Evaluate driver response to active warning system in level-2 automated vehicles.

As vehicles with automated functions become more prevalent on U.S. roadways, maintaining driver attention while the vehicle is engaged in automation will be an important consideration for safe operation of these vehicles. The objective of this paper is to evaluate how drivers respond and adapt to active safety warning signals in a Level 2 automatic vehicle. Specifically, statistical analysis was conducted to evaluate whether the amount of inattention prompts that drivers received changed over time, possibly indicating a change in the amount of inattention that drivers exhibited. The driving performance data was collected from sixteen participants who drove a Level 2 vehicle in an experimental setting, as part of the study Human Factors Evaluation of Level 2 and Level 3 Driving Concepts. A proprietary driver inattention warning system was installed on the experiment vehicles. The system would send a warning signal if the driver's attention was not on the primary driving task for a pre-specified duration. This study focuses on driver's response when experiencing prompts after two seconds of inattention while operating a Level 2 vehicle in automated mode. The results show that on average, the frequency of prompts the participants received decreased over the course of the experiment from 29.9 in the first ten minutes to 18.1/10 min after 110 min. The decrease levelled off after about two hours. The fact that participants received fewer prompts over time suggests that they had fewer instances of inattention lasting at least two seconds as the experiment progressed. This suggests that drivers would adapt to the alert and adjust their behavior to avoid triggering the inattention alert. The results of this study provide evidence for a potential benefit of incorporating a prompting system in vehicles with automated functions.

[1]  Feng Guo,et al.  Driver crash risk factors and prevalence evaluation using naturalistic driving data , 2016, Proceedings of the National Academy of Sciences.

[2]  Mica R. Endsley,et al.  Design and Evaluation for Situation Awareness Enhancement , 1988 .

[3]  T. Jung,et al.  Task performance and eye activity: predicting behavior relating to cognitive workload. , 2007, Aviation, space, and environmental medicine.

[4]  Michael J. Goodman,et al.  NHTSA DRIVER DISTRACTION RESEARCH: PAST, PRESENT, AND FUTURE , 2001 .

[5]  T. Dingus,et al.  Distracted driving and risk of road crashes among novice and experienced drivers. , 2014, The New England journal of medicine.

[6]  Mica R. Endsley,et al.  Toward a Theory of Situation Awareness in Dynamic Systems , 1995, Hum. Factors.

[7]  Guy H. Walker,et al.  Feedback and driver situation awareness (SA): A comparison of SA measures and contexts , 2008 .

[8]  Jeremy D Sudweeks,et al.  An Analysis of Driver Inattention Using a Case-Crossover Approach On 100-Car Data: Final Report , 2010 .

[9]  Charles A. Green,et al.  Human Factors Issues Associated with Limited Ability Autonomous Driving Systems: Drivers’ Allocation of Visual Attention to the Forward Roadway , 2017 .

[10]  David M. Neyens,et al.  Assessing drivers’ performance when automated driver support systems fail with different levels of automation , 2014 .

[11]  Natasha Merat,et al.  How do Drivers Behave in a Highly Automated Car , 2017 .

[12]  Thomas A. Dingus,et al.  The Impact of Driver Inattention on Near-Crash/Crash Risk: An Analysis Using the 100-Car Naturalistic Driving Study Data , 2006 .

[13]  Charlene Hallett,et al.  Driver distraction and driver inattention: definition, relationship and taxonomy. , 2011, Accident; analysis and prevention.

[14]  Miguel A. Perez,et al.  The effects of age on crash risk associated with driver distraction. , 2016, International journal of epidemiology.

[15]  W. Stroup Generalized Linear Mixed Models: Modern Concepts, Methods and Applications , 2012 .

[16]  Feng Guo,et al.  Statistical Methods for Naturalistic Driving Studies , 2019, Annual Review of Statistics and Its Application.