BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251016T135225Z
LOCATION:Grand Hall J
DTSTART;TZID=America/Chicago:20251014T135000
DTEND;TZID=America/Chicago:20251014T141000
UID:HFESAM_ASPIRE 2025_sess261_LECT267@linklings.com
SUMMARY:Explaining Trust and Proactive Takeovers in Automated Driving: A M
 achine Learning Analysis with Neural, and Gaze Metrics
DESCRIPTION:Yinsu Zhang, Xingjian Ma, Anthony McDonald, and Ranjana Mehta 
 (University of Wisconsin - Madison)\n\nDespite recent advancements towards
  fully automated vehicles (AVs), SAE L4/5 systems would likely remain limi
 ted by their operational design domains. This study attempts to explain dr
 ivers’ trust towards partially automated vehicles (L2/3) and takeover deci
 sions using gaze and neural data. Fifty-one drivers (24 females) experienc
 ed an 85-minute simulation with four traffic events manipulating AV crash 
 avoidance and silent failures. Participants were allowed to proactively ta
 ke over the AV whenever they thought it was unsafe. XGBoost inference mode
 ls were constructed with brain cortical activation and gaze metrics to pre
 dict drivers’ binary proactive takeover decisions (takeover; no-takeover) 
 and subjective trust levels (high; low). The best model achieved an area-u
 nder-the-curve (AUC) of 0.905 and predicted proactive takeover with lower 
 medial dorsolateral prefrontal cortex (DLPFC) and higher right DLPFC activ
 ations. This trend shows that proactive takeover reduces cognitive load as
  a risk-avoidance strategy. Meanwhile, models predicting subjective trust 
 had an AUC of 0.631, with fixation duration on the steering peak and left 
 DLPFC being the strongest predictors. These are reflections of trusting dr
 ivers’ goal hierarchy approach and offloading cognitive demands on the AV,
  without gaze attention on disengagement control for takeovers. Our findin
 gs provide design insights for adaptive AV using neurophysiological measur
 es.\n\nTrack: Surface Transportation\n\nSession Chairs: Shannon Roberts (U
 niversity of Massachusetts, Amherst) and Stanislaus Oshimeje (Michigan Tec
 hnological University)\n\n
END:VEVENT
END:VCALENDAR