Drivers’ Performance Examination using a Personalized Adaptive Curve Speed Warning: Driving Simulator Study

ABSTRACT

A great number of traffic accidents occur during curve negotiation maneuvers. Most of these accidents could be avoided if drivers are provided with information that better guide them through the maneuver. Advanced Driver Assistance Systems (ADAS) such as Curve Speed Warning (CSW) have shown to be effective to improve safety on curve maneuvers by warning drivers of the speed required to make a safe curve maneuver. The effectiveness of such warning systems can potentially improve if the warnings are not only adapted to road and traffic condition but also adapted to individual drivers’ behavior. In this study, an Adaptive Curve Speed Warning (ACSW) system is developed that presents drivers a two-level visual and audio warning considering the variation in individual drivers’ perception-reaction time (PRT). The warning timing is adjusted according to a reward/punishment function to reinforce safer actions while providing an individualized in-time warning. Next, within a driving simulator environment, drivers’ performance using ACSW is compared to a CSW that does not consider PRT variation among drivers. Further, variation in drivers’ performance on curve maneuvers is discussed with respect to drivers’ approaching speed, variation in PRT, and braking behavior. Results show that drivers’ interaction with warning systems varies significantly based on their age and gender. In addition, results show how drivers approaching speed to a curve varies significantly based on road characteristics such as curve advisory speed and curve direction. Results from this study contribute to the development of more intelligent ADAS that could improve drivers’ comfort and safety.

Additional information

Funding

The authors wish to thank the University Grants Program (UGP) at San Diego State University for sponsoring this study.

Notes on contributors

Alidad Ahmadi

Alidad Ahmadi (Civil Engineering, San Diego State University, 2017) is a Transportation Engineer at Linscott, Law & Greenspan Engineers. As a graduate researcher at SDSU Smart Transportation Analytics Research Lab, Alidad has conducted research on topics including drivers’ safety, human behavior studies by simulator, big data cleansing, and statistical analysis.

Sahar Ghanipoor Machiani

Sahar Ghanipoor Machiani, PhD (Civil Engineering, Virginia Tech, 2014), is an Assistant Professor of San Diego State University (SDSU) Department of Civil Engineering, and an Associate Director (SDSU Director) of Safe-D National University Transportation Center. She has expertise in traffic safety, driver behavior modeling, traffic signal operation, and evacuation modeling.