Evaluating Safety of Mechanisms that Transit Control from Autonomous Systems to Human Drivers

Abstract

Driver-automation co-piloting, a driving mode under which autonomous driving systems and human drivers accomplish driving tasks cooperatively is expected to be widely used to reduce driver workload in future driving. The work presented in this paper focuses on safety evaluation of the transition mechanism between autonomous system and human drivers. A group of two-factor experiments, in which two factors are: (1) advance responding time for drivers: 15s,45s, (2) notification modes to drivers: audio, visual, audio/visual, were performed to quantitatively measure driver workload by using eye tracking data, which is highly relevant to driving safety. The results of these experiments indicate that drivers' workloads increased more smoothly when given audio notification and more responding time during transitions. The research has brought about a solution to ensure a good level of driving safety in co-piloting.