BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Phoenix
X-LIC-LOCATION:America/Phoenix
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19700101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241014T203101Z
LOCATION:Flagstaff
DTSTART;TZID=America/Phoenix:20240911T113500
DTEND;TZID=America/Phoenix:20240911T115500
UID:HFESAM_ASPIRE - Presented by HFES_sess197_LECT515@linklings.com
SUMMARY:Assessing AI Social Aptitude Using Crowd Sourced Cognitive Labels
DESCRIPTION:Lecture\n\nMd Fazle Elahi and Jiachen Jiang (Purdue University
 ), Joshua Domeyer (Toyota Collaborative Safety Research Center), and Renra
 n Tian (North Carolina State University)\n\nIn the pursuit of effective hu
 man-AI cooperation, understanding and aligning with human social cognition
  is critical. This paper investigates the capacity of algorithms to imitat
 e human social behaviors, particularly in cooperative scenarios such as au
 tomated cars interacting with pedestrians. While existing studies have dev
 eloped prediction models for pedestrian intentions, the subjective nature 
 of cognitive labels and temporal variations pose challenges to accurately 
 imitate human socialization. We introduce the Human-Like index (HL-i) as a
  novel metric to assess algorithmic social aptitude during interaction pro
 cesses. Through empirical experiments and analyses, we address three resea
 rch questions regarding AI social performance and human discernment of AI-
 generated outputs. Findings reveal significant variability in algorithmic 
 mimicry of human behavior across scenarios, with HL-i serving as a crucial
  indicator of alignment with human cognitive patterns. The study underscor
 es the complexity of human social cognition and proposes HL-i as a valuabl
 e tool for enhancing algorithmic social aptitude.\n\nTrack: Human AI Robot
  Teaming (AI)\n\nSession Chair: Xiaoyun Yin (Arizona State University)
END:VEVENT
END:VCALENDAR