VTTI researchers are using advanced machine learning and statistical methods to examine key characteristics of high G-force events and their connection with crashes and develop machine-learning models that can help predict crashes from high G-force events in real-time.
As part of a research project (Data Mining Twitter to Improve Automated Vehicle Safety), Safe-D researchers have created guidelines for automated vehicle crash responses to help public information officers structure their communications about crashes.
States are required to have access to annual average daily traffic (AADT) for all public paved roads, including non-Federal aid system (NFAS) roadways. The expectation is to use AADT estimates in data-driven safety analysis. Because collecting data on NFAS roads is financially difficult, agencies are interested in exploring affordable ways to estimate AADT. The goal of this project was to determine the accuracy of AADT estimates developed from alternative data sources and quantify the impact of AADT on safety analysis. The researchers compared 2017 AADT data provided by the Texas Department of Transportation (DOT) and the Virginia DOT against probe-based AADT estimates supplied by StreetLight Data Inc. Further, the research team developed safety performance functions (SPFs) for Texas and Virginia and performed a sensitivity analysis to determine the effects of AADT on the results obtained from the empirical Bayes (EB) method that uses SPFs. The results showed that the errors stemming from the probe AADT estimates were lower than those reported in a similar study that used 2015 AADT estimates. The sensitivity analysis revealed that the impact of AADT on safety analysis mainly depends on the size of the network, the AADT coefficients, and the overdispersion parameter of the SPFs.
Fueled by the inevitable changes in our transportation system, the Safety through Disruption (Safe-D) University Transportation Center (UTC) endeavors to maximize the potential safety benefits of disruptive technologies through targeted research that addresses the most pressing transportation safety questions. With the outstanding leadership of the Virginia Tech Transportation Institute and the Texas A&M Transportation Institute in a mentoring collaboration with the new transportation research group at San Diego State University, a Hispanic-serving institute known for educating the transportation workforce, our geographically balanced consortium encompasses the largest collection of transportation safety researchers in the nation and provides unparalleled expertise, facilities, and resources to conduct impactful research towards our long-term vision. The Safe-D Center will focus its efforts in three key areas: (1) cutting-edge research by leading transportation safety experts and their students; (2) education and workforce development with programs for all levels from grade school through college to continuing education for professionals; and (3) fully supported technology transfer including practitioner training partnerships, social networking, commercialization, and intellectual property management.
The mission of Safe-D is to proactively promote safety through a data-driven collaboration among the nation’s brightest researchers.
The vision of Safe-D is a nation with a systemically safe transportation system.
The Safe-D consortium was assembled by the Director, Dr. Zachary Doerzaph, with the expressed intent to make significant progress toward a nation with systemically safe travel through research, education and workforce development, and technology transfer efforts.