Impact of VR-Based Training on Human–Robot Interaction for Remote Operating Construction Robots

Enhancing Humans Trust in Robots through Explanations

In recent years, Sri Lanka’s construction industry has seen a troubling increase in both fatal and non-fatal accidents, largely attributed to insufficient safety knowledge among workers and deficiencies in the health and safety system. To mitigate these accidents, effective occupational health and safety training is imperative. However, the efficacy of traditional safety training methods has been questioned due to their limited impact on workers’ ability to identify and assess risks critically. The lack of experiential training is the primary cause of accidents that could have been easily avoided at construction sites in Sri Lanka. Addressing this gap, there is growing interest in utilising Virtual Reality (VR) as a powerful tool for experiential safety training in the construction sector. VR offer a realistic and safe environment where workers can engage with various scenarios and procedures, enhancing their understanding and awareness of safety protocols. This research explores the effectiveness of VR tools in enhancing safety knowledge and awareness among construction workers through a simulation safety training platform, using VR and PowerPoint methods for data collection. An experiment was conducted with VR and PowerPoint safety training methods as a data collection method. A questionnaire survey was conducted to compare conventional training methods with the VR solution. The results indicate that workers trained in VR environments had better retention of critical information, highlighting the efficiency of VR in providing a safe yet realistic training experience. This research emphasises the potential advantages of the suggested VR safety training methods in improving construction safety knowledge and awareness of construction workers.

DATA-DRIVEN APPROACH TO HOLISTIC SITUATIONAL AWARENESS IN CONSTRUCTION SITE SAFETY MANAGEMENT

The risk of major occupational accidents involving tripping hazards is commonly underestimated with a large number of studies having been conducted to better understand variables that affect situation awareness: the ability to detect, perceive, and comprehend constantly evolving surroundings. An important property that affects situation awareness is the limited capacity of the attentional system. To maintain situation awareness while exposed to tripping hazards, a worker needs to obtain feedforward information about hazards, detect immediate tripping hazards, and visually scan surroundings for any potential environmental hazards. Despite the importance of situation awareness, its relationship with attention remains unknown in the construction industry. To fill this theoretical knowledge gap, this study examines differences in attentional allocation between workers with low and high situation awareness levels while exposed to tripping hazards in a real construction site. Participants were exposed to tripping hazards on a real jobsite while walking along a path in the presence of other workers. Situation awareness was measured using the situation awareness rating technique, and subjects’ eye movements were tracked as direct measures of attention via a wearable mobile eye tracker. Investigating the attentional distribution of subjects by examining fixation-count heat maps and scan paths revealed that as workers with higher situation awareness walked, they periodically looked down and scanned ahead to remain fully aware of the environment and its associated hazards. Furthermore, this study quantitatively compared the differences between the eye-tracking metrics of worker with different situation awareness levels (low versus high) using permutation simulation. The results of the statistical analysis indicate that subjects did not allocate their attention equally to all hazardous areas of interest, and these differences in attentional distribution were modulated by the workers’ level of situation awareness. This study advances theory by presenting one of the first attempts to use mobile eye-tracking technology to examine the role of cognitive processes (i.e., attention) in human error (i.e., failure to identify a hazard) and occupational accidents.

In order to enhance the effectiveness of military training, military education authorities are very interested in the use of virtual reality (VR), which is the core technology of the 4th industrial revolution. The purpose of this paper is to analyze effects of the army’s VR-based military training. For this purpose, we draw evaluation factors of AHP through related literature and Delphi technique and divide them into two levels: equipment effects and learning effects. The sub-factors of each factors consist that equipment effects are reality, safety, and availability, and learning effects are interest, immersion, and understanding. The questionnaire for evaluation factors was composed of pairwise comparison on 9-point scales. The 14 experts who had experience of teaching the VR-based training participated in a pairwise comparison survey. As a result of this study, the top six factors determined are as follows: interest, reality, immersion, understanding, availability, and safety. The VR-based training showed higher values in term of Interest (6.3), reality (5.2), immersion (3.5), and understanding (3.1) than existing training method of video contents (VC)-based training. On the other hand, availability (0.9) and safety (0.9) were lower. It is expected that the result of this study will be used as the basic data for the military’s VR-based training policy in the future.

