Abstract
Introducing automation into the vehicle fleet disrupts how vehicles operate and potentially affects what drivers do with these features and expect from vehicle performance. Therefore, it is imperative to study driver adaptations in response to these innovations. This investigation leveraged 47 vehicles from the Virginia Tech Transportation Institute Level 2 (L2) Naturalistic Driving Study to analyze driver behavior with L2 automation features. Results showed no sizeable differences between periods of L2 feature usage and general driving periods with respect to time-of-day and calendar-related metrics. Most L2 feature usage occurred on motorways, following design expectations. L2 features were activated for 7.2 minutes in trips lasting an average of 22.8 minutes, or about 32% of the L2 trip duration. Driver-initiated overrides were predominantly done by braking or accelerating the vehicle, with steering-based overrides being minimal and likely involving lane changes without using a turn signal. Intervention requests were the most common takeover request, followed by requests due to insufficient driver hand contact with the steering wheel. Findings suggest that as L2 features penetrate the U.S. fleet in non-luxury consumer vehicles, system usage will be common and comparable with previous findings for luxury offerings. While evidence of potential system misuse was observed, future work may further operationalize system misuse and assess the prevalence of such behaviors.
Project Highlights
- The findings suggest that as L2 features penetrate the US fleet in non-luxury consumer vehicles, usage of the systems will be quite common and comparable with previous findings for luxury offerings.
- Findings also indicate that excessive misuse of the systems may not be as prevalent as initially expected.
Final Report
EWD & T2 Products
Educational Module which provides background of this area of research and guides students through relevant analysis approaches. Solutions to exercises available here.
Student Impact Statement(pdf): Five Graduate level students from Virginia Tech University received funding under this project (Nicholas Britten, Paolo Terranova, Haden Bragg, Mariette Metrey, and Martha Gizaw). This file contains a statement by all five students as to the impact this project had on education and workforce development.
Dictionary to standardize the system states of ADAS technologies, particularly those related to L2 automation features. The dictionary is available on the SAGE advance TransportRxiv as a publicly available preprint here.
A human-in-the-loop machine-assisted approach for inferring L2 feature activation state from video of a vehicle’s instrument panel (see the Appendix in the final report).
Virginia Tech Science Festival, Blacksburg, VA, November 2019, exhibit focused on vehicle instrumentation and related data, over 6,000 attendees, Nicholas Britten and Miguel Perez.
Presentations/Publications
Coming Soon!
Final Dataset
The final datasets for this project are located in the Safe-D Collection on the VTTI Dataverse; DOI: 10.15787/VTT1/42MUF1.
Research Investigators (PI*)
Miguel Perez (VTTI)*
Jon Hankey (VTTI)
Nick Britten (Student-VT)
Haden Bragg (Student-VT)
Mariette Metrey (Student-VT)
Paolo Terranova (Student-VT)
Project Information
Start Date: 2019-08-10
End Date: 2023-08-09
Status: Complete
Grant Number: 69A3551747115
Total Funding: $869,677
Source Organization: Safe-D National UTC
Project Number: VTTI-00-024
Safe-D Theme Areas
Big Data Analytics
Automated Vehicles
Safe-D Application Areas
Driver Factors and Interfaces
Vehicle Technology
More Information
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
Virginia Polytechnic Institute and State University
Virginia Tech Transportation Institute
3500 Transportation Research Plaza
Blacksburg, Virginia 24061
USA