Can virtual reality tools be used to train engineers that inspect work zones? In this paper, we share the findings of a research project that developed an interactive and immersive training platform using virtual reality to train state department of transportation (DOT) staff that inspect work zones for compliance. Virtual reality offers an immersive platform that closely replicates the actual experience of an inspector driving through a work zone, but in a safer, cheaper, and quicker way than field visits. The current training practice involves reviewing temporary traffic control procedures, and reports and pictures from previous inspections. The developed platform consists of a learning module and an immersive module. The learning module is founded on the historical knowledge gained by DOT staff from inspections dating back at least 5 years. This knowledge incorporated representative inspection reports from previous years from all DOT districts including photographs of deficiencies. The synthesized knowledge was converted into a concise easy-to-consume format for training. The immersive module places the trainee in a vehicle moving through a work zone, thus providing a realistic experience to the engineer before inspecting a real work zone. The research team developed and tested two immersive scenarios of a freeway work zone. The training platform was tested by 34 individuals that worked for the Missouri Department of Transportation. An overwhelming majority (97%) agreed that virtual reality offered a realistic and effective way to train inspectors.
Traffic congestion is a serious problem in the Seoul metropolitan area in Korea, as the city has sprawled drastically over the past several decades. Although the area has a considerable length of expressways, commuters travelling on them ironically suffer from recurrent traffic congestion. The present study focused on the factors that lead commuters to depend on expressways regardless of the disadvantages in terms of travel costs and even travelling times. The impact of commuters' behavioural or attitudinal latent propensities on determination of their usual route for their commute to work was investigated based on a binary logit choice model. Route- and individual-specific variables, which have been widely adopted in conventional route choice studies, were also included in the model. A total of 522 commuters participated in the survey and provided actual information of the routes they used to travel to work. The results showed that behavioural or attitudinal latent determinants other than travel times and costs also contributed to commuters' dependence on expressways.
Natural disasters such as hurricanes and pandemics cause significant disruption in people's lives. This research aims to model such disasters' transportation impacts using state-of-the-art simulation methods, statistical and machine learning algorithms. Specifically, two case studies of disasters were studied. First, the effects of various travel demand management and network control strategies on hurricane evacuation of the Hampton Roads region in Virginia were modeled. A mesoscopic simulation model was updated using demand data generated from a household survey effort. The results indicated that phased evacuation scenarios performed the best in terms of travel times, evacuating volumes, and clearance times. Also, the use of lane-reversal on a major interstate evacuation route was shown to be effective in several scenarios. The household survey also asked respondents to provide their preferred route types in the event of a hypothetical Category 4 hurricane evacuation. The responses were used to understand better which factors contribute to evacuees selecting freeway vs. non-freeway evacuation routes. A mixed (random parameters) logit model was developed to determine factors that influence evacuees deciding between a freeway and a non-freeway route. The study found that several factors contribute to evacuees choosing a freeway over other routes. In the descending order of importance (i.e., marginal effects), these factors are willing to use the official recommended route, living in a single-family or duplex housing, expected travel time to reach the destination, being employed, and possessing prior evacuation experience. Conversely, a few factors had a negative effect on choosing a freeway. These factors are willingness to evacuate two days before landfall and evacuating to a public shelter or a second home. This study's findings can help emergency management and transportation agencies design effective demand management and traffic control plans to evacuate regions during a hurricane safely. The second case study involved the modeling of travel impacts of COVID-19 pandemic. Using New York County (i.e. Manhattan) as an example, publicly available location-based mobility data from Google and COVID-19 data from government sources were used to build mobility prediction models. Three machine learning algorithms, Regression Tree, Random Forest, and Extreme gradient boosting (XGBoost) were used to develop different models. Among the three models, the Random Forest models performed the best at predicting mobility index with mean absolute percentage errors of 5.3 percent and 5.8 percent at transit stations, 6.5 percent and 7.1 percent for retail and recreation activities. These models enable accurate forecasting of expected mobility by taking into account time series data of activity and COVID variables.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.