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:20261012T210904Z
LOCATION:Summit Pavilion
DTSTART;TZID=America/Los_Angeles:20261021T173000
DTEND;TZID=America/Los_Angeles:20261021T183000
UID:HFESAM_ASPIRE 2026_sess257_POST162@linklings.com
SUMMARY:From Code to Collaboration: A Cognitive Agent Framework for Large 
 Language Model (LLM)-Based Human-Vehicle Teaming
DESCRIPTION:Jingjie Wang and Brandon Pitts (Purdue University)\n\nAs autom
 ated vehicles become more advanced, safe use will depend not only on vehic
 le performance, but also on how well people understand, trust, and coordin
 ate with automated systems. However, current research on LLM-based driving
  systems remains fragmented, and there is no unified framework explaining 
 how LLMs can be integrated into automated vehicles to support human-vehicl
 e teaming. This study examines how large language models (LLMs), such as c
 onversational artificial intelligence (AI) systems, can support human-vehi
 cle collaboration. A systematic review of recent studies on LLM-based syst
 ems in driving contexts was conducted, and prior research was categorized 
 into a four-capability framework: perception and awareness, reasoning and 
 decision-making, action and control, and interaction and communication. Fi
 ndings show that LLMs can help vehicles describe driving scenes, reason ab
 out safety risks, explain decisions, support takeover communication, and i
 mprove shared situational awareness. However, risks such as hallucinations
 , weak physical grounding, unpredictable reasoning, and real-time delays s
 uggest that LLMs should not be treated as standalone vehicle controllers. 
 Instead, they should serve as high-level cognitive partners that coordinat
 e with verified safety-critical vehicle modules. This review highlights th
 e need for human-centered, safety-focused LLM driving systems that support
  transparency, calibrated trust, authority sharing, and collaboration betw
 een human drivers and automated vehicles.\n\n
END:VEVENT
END:VCALENDAR