Abstract
The large-scale assessment of how driving behavior affects traffic safety and ongoing surveillance is hindered by data collection difficulties, small sample sizes, and high costs. Connected vehicles (CV) now offer massive volumes of observed driving behavior data from newer vehicles with myriad electronics and sensors that monitor the state of the vehicle, environmental conditions, and the driver’s actions. This project evaluated the viability of CV data in roadway safety applications with the objective of improving existing predictive crash methods, measuring traffic speed and its relationship to crashes, and determining whether CV data could be used to evaluate pavement marking products. The research team developed safety performance functions (SPFs) for rural two-lane segments and urban intersections in Texas. The results showed that the SPFs improved with the addition of hard braking and hard acceleration counts in a majority of areas. Further, a variety of CV speed measures were generated from the CV data and were shown to have conflicting correlations with crash risk and counts. Lastly, the research team developed the data processing methods for evaluating pavement marking products but was unable to perform an evaluation due to the lack of detailed construction project records.
Project Highlights
- The research team developed a cloud-based architecture to spatially process and analyze billions of data points from connected vehicles.
- The results showed that connected vehicle driver events, like hard braking, can help improve crash prediction models for rural, 2-lane segments and urban intersections.
- Very large data sets, like connected vehicle data, can supplement existing data to help explain roadway conditions and crash potential.
Final Report
EWD & T2 Products
Student Impact Statement(pdf): Three undergraduate students from Texas A&M University worked on this project (Sophia Stutes in Computer Science, Faiza Hasan in Environmental Geoscience and Michael Potter in Statistics). This file contains a statement by Michael Potter as to the impact this project had on education and workforce development.
Educational Module: Leveraging Connected Vehicle Data for Roadway Safety Applications. The lecture was prepared for a PhD-level course CARC 601 titled, Foundations in Research. The course introduced connected vehicle data to the students and illustrate roadway safety applications.
Transportation Research Lecture Series on CV data. College Station , Texas: online presentation. March 4, 2021. Summary here.
Presentations/Publications
Martin, M. (2022, October 27). How Universities are Using Big Data for Mobility Innovation. Wejo Webinar. Bryan, Texas: webinar.
Martin, M. (2022, May 26). Introduction of connected vehicle data to TTI research staff and individual in-person meetings to discuss research ideas for the data;. Wejo visits to TTI. Bryan, Texas: presentation.
Martin, M. (2022, February 8). Putting CV Data to Work. Texas Transportation Forum. San Antonio, Texas: presentation.
Martin, M. (2022, September 2). Turning Data into Automotive Insights. MOVE America Conference Austin, TX; Roundtable discussion of the application of CV data. Austin, Texas: presentation.
Martin, M. (2023, January 24 &27th). AVID student visit to TTI. Elementary school students were introduced to connected vehicle data. Bryan, Texas: presentation.
Martin, M. (2023, April 27). Connected-Car data: Unpacking different approaches to generating meaningful safety metrics. ITS America Conference. Grapevine, Texas: presentation.
Martin, M., & Li, X. (2021, April 19). 3M Wet Pavement Marking: Surrogate Safety Measure Evaluation. Discussion with 3M about using CV data to evaluate pavement marking products. College Station, Texas: online presentation.
Martin, M., Chrysler, S., & Turner, S. (2022, July 26-27). Putting CV Data to Work. In-depth discussion and presentation of connected vehicle data to Wejo and TTI. Bryan, Texas: presentation.
Martin, M., Turner, S., & Chrysler, S. (2021, January 19). Data for Transportation: Past, Present, Future. Discussion with 3M about transportation data. Bryan, Texas: presentation.
Martin, M., Turner, S., Ramezani, M., & Wu, L. (2022, September 2). CV Data Privacy. Data privacy discussion with Wejo executives, TxDOT Data Privacy Officer, and TTI research staff and directors. Bryan, Texas: presentation.
Martin, M., Wu, Lingtao, and Ramezani, M. (2023, November 15). Connected Vehicle Data Safety Applications. Webinar SafeD Virtual Webinar is available here. PDF of PowerPoint slides from Webinar available here.
Final Dataset
The final datasets for this project are located in the Safe-D Collection on the VTTI Dataverse; DOI: 10.15787/VTT1/GO97E4
Research Investigators (PI*)
Michael Martin (TTI/TAMU)*
Shawn Turner (TTI/TAMU)
Xiao Li (TTI/TAMU)
Eva Shipp (TTI/TAMU)
Lingtao Wu (TTI/TAMU)
Sophia Stutes (TTI/TAMU)
Xinyue Ye (TTI/TAMU)
Project Information
Start Date: 2020-02-01
End Date: 2023-08-01
Status: Complete
Grant Number: 69A3551747115
Total Funding: $344,550 (Phase 1: $75,000 Phase 2: $269,550)
Source Organization: Safe-D National UTC
Project Number: TTI-05-01
Safe-D Theme Areas
Big Data Analytics
Connected Vehicles
Safe-D Application Areas
Planning for Safety
Risk Assessment
Operations and Design
Infrastructure Technology
More Information
UTC Project Information Form
UTC Project Information Form Phase II
Sponsor Organization
Office of the Assistant Secretary for Research and Technology
University Transportation Centers Program
Department of Transportation
Washington, DC 20590 United States
Performing Organization
Texas A&M University
Texas A&M Transportation Institute
3135 TAMU
College Station, Texas 77843-3135
USA