Journal of Computing in Civil Engineering

With the construction sector primed to incorporate such advanced technologies as artificial intelligence (AI), robots, and machines, these advanced tools will require a deep understanding of human–robot trust dynamics to support safety and productivity. Although other disciplines have broadly investigated human trust-building with robots, the discussion within the construction domain is still nascent, raising concerns because construction workers are increasingly expected to work alongside robots or cobots, and to communicate and interact with drones. Without a better understanding of how construction workers can appropriately develop and calibrate their trust in their robotic counterparts, the implementation of advanced technologies may raise safety and productivity issues within these already-hazardous jobsites. Consequently, this study conducted a systematic review of the human–robot trust literature to (1) understand human–robot trust-building in construction and other domains; and (2) establish a roadmap for investigating and fostering worker–robot trust in the construction industry. The proposed worker–robot trust-building roadmap includes three phases: static trust based on the factors related to workers, robots, and construction sites; dynamic trust understood via measuring, modeling, and interpreting real-time trust behaviors; and adaptive trust, wherein adaptive calibration strategies and adaptive training facilitate appropriate trust-building. This roadmap sheds light on a progressive procedure to uncover the appropriate trust-building between workers and robots in the construction industry.

This study investigated the utilization of images collected from low-quality dash cameras on passenger vehicles for the estimation of traffic-related air pollution (TRAP). We conducted mobile monitoring along Taiwan Avenue, Taichung, Taiwan, and collected pollution concentration data including carbon dioxide (${\mathrm{CO}}_2$), nitrogen oxides (${\mathrm{NO}}_x$), black carbon (BC), and particle number (PN). Dash cameras record images that reveal the environment through which the vehicle passes. Image semantic information such as the proportion of sky, buildings, traffic, and vegetation can be extracted through deep learning models. Training of deep learning models requires the pixel-level labeling of each image, which is labor intensive. We propose the use of publicly available data sets for the training of the deep learning model. Transfer learning was utilized to customize the model for locally collected, unlabeled, low-quality dash camera images. TRAP was estimated with a hybrid model consisting the land-use regression (LUR) and image semantic information. With a five-fold cross-validation, the hybrid model with transfer learning resulted in improved $R^2$ values for ${\mathrm{CO}}_2$ ($R^2=0.81$), ${\mathrm{NO}}_{\mathrm{x}}$ ($R^2=0.64$), PN ($R^2=0.65$), and BC ($R^2=0.87$). Public labeled data sets and transfer learning may be helpful when labeled data are difficult to acquire in the local region. This work demonstrates the adaptation of image semantic information, extracted from videos captured from vehicle dash cameras, into a LUR model to improve pollutant estimation.

The visibility of pavement markings is one of the most critical factors for traffic safety, and a periodical assessment plan is crucial for maintaining this function. Traditional assessment methods, such as visual windshield surveys or manual testing using handheld devices, are unsafe, time-consuming, and labor-intensive. In recent years, transportation agencies have begun to adopt the use of mobile retroreflectivity units (MRUs) for condition assessment of pavement markings. MRUs, different from other manual methods, can be utilized to collect large-scale retroreflectivity data in an efficient manner. However, no relevant research has yet proposed a mathematical optimization model for arranging the evaluation schedule and paths of MRUs. This study aims to propose a MRU routing model, and an efficient solution methodology. A branch-and-price algorithm, including column generation and branch-and-bound, was implemented. Computational experiments have been conducted based on actual tasks from the Florida MRU program for validation. Results show that the proposed solution methodology with a set partitioning model in this study not only finds the optimal solution for problems with tasks less than 60, but also effectively narrows the solution gap to be within 1.0% for problems with tasks less than 131.

Deep learning-based scan-to-building information models (BIMs) approaches have gained popularity in generating as-built BIMs for highway bridges. However, several critical challenges emerge. First, the acquisition of large-scale training data is prohibitively expensive. Second, the complex geometry of bridges, such as variable curvature and cross sections, poses difficulties for modeling. Lastly, these generated models often lack a parametric definition. To address these challenges, this paper introduces an enhanced scan-to-BIM framework that uses low-cost synthetic point clouds and parametric modeling. This approach contains two main components: (1) semantic segmentation using augmented datasets, and (2) a projection-based parametric modeling method. Through rigorous experiments, it is evident that augmenting the training process with synthetic data significantly improves model performance, yielding up to a 12.2% segmentation improvement in this work. In terms of modeling, the reconstructed model showed a marginal mean difference of 0.06 m against the ground truth. Notably, when applied to real-world bridges, the framework demonstrated a comparable accuracy level, with deviations primarily stemming from occlusions in the bridge abutments. In conclusion, this study highlights the effectiveness of the proposed framework in creating as-built BIM models for highway bridges. Additionally, it emphasizes the significance of combining synthetic and real data for optimal accuracy and proves its potential in modern highway infrastructure applications.

