Safe-D: Safety through Disruption

Countermeasures to Detect and Combat Inattention While Driving Partially Automated Systems

Abstract

This project will investigate and develop countermeasures for problems that can arise when human drivers are required to recognize a fault and assume manual control of a vehicle which is partially-automated. Researchers at Texas A&M University (TAMU) and Texas A&M Transportation Institute will collaborate with those at Virginia Tech Transportation Institute (VTTI) to complete and integrate two research thrusts. The VTTI group will develop and refine a Driver Monitoring System (DMS) for automated vehicles which will estimate the level of attentiveness the driver gives to driving tasks that may require human input and/or taking over from automation control. The TAMU team will first perform an extensive literature review to define a set of failure scenarios in which human action (or inaction) following automation faults could contribute substantially to driving performance and/or safety. These scenarios will be developed in a driving simulator at TAMU, which will be used to conduct a human subjects study to evaluate driving performance with and without various types of multisensory cues (visual, auditory, tactile, and combinations) designed to guide attention to relevant displays and controls. This study will identify the most promising cuing system for guiding attention to these areas of interest, and for easing the transition into manual control for the required task. Finally, researchers at both institutions will combine the products of their research to implement and test the cuing system in a partially-automated vehicle on a controlled test track at VTTI. A short qualitative pilot study will be conducted to validate the usefulness of the cuing system in more realistic driving contexts designed to encourage inattentiveness, and possibly using a Wizard-of-Oz style triggering of cues based on similar logic being developed for the DMS. This effort will also serve as a partial proof-of-concept to springboard future development in this research toward an integrated system that combines DMS attentiveness assessment and cuing to mitigate driver inattentiveness.

Final Report

Coming soon!

EWD/T2 Products

Coming soon!

Presentations/Publications

Suh, Y. and Ferris, T. (2018). On-road evaluation of in-vehicle interface characteristics and their effects on performance of visual detection on the road and manual entry. Human Factors, 61(1), 105-118. DOI: 10.1177/0018720818790841 (Published)

McKenzie, J., Zahed, K., Warner, J., Uster, H., and Ferris, T.K. (2018). Survey and modeling approach to predicting driver turnover in long-haul trucking. Proceedings of the Human Factors and Ergonomics Society 62nd Annual Meeting. Philadelphia, PA, October. 1383-1383. (Published)

Rodriguez Paras, C., Ferris, T.K. (2018). A model for characterizing startle in driving contexts. Proceedings of the Human Factors and Ergonomics Society 62nd Annual Meeting. Philadelphia, PA, October. (Published)

Research Investigators (PI*)

Thomas Ferris (TTI/TAMU)*
Miao Song (VTTI/VT)
Mike Mollenhauer (VTTI/VT)

Project Information

Start Date: 2017-05-25
End Date: 2018-10-31
Status: Active
Grant Number: 69A3551747115
Total Funding: $178,162
Source Organization: Safe-D National UTC
Project Number: 01-002

Safe-D Theme Areas

Automated Vehicles

Safe-D Application Areas

Driver Factors and Interfaces
Planning for Safety
Vehicle Technology

More Information

RiP URL
UTC Project Information Form

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

Virginia Polytechnic Institute and State University
Virginia Tech Transportation Institute
3500 Transportation Research Plaza
Blacksburg, Virginia 24061
USA