Effectiveness of VR-based training on improving occupants’ response and preparedness for active shooter incidents

Recently, there has been a surge in virtual reality (VR)-based training for upper limb (UL) rehabilitation, which has yielded mixed results. Therefore, we aimed to explore the effects of conventional therapy combined with VR-based training on UL dysfunction during post-stroke rehabilitation. Studies published in English before May 2023 were retrieved from PubMed, Embase, and the Cochrane Library. We also included randomized controlled trials that compared the use of conventional therapy and VR-based training with conventional therapy alone in post-stroke rehabilitation. The meta-analysis was performed using Review Manager Software (version 5.3; The Nordic Cochrane Centre, The Cochrane Collaboration; Copenhagen, Denmark) and Stata/MP 17.0 (StataCorp, LLC, College Station, TX, USA). Univariate and multivariate meta-regression analyses were performed to investigate the effects of stroke duration, VR characteristics, and type of conventional therapy on VR-based training. In total, 27 randomized controlled trials were included, which enrolled 1354 patients. Our results showed that conventional therapy plus VR-based training is better than conventional therapy alone in UL motor impairment recovery measured using Fugl-Meyer Upper Extremity (standardized mean difference [SMD] = 0.32, 95% confidence interval [CI]: 0.07-0.57, Z = 2.52, p = 0.01). Meta-regression showed that stroke duration had independent effects on Fugl-Meyer Upper Extremity scores of VR-based training in rehabilitation (p = 0.041). Furthermore, in subgroup analysis based on stroke duration, stroke duration >6 months was statistically significant (SMD = 0.20, 95% CI: 0.01-0.39, Z = 2.06, p = 0.04). No relevant publication bias (p = 0.1303), and no significant difference in activity limitation assessed using the Box-Block Test (mean difference [MD] = 2.79, 95% CI: -0.63-6.20, Z = 1.60, p = 0.11) was observed. Regarding the functional independence measured using the Functional Independence Measure scale, studies presented no significant difference between the experimental and control groups (MD = 1.15, 95% CI: -1.84-4.14, Z = 0.76, p = 0.45). Conventional therapy plus VR-based training is superior to conventional therapy alone in promoting the recovery of UL motor function after stroke. Therefore, VR-based training may be a potential option for improving UL motor function. The study was registered on PROSPERO (https://www.crd.york.ac.uk/prospero/), registration number: CRD42023472709.

In this paper, a review of the implementation of Virtual Reality (VR) with robotics and how it has changed various areas is explored. In general, VR improves efficiency and safety in operational work—especially in the energy sector, where it optimizes substation operations (e.g., increasing accuracy by up to 25% due to a higher level of automation). For mechatronics, VR allows advanced digital design, such as virtual prototyping and collaborative simulation, which significantly increase system efficiency. In education, VR technology has increased student engagement and learning outcomes by up to 40%, improving participation in subjects such as natural sciences. VR integration into robotics also enables the testing of various movements and trajectories for safety, resulting in minimal damages incurred during the design phase and increased productivity. VR also enhances human-robot interaction by enabling intuitive control based on better gesture recognition and a 35% increase in precision. In future applications, the remote operation of robots in dangerous environments will greatly improve emergency rescue efficiency and speed. Using VR for substation operations has translated to 25% better accuracy and a similar gain in terms of operational efficiency. By providing a more connected, efficient future in multiple spheres and delivering about 40% fewer accidents during simulations, the fusion of VR with robotics is an overall successful venture.

In recent years, virtual reality training technology (VRTT) has been considered by many scholars as a new training method instead of traditional training (TT) to reduce unsafe behaviors ascribed to construction workers (CWs) and corporate accident rates. However, in this process, a conflict of interest arises among the government, construction enterprises (CEs), and CWs. Therefore, this study introduces a quantitative research method, the three-party evolutionary game and creatively combining them with the product life cycle (PLC) to solve this problem by analyzing the equilibrium and evolutionarily stable strategies of the system. Finally, collaborative players' decision-making behaviors and their sensitivity to critical factors are examined. This paper will illustrate these in each stage through numerical simulations. The results of the study indicate that the government plays a dominant role in the VRTT introduction stage. When the government gives CEs appropriate subsidies, CEs will eventually realize the importance of VRTT for CWs. Then the government will gradually reduce the amount of the subsidies in this process. In addition, we also find that the continually high cost will lead to negative policies by the government, which requires the active cooperation and attitude change from CEs and CWs. Ultimately, the government, CEs and CWs adopt the best strategy in the evolutionary process to facilitate the promotion, application and sustainability of VRTT in the construction industry.

Extended-Reality Technologies: An Overview of Emerging Applications in Medical Education and Clinical Care.

