Passenger Emotional Response Type and Timing during Automated Vehicle Intersection Negotiation

Abstract

Most automated vehicle studies have focused on limited automation where the role of the user is that of a driver, supervisor or fallback, but comparatively fewer have considered riders. If riders’ experiences are ignored, it could undermine the adoption of the technologies and, consequently, the realization of their anticipated benefits. A driving simulator study was conducted to evaluate the response of riders to intersection negotiation with conservative, moderate, or aggressive automated driving styles. Riders’ emotional responses—operationalized as changes in facial action units—were detected using video processing software. Results showed that changes in speed, acceleration, and jerk preceded changes in the facial action units and were associated with the magnitude of the change. The speed, acceleration, and jerk changes were represented in different automated driving styles that then affected the magnitude and timing of emotion response. Facial action units may provide a way to gauge riders’ emotional responses to vehicle control algorithms could be used to improve rider experiences.

Bimodal Trust: High and Low Trust in Vehicle Automation Influence Response to Automation Errors

“…Pilot study data from the manual driving scenarios guided the development of the automated driving style. The aggressive, moderate, and conservative styles were determined using the 15th, 50th, and 85th percentile of driv-ers’ manual driving data such as mean deceleration, mean ac-celeration, distance to the stop line when the speed first goes below 1 mph during the approach to stop-controlled intersec-tions and stop duration at stop-controlled intersections (Domeyer et al, 2019; Kamaraj et al, 2023; J. D. Lee et al, 2021).…”

The DataScope: A Mixed-Initiative Architecture for Data Labeling

“…In the field of human factors, researchers are frequently faced with the challenge of labeling qualitative human data (e.g., interviews, images, videos). Oftentimes, however, labeling human data requires task-specific knowledge, such as driving (Alsaid, Lee, Roberts, Barrigan, & Baldwin, 2018;Domeyer, Alsaid, Liu, & Lee, 2019. ) Hence, in this paper, we propose a method to speed up the data labeling process without compromising human expertise.…”