The objective of this research was to understand the impact of transition window
duration on success and performance during nominal transitions from conditional
driving automation (SAE level 3). Because the driver can be disengaged from
driving when conditional driving automation is engaged, the central challenge is
how to safely transition from automated control to human control. Past research
from the literature on Level 3 Automated Driving Systems (L3 ADS) has focused on
safety-critical event responses (e.g., responding to a hazard) and on automation
that operates at high speeds, which is not representative of the systems
currently deployed that operate in lower-speed traffic jam situations [4, 5].
This article presents an analysis of data from several transition-of-control
studies with conditional driving automation in a high-fidelity driving
simulator. A range of transition window durations were compared, and different
transition-of-control behaviors were coded from video data. Transition windows
for 4, 6, 8, and 10 s conditions resulted in failures by the drivers to resume
control. Success rates by condition were lowest with 4 s transition windows, but
also lower with 10 s windows, compared to 6 s, 8 s, or 15 s windows (potential
explanations appear in the discussion). Time to first glance back at the forward
road and time to first-hand on the steering wheel were predictors of transition
of control success across all transition windows. Survival analyses showed that
drivers needed to begin the transition process within a few seconds to make
successful transitions, even with longer transition windows. The results
demonstrate the impact of different transition window durations on transition of
control and provide unique insights into the factors influencing transition
success in situations representative of those happening on the road now. These
results help shape understanding of the requisite time needed for safe
transition from automated to manual control and speak to the design
recommendations for human–automation interactions.