Effective safety management at construction sites requires accurate hazard recognition. However, previous research studies have revealed a significant proportion of hazards remain unrecognized. Poor hazard recognition may be attributed to the deficiency at one or more levels of situational awareness (SA). Understanding how different hazard types, particularly those with high fatality rates, influence workers’ SA is critical to improving safety outcomes. To address this research gap, three hazard types with different fatality hierarchies (F-I: fall, F-II: struck-by, and F-III: electrical hazards) were built in a complex and dynamic virtual reality (VR) construction environment. Participants’ hazard recognition behaviors regarding hazard perception, comprehension, and projection (Level 1, 2, and 3 SA) were measured by a well-recognized situational awareness global assessment technique (SAGAT). The findings revealed that the achievement of SA varied among different hazard types and was impacted by fatality hierarchy. There was a consistent decline in success rates from Level 1 to Level 3 SA across all hazards, and the potential to achieve a high-level SA demonstrated a positive correlation with the hazard fatality hierarchy. Specific reasons for failure at each SA level attributed to shortcomings included a deficiency in prior knowledge, narrowed attention, and the increased demand for cognitive resources. The findings enhance the understanding of workers’ SA in hazard recognition behaviors and provide a foundation for developing customized interventions. These interventions can be tailored to address SA deficiencies at different levels based on hazard types with distinct fatality hierarchies, ultimately improving safety performance at construction sites.

Advances in robotics have led to breakthroughs in several areas, including the development of humanoid robots. There are now several different models of humanoid robots available, but operating them remains a difficult challenge. Current operator control interfaces for humanoid robots often require very experienced operators and significant amounts of time for planning. A large amount of the planning and cognitive load is attributable to the operator attempting to gain adequate three-dimensional (3D) situation awareness and task awareness while viewing an interface on a flat, two-dimensional (2D) screen. Virtual reality (VR) has enormous potential to provide benefits to allow the operator to quickly and accurately understand the state of a robot in a scanned 3D environment and to issue accurate commands with less cognitive load. In the gaming sphere, VR headsets remain a new and promising interface for playing video games. In some cases, existing video games are being ported over to VR and, in others, brand new games are being designed with VR in mind. Control schemes and best practices for VR are emerging within the video game industry. This paper aims to leverage their lessons learned and to apply them to the teleoperation of humanoid robots.

One of the directions of the economic development of the state is the construction industry, in which the issues of labor protection and improving safety are extremely acute, since its effective growth depends on the solution of this issue. With the development of scientific and technological progress, as well as digital technologies, the question of the possible application of this area in matters of ensuring the safety of production processes becomes relevant. Today, in the construction industry, BIM technologies are actively being used. BIM (Building Information Modeling) - Building information modeling is the process of creating an integrated model of the future construction project, which includes all stages of the life cycle of the project from the design stage to the dismantling stage. BIM technology is the very tool that shows how to improve the interaction of all project participants. BIM is based on a three-dimensional information model. The information model of the building means obtaining full information about the future construction site according to the most popular sections of the design documentation. This technology is a universal information platform that allows you to integrate various software modules into the BIM model of investment and construction projects. Thanks to this approach, it became possible to digitize construction production while monitoring the safety of work, as well as labor protection using a risk-oriented approach. Considering the application of this technology and the result, it can be seen that all research is aimed mainly at the work of designers. However, if we consider BIM technology as an information platform (base) on which new software products (complexes) can be superimposed, then we can create a qualitatively different approach in the application of this technology. In particular, it is possible to review the approach to the assessment of industrial safety and labor protection, in another perspective to approach the scheduling of construction schedules, consider the possibility of applying such programs in the assessment of construction and installation risks during the implementation of the investment and construction project. The article discusses 3D modeling of objects, such as a construction site. Individual areas with boundary assignment were analyzed to assess the degree of safety in these areas. To assess the state of labor protection, a breakdown of the studied object to 100 square meters was adopted. The stage of determining the most hazardous production factors, as well as possible risks that may be involved in the construction work has been investigated. According to the results of ranking of hazardous and harmful production factors, hazard zones are determined regardless of the type of construction and installation work. Based on the distribution of hazard zones (boundaries), it is possible to rank safety levels that characterize the safety situation at the construction site. The Construction Safety Index allows you to identify the processes and factors that most affect labor safety, which makes it possible for inspectors to most effectively correct the selection of protective measures at the construction site.

Trust in Robots Versus Trust in Humans

Drones are increasingly being utilized in the construction industry, offering a wide range of applications. As these drones have to work with or alongside construction professionals, this integration could pose new safety risks and psychological impacts on construction professionals. Hence, it is important to understand their perceptions and attitudes towards drones and evaluate the cognitive demand of working with or near drones. Limited research has explored individuals' perceptions of drones, particularly when engaged in construction activities at job sites. This study specifically targets construction students, the future professionals in the field, to understand their responses to drone interactions on job sites. An immersive virtual reality construction site was developed using a VR game engine, allowing construction students to interact with drones while engaging in typical construction activities. Through a user-centered experiment, the influence of drone presence on construction students' attitude, cognitive workload, and perceived safety risk was evaluated. The results suggest that presence of drones did not significantly elevate cognitive load or foster significantly negative attitudes among construction students. Instead, they perceived only mild safety risks, suggesting a general acceptance and adaptability towards drone technology in construction settings.