributes to automation in construction by enabling intelligent construction site monitoring, progress tracking, and digital twin development through automated point cloud understanding.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"101 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744154","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":"Model-Free Geometric Perception Framework for Automated Deformation Monitoring of Space Grid Structures","authors":"Yanzong Zhang, Guibo Nie, Xuelai Li, Duozhi Wang, Yu Zhang","doi":"10.1016/j.cacaie.2026.100067","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100067","url":null,"abstract":"Automated deformation monitoring of large-span space grid structures using point clouds is frequently constrained by data scarcity and a strong reliance on prior design models. To address these, a model-free geometric perception framework is proposed. First, a virtual scanning mechanism generates synthetic data with non-structural artifacts, solving data scarcity with zero annotation cost. This enables GridSegNet to achieve 95.52% mIoU, effectively eliminating semantic ambiguity at complex node-rod interfaces. Subsequently, an automated workflow is established: utilizing pre-trained models for semantic perception; employing graph theory-based topological reconstruction to build high-fidelity geometric digital twins under severe occlusion. By autonomously quantifying the discrepancy between the reconstructed axis and the inferred topological baseline, the framework generates self-referenced deformation vector fields, effectively isolating and capturing local geometric anomalies (e.g., rod buckling). The framework achieves a 0.72 mm RMSE in synthetic evaluations and is further validated through a field deployment on an actual 32 m × 21 m space grid structure. In this zero-shot real-world scenario, the system successfully identifies physical buckling with an average deviation of 0.82 mm compared to expert manual measurements while processing million-scale point clouds in 90 seconds. By bridging the semantic and topological mapping from raw scans to digital twins, this work provides robust theoretical support for constructing cognitive construction automation systems with self-referenced diagnostic capabilities.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"54 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744155","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":"3D modeling and automated measurement of concrete cracks via segment anything refinement and visual inertial LiDAR fusion","authors":"Pengru Deng, Jiapeng Yao, Chun Li, Su Wang, Xinrun Li, Varun Ojha, Xuhui He","doi":"10.1016/j.cacaie.2026.100019","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100019","url":null,"abstract":"In practical applications, AI-based concrete crack inspection still suffers from performance degradation in few-shot, unfamiliar scenarios and lacks the capability for high-precision, synchronized quantification of three-dimensional (3D) crack geometry and location without manual post-processing. To address these limitations, a systematic methodology for crack segmentation, 3D reconstruction, and automated measurement is proposed, grounded in computer vision and Simultaneous Localization and Mapping (SLAM) techniques. First, a novel prompt generation strategy and a tailored segmentation quality assessment module are developed to improve the performance of the Segment Anything Model (SAM), enabling few-shot crack segmentation with strong generalization across diverse and unseen scenarios. Second, a comprehensive concrete cracks reconstruction within a 3D representation is achieved through a newly proposed Visual Inertial LiDAR (VIL) SLAM-based fusion approach. By integrating multi-frame RGB images, LiDAR point clouds, and inertial measurements, the method enables precise alignment of crack segmentation masks with 3D structural geometry, generating high-precise, dense, and semantically enriched point clouds that capture fine-grained crack details at real-world scale. Furthermore, an automated measurement module is introduced to directly quantify detailed crack geometrical and spatial information from the established 3D representation, eliminating manual post-processing and advancing beyond traditional image-based methods. Finally, extensive experiments are successfully conducted on diverse concrete structures validating the accuracy, robustness, and effectiveness in complex, non-planar, and cluttered environments of the proposed method.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"22 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744157","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":"Anticipatory Monte Carlo tree search-based optimization for stochastic dynamic routing with time windows","authors":"Mehr Sadat Salami, Leila Hajibabai, Kuangying Li","doi":"10.1016/j.cacaie.2026.100024","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100024","url":null,"abstract":"This paper develops an anticipatory logistics optimization framework for non-profit food rescue operations to address the challenges of hunger and food waste. The study aims to distribute perishable surplus food from food banks to food-insecure households, taking into account uncertain volunteer availability, dynamic household requests, and limited transportation resources. The problem is formulated as a dynamic vehicle routing problem incorporating time windows. A Monte Carlo tree search (MCTS)-based approach is proposed that incorporates vehicle returns to depots for loading food packages. The framework utilizes stochastic rollouts to anticipate future customer arrivals and inform online routing and replenishment decisions. The numerical results indicate that the proposed MCTS framework can effectively solve the problem, outperforming conventional insertion heuristics. Compared to baseline heuristics, the proposed method achieves a 10–15% reduction in total routing cost while serving a larger number of newly arriving household requests under uncertainty.