Presentation
Identifying Preferred Driving Styles of Automated Vehicles through Drivers’ Feedback
DescriptionDriving style preferences in automated vehicles (AVs) is one topic that has received less attention. Personalized driving styles in AVs can improve drivers’ trust and acceptance. However, little is known about the ways in which drivers identify and communicate their preferred driving styles to AVs. Also, most studies have focused on normal driving situations, without considering how vehicles handle risky or off-nominal scenarios. In this study, we examined how drivers find and choose their preferred driving style by allowing participants to provide feedback to adjust the AV’s driving behavior. A driving simulator study was conducted whereby drivers experienced one of four predefined driving styles, categorized by their level of conservativeness in terms of safety and speed in navigating road obstacles. Thirty-two participants completed 10 driving trials where they provided feedback to an AV regarding whether to change or maintain its driving style. Overall, drivers preferred the AV to maintain the same driving style it had displayed in previous trials. Drivers also preferred a driving style that was closer to natural driving experiences, i.e., neither too aggressive nor too conservative. This study can help inform the development of adaptive algorithms that preemptively adjust driving style without drivers’ explicit inputs.
Event Type
Lecture
TimeWednesday, October 15th1:30pm - 1:50pm CDT
LocationGrand Hall L
Surface Transportation
Similar Presentations