This course provides participants with (1) a basic understanding of intersection safety issues, (2) “how to” information for common safety tasks and low cost safety improvements that do not require an engineered design, and (3) background information on safety tasks that do not require an engineer.
This proposal will develop machine-learning algorithms using real-time vehicle, pedestrian, and infrastructure data to improve our understanding of how people drive on highways and urban roads. These models will help monitor and support the transportation systems to accommodate both human-driven and automated vehicles.
The primary goal of this project is to define and document JFK Cargo View requirements, evaluating the options and costs to acquire, develop, and manage the system, exploring potential business models to operate and monetize it, and establishing an implementation plan to develop and deploy it.
The goal of this proposal is to develop and assess an innovative real-time proactive safety monitoring system based on the trajectory of road users (e.g., cars, pedestrians, and cyclists) collected by video cameras.
This proposal will develop a digital twin for urban mobility, the Mobi-Twin platform, focusing on enabling the microscopic accurate modeling and simulation of Urban Mobility System of Systems with the emerging self-driving grade high-resolution 3D data.
Researchers at the Rutgers Center for Advanced Infrastructure and Transportation continue to conduct important work and take on new challenges in transportation during the ongoing COVID-19 Pandemic. Here are some of our recent highlights.
Columbia University recently announced 10 faculty teams that were each awarded $85,000 to develop innovative technology for New York City during COVID-19. CAIT-affiliated researcher Dr. Sharon Di was among one of those faculty teams selected for a project developing a crowd management systems for public transit systems.