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"21 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744156","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":"Railway Track Geometry Irregularity Exceedance Prediction Based on CNN-BiLSTM-Attention and Neural-Wiener Process Fusion with Degradation Feature Diversity","authors":"Yong Zhuang, Xiaolin Li, Ziteng Wang, Yuanjie Tang, Lifen Yun","doi":"10.1016/j.cacaie.2026.100065","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100065","url":null,"abstract":"Railway track geometry prediction faces heterogeneity-data sparsity challenges: degradation dynamics vary, while inspections are sparse and irregular. Preventive maintenance further creates label-scarce, interrupted histories, invalidating direct prediction. In this study, a four-stage framework is proposed: An optimization model of degradation period division is designed based on adaptive detection of change point on trend curve. A CNN-BiLSTM-Attention model is constructed for multi-index prediction in a collaborative way. The probability distribution of the first arrival time on thresholds is estimated by integrating neural network and Wiener process. Finally, the prediction is re-corrected through a feature transformation approach. Based on six-year measured data on Wuhan-Jiujiang Railway in China and a cross-domain validation, the experiments show that the proposed method has distinct improvements compared with the existing methods in error controls for predicting both the value of track geometry and the exceedance time. This study provides theoretical and engineering support for preventive maintenance of railway tracks.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"133 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744158","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":"Energy-aware reinforcement learning for robotic manipulation of articulated components in infrastructure operation and maintenance","authors":"Xiaowen Tao, Yinuo Wang, Haitao Ding, Yuanyang Qi, Ziyu Song","doi":"10.1016/j.cacaie.2026.100015","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100015","url":null,"abstract":"With the growth of intelligent civil infrastructure and smart cities, operation and maintenance (O&amp;M) increasingly requires safe, efficient, and energy-conscious robotic manipulation of articulated components, including access doors, service drawers, and pipeline valves. However, existing robotic approaches either focus primarily on grasping or target object-specific articulated manipulation, and they rarely incorporate explicit actuation energy into multi-objective optimisation, which limits their scalability and suitability for long-term deployment in real O&amp;M settings. Therefore, this paper proposes an articulation-agnostic and energy-aware reinforcement learning framework for robotic manipulation in intelligent infrastructure O&amp;M. The method combines part-guided 3D perception, weighted point sampling, and PointNet-based encoding to obtain a compact geometric representation that generalises across heterogeneous articulated objects. Manipulation is formulated as a Constrained Markov Decision Process (CMDP), in which actuation energy is explicitly modelled and regulated via a Lagrangian-based constrained Soft Actor-Critic scheme. The policy is trained end-to-end under this CMDP formulation, enabling effective articulated-object operation while satisfying a long-horizon energy budget. Experiments on representative O&amp;M tasks demonstrate 16%-30% reductions in energy consumption, 16%-32% fewer steps to success, and consistently high success rates, indicating a scalable and sustainable solution for infrastructure O&amp;M manipulation. A repository is hosted at <ce:inter-ref xlink:href=\"https://github.com/allen-legged-robot/csac-arm-rl\" xlink:type=\"simple\">https://github.com/allen-legged-robot/csac-arm-rl</ce:inter-ref>.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"23 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744159","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 Mechanisms of Polyphenol-Grafted Submicron Mineral Fillers Regulating Fracture Resistance of Asphalt Mixtures across Oxidative Aging States","authors":"Jiao Jin, Shuai Liu, Hao Xu, Hanbo Li, Yao Deng, Kunfeng Ma, Mingzeng Zhang, Tao Zhu, Huiwen Chen, Yalong Zhang, Zhuang Wen, Jianlong Zheng","doi":"10.1016/j.cacaie.2026.100066","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100066","url":null,"abstract":"Oxidative aging stiffens asphalt mixtures and accelerates cracking, and aging-induced polarity shifts weaken the asphalt-mineral interface. This study grafts submicron basalt fillers with catechol or gallic acid and incorporates them into asphalt mixtures to regulate aging-related damage. Fracture is evaluated by semi-circular bending with simultaneous acoustic emission (AE) and digital image correlation. RA and AF features are extracted from AE; a Gaussian mixture model in RA-AF space identifies tensile, shear, and boundary events using posterior probability ≥ 0.60, avoiding empirical divider lines. Lower temperature and greater aging shift the response toward brittleness, with higher peak load, reduced peak displacement, and steeper post-peak softening. Polyphenol-grafted fillers moderate the post-peak drop and reduce high-amplitude bursts, indicating more gradual damage accumulation. Across all conditions, tensile events dominate (51.2%-86.4%), shear events are secondary (11.5%-43.4%), and boundary events rise to ∼31% in specific temperature-aging combinations. Molecular dynamics simulations show pronounced interfacial segregation of asphalt fractions (relative peaks ∼4-7 near the mineral surface); gallic-acid functionalization yields smoother, more consistent profiles across aging states, implying improved microstructural stability. Overall, polyphenol-grafted submicron fillers—especially gallic acid—mitigate aging-related cracking by stabilizing interfacial organization and reshaping the fracture damage sequence.