Passenger Emotional Response Type and Timing during Automated Vehicle Intersection Negotiation

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.