In the architecture, engineering, and construction (AEC) fields, computing and information technologies play an increasingly prevalent and complex role in day-to-day work. Consequently, educators must adjust and, in many cases, reimagine curricula and teaching methodologies to adapt to the changing landscape. Past research efforts led by the ASCE Computing Division Education Committee, formerly called the Task Committee on Computing Education of the Technical Council on Computing and Information Technology (TCCIT), have regularly surveyed AEC educators to understand computing trends in AEC curricula, with the latest survey taking place nearly a decade ago. This work presents the results of an updated survey that used this prior work as a springboard, providing timely insights into the computing skills and curricular barriers faced by AEC educators today. The results showed that the technical skills used by students have evolved, but the barriers faced in incorporating new skills into curricula have remained largely the same. In addition to comparisons with prior surveys, this work presents the results of an expanded, open-ended portion of the survey that explores educator perspectives on the future of the AEC workforce in a broader lens than used in previous surveys. Thematic analysis of these open-ended responses revealed themes that were common among responses and provided organization to the findings. For example, educators provided their vision of what competencies the future AEC workforce would need, which were thematically organized into a continuum based on the level of interaction between humans and technology. These results suggest an increasingly complex and evolving relationship between the AEC workforce and emerging technology, highlighting the need for educators to encourage the development of technological adaptability and agility. Overall, this work provides a systematic comparison of current educational practices in AEC computing with a decade ago to illustrate educational shifts and adds a prediction of AEC trends from experts in AEC education, providing crucial discussion of curricular transformations that will better position students for success in the workforce.

Wearable biosensors, in conjunction with machine learning, have been employed to develop less invasive monitoring techniques for assessing stress among construction workers during fieldwork. However, existing techniques face limitations in terms of scalable field application due to their subject and context dependency; it is difficult to apply them to new people in new contexts without additional labeled data collection. Therefore, this study developed a stress detection technique that incorporates domain adaptation, simultaneously learning a classifier and a subject- and context-independent features, in this way advancing generalizability. The proposed technique consistently demonstrated superior accuracy compared with benchmarks in classifying stress levels within a testing data set whose subjects and contexts were different from those of training data sets. Thus, the technique can advance generalizability across subjects and contexts. This finding can help us to reliably detect stress for new people in new contexts without additional labeled data collection, thereby contributing to scalable field application of wearable-based stress monitoring at construction sites.

This study aimed to investigate the key technical and psychological factors that impact the architecture, engineering, and construction (AEC) professionals’ trust in collaborative robots (cobots) powered by artificial intelligence (AI). This study seeks to address the critical knowledge gaps surrounding the establishment and reinforcement of trust among AEC professionals in their collaboration with AI-powered cobots. In the context of the construction industry, where the complexities of tasks often necessitate human–robot teamwork, understanding the technical and psychological factors influencing trust is paramount. Such trust dynamics play a pivotal role in determining the effectiveness of human–robot collaboration on construction sites. This research employed a nationwide survey of 600 AEC industry practitioners to shed light on these influential factors, providing valuable insights to calibrate trust levels and facilitate the seamless integration of AI-powered cobots into the AEC industry. Additionally, it aimed to gather insights into opportunities for promoting the adoption, cultivation, and training of a skilled workforce to effectively leverage this technology. A structural equation modeling (SEM) analysis revealed that safety and reliability are significant factors for the adoption of AI-powered cobots in construction. Fear of being replaced resulting from the use of cobots can have a substantial effect on the mental health of the affected workers. A lower error rate in jobs involving cobots, safety measurements, and security of data collected by cobots from jobsites significantly impact reliability, and the transparency of cobots’ inner workings can benefit accuracy, robustness, security, privacy, and communication and result in higher levels of automation, all of which demonstrated as contributors to trust. The study’s findings provide critical insights into the perceptions and experiences of AEC professionals toward adoption of cobots in construction and help project teams determine the adoption approach that aligns with the company’s goals workers’ welfare.

In the context of the unstructured and fast-changing construction environment, the adaptability of robots to human improvisation is crucial. However, existing construction robots are limited in understanding spatial goals communicated spontaneously in the workplace and require substantial human-user training. Incorporating deictic gestures into human–robot interfaces holds promise for enhancing the intuitive operation of construction robots and for on-site collaboration. However, applying deictic gestures in precision-demanding construction tasks presents challenges because in a large-scale work environment, humans have limited accuracy in pointing at objects at a distance. This study introduces LaserDex, a novel interface for distant spatial tasking based on a global-to-local identification approach, in which the human first guides the robot toward the general area of the task using a deictic gesture and then indicates the precise area by dynamically using a laser pointer. Our user study with 11 participants demonstrated that LaserDex can achieve an intersection over union (IoU) of 0.830 when outlining a rectangular drywall opening (compared with an IoU of 0.514 for the baseline, a handheld controller), and an 11.4-mm distance error of the center of the estimated rectangle compared with the center of the targeted rectangle. The findings of this study underscore the potential of LaserDex to seamlessly combine intuitive human–robot interaction with precise robot operations.