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"63 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744161","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":"Towards next-generation autonomous structural health monitoring and inspection with humanoid robots","authors":"Zhen Wang, Yuqing Gao, Ying Zhou, Jialong He, Jiaxin Peng, Wensheng Lu","doi":"10.1016/j.cacaie.2026.100007","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100007","url":null,"abstract":"Humanoid robots have recently drawn increasing attention due to their anthropomorphic morphology, high degrees of freedom, and integrated multimodal sensing capabilities, and they have been explored in a range of robotics and engineering applications. However, their potential for structural health monitoring remains largely unexplored. Current indoor SHM practices still rely primarily on manual inspection or on mobile robotic platforms with limited adaptability and flexibility, which constrains inspection efficiency and operational coverage in complex indoor environments. Motivated by this gap, this study proposes RoboInspect, an end-to-end autonomous inspection framework that employs a full humanoid robot for indoor civil infrastructure inspection. RoboInspect comprises three key modules: (i) a reinforcement learning–based locomotion controller trained and deployed on humanoid hardware, (ii) an autonomous navigation and path-planning pipeline that leverages prior maps together with onboard perception, and (iii) a vision-based perception module for structural crack detection in indoor inspection scenarios. These modules are designed to operate in coordination to support repeated, goal-driven indoor inspection tasks. The framework is evaluated through two representative case studies conducted in a university building, covering first-floor common areas and a stair landing with an adjacent corridor. Under controlled experimental conditions, the system demonstrates reliable autonomous navigation along predefined inspection routes and effective crack detection, with a minimum detectable crack width exceeding 0.2 mm. These results provide preliminary evidence supporting the feasibility of humanoid robots as inspection agents for civil engineering infrastructure.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"101 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744160","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":"Vision-driven state-space imitation learning for quadrotor navigation in infrastructure inspection","authors":"Xiaowen Tao, Yinuo Wang, Bing Zhu, Jiayi Han, Peixing Zhang, Pengxiang Meng, Jinzhao Zhou, Chin-Teng Lin","doi":"10.1016/j.cacaie.2026.100030","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100030","url":null,"abstract":"With the rapid development of intelligent civil infrastructure and smart cities, quadrotors are increasingly deployed for inspection, monitoring, and emergency response in infrastructure environments, such as power transmission corridors, transportation greenbelts, and urban green infrastructure. Reliable quadrotor navigation in such environments requires robust perception-driven decision making to safely avoid obstacles while maintaining operational efficiency. However, existing quadrotor navigation approaches often rely on handcrafted heuristics, task-specific planning, or reinforcement learning methods with high training cost and limited stability, which restrict their applicability in safety-critical infrastructure scenarios. To address these challenges, this paper proposes a vision-driven imitation learning framework with state-space models for quadrotor navigation in infrastructure inspection environments. The approach leverages a privileged expert to generate large-scale demonstration data in simulation, from which a vision-based navigation policy is trained via imitation learning. Depth-based visual observations and proprioceptive states are encoded into compact representations and processed by a selective state-space model to capture long-horizon temporal dependencies and motion continuity. The learned policy outputs high-level navigation commands, which are executed through a geometric control module, facilitating stable and physically consistent deployment. Extensive simulation experiments in representative infrastructure navigation scenarios demonstrate that the proposed method reduces collision occurrences and energy consumption, while producing smoother and more temporally consistent trajectories than state-of-the-art baselines, even at high flight speeds. The results indicate that the proposed framework provides a robust, computer-aided solution for safe quadrotor navigation in civil infrastructure inspection environments. A repository is hosted at <ce:inter-ref xlink:href=\"https://github.com/allen-legged-robot/quadrotor-mamba\" xlink:type=\"simple\">https://github.com/allen-legged-robot/quadrotor-mamba</ce:inter-ref>.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"8 8 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744171","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":"Balancing confidence and precision in real-time bus arrival time prediction with uncertainty quantification","authors":"Beiyu Song, Changlin Li, Edward Chung, Hongbo Ye","doi":"10.1016/j.cacaie.2026.100006","DOIUrl":"https://doi.org/10.1016/j.cacaie.2026.100006","url":null,"abstract":"Accurate and reliable real-time bus arrival time (BAT) predictions are crucial for improving passenger satisfaction and operational efficiency. Existing pointwise BAT prediction models have demonstrated their effectiveness in estimating single values close to the true arrival time. However, there is a lack of research on quantifying the uncertainties associated with these predictions, which is essential for better passenger planning and enhancing the credibility and reliability of bus operators. This paper introduces UncertBAT, a novel framework designed to address this gap. UncertBAT provides not only the predicted BAT but also an arrival time window with a high degree of confidence. The model incorporates conformalized quantile regression and a grouping calibration mechanism to address challenges posed by data skewness and variability, ensuring an optimal balance between prediction confidence and precision. Several experiments conducted in the study demonstrate the model’s effectiveness in BAT prediction. Additionally, the model exhibits high flexibility in generating optimal arrival time windows that meet specific confidence requirements or precision-based requirements in related uncertainty-aware tasks.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"14 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147744162","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}