BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20261009T184111Z
LOCATION:Summit Pavilion
DTSTART;TZID=America/Los_Angeles:20261021T173000
DTEND;TZID=America/Los_Angeles:20261021T183000
UID:HFESAM_ASPIRE 2026_sess257_POST304@linklings.com
SUMMARY:Eyes off the road: Where Drivers Look When ADAS Control Authority 
 Changes
DESCRIPTION:Ramkumaar Ekambaram Thondaiman, Jesudara Omidokun, Duha Alkurd
 i, and Sai Dheeraj Koundinya Chunduru (University of Michigan, Dearborn); 
 John K. Lenneman (Toyota Collaborative Safety Research Center); and Areen 
 Alsaid (University of Michigan, Dearborn)\n\nAs Level 2 driver assistance 
 becomes standard in production vehicles, drivers continuously supervise au
 tomation that varies widely in how features are bundled together and how s
 ystem states are communicated to the driver, which we term ADAS architectu
 re. But does this architecture actually shape where drivers look, and how 
 effectively they manage control transitions? \nThis study examined three A
 DAS architectures: Modular (each feature activated separately within its o
 wn boundaries), Integrated (functions bundled under a single control logic
  that transitions automatically based on context), and Hybrid (longitudina
 l functions combined while lateral control remains separate). Thirty-six d
 rivers completed a fixed-base simulator drive while gaze was tracked using
  a deep-learning estimation pipeline synchronized with simulator telemetry
 . Functional capabilities were held constant: only the coupling and commun
 ication of control authority varied across conditions. \nThe results revea
 led that the Hybrid architecture produced the most stable, road-focused ga
 ze and the least unnecessary interface checking, while Modular drivers spe
 nt significantly more time verifying status on the HUD. Lateral control co
 nsistently elicited the most stable monitoring, suggesting steering automa
 tion is especially sensitive to architectural design. These findings posit
 ion ADAS architecture as a key design criterion for shaping driver visual 
 attention in Level 2 systems.\n\n
END:VEVENT
END:VCALENDAR
