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:20251016T135135Z
LOCATION:Grand A
DTSTART;TZID=America/Chicago:20251015T133000
DTEND;TZID=America/Chicago:20251015T135000
UID:HFESAM_ASPIRE 2025_sess211_LECT401@linklings.com
SUMMARY:Human-AI Interaction Dynamics with Voice-Driven Autonomous Pilots 
 in MEDEVAC Operations
DESCRIPTION:Sanya Doda, Richard Agbeyibor, Carmen Jimenez Cortes, Jack Kol
 b, Jose Magalhaes, and Karen Feigh (Georgia Institute of Technology)\n\nWh
 ile autonomous systems advance, human involvement remains crucial in criti
 cal domains like medical evacuation, where precise human discernment is es
 sential. In our study, we explored human-AI collaboration between an AI Pi
 lot (AP) and a medical professional in simulated MEDEVAC situations. We re
 cruited 22 primarily licensed medical professionals with limited AI or avi
 ation experience who managed patient care and communicated with the AP usi
 ng voice commands. Participants faced medical and aviation emergencies in 
 four increasingly complex scenarios in our realistic flight simulator. The
 y engaged in bi-directional communication with the AP to make decisions, e
 xecute commands, and respond to requests. Metrics included NASA-TLX and SA
 RT scores, task performance, trust measures (iTHAu and Merritt), and voice
  feature usage.\n \nThe results demonstrated an effective interaction with
  the AP. As expected, as scenario complexity increased, workload increased
 , while situational awareness declined. A general upward trend in trust in
  AP was observed, with an anticipated decline during scenarios where the A
 P provided suboptimal suggestions. The voice feature was predominantly emp
 loyed during situations of uncertainty rather than higher workload situati
 ons.\n \nIn conclusion, this study demonstrates that human-AI collaboratio
 n is feasible but further research  is needed to understand the subtle asp
 ects of these interactions in dynamic, safety-critical settings.\n\nTrack:
  Aerospace Systems, Human AI Robot Teaming (AI)\n\nSession Chairs: Briana 
 Sobel (Embry-Riddle Aeronautical University) and Xiaoyun Yin (Arizona Stat
 e University; Center for Human, Artificial Intelligence, and Robot Teaming
 )\n\n
END:VEVENT
END:VCALENDAR