Close

Presentation

Behave Yourself! Behavioral Indicators of Trust in Human Agent Teams
DescriptionWith the rise in the complexity and number of autonomous agents placed in human agent teams
(HAT), recent research has examined the factors that influence human trust in an agent, and
elements that negatively impact this trust. (Nguyen, et al., 2023; Carmody, 2022; Hidalgo 2021). In this research, human trust in agent teammates is typically measured via self-report surveys, which can be disruptive and lack the temporal resolution needed to capture nuanced and dynamic changes in trust (Ficke et al., 2022). Alternative measurement approaches aim to unobtrusively capture measures that correlate with trust using behavioral or physiological sensors (Kong, 2017); however, studies often utilize a single measure, which can be indicative of various states unrelated to trust. This paper presents the methods and results of a simulation-based study conducted to examine the benefit of capturing multiple behaviors together as unobtrusive indicators of human trust in an agent teammate.
Event Type
Lecture
TimeTuesday, September 10th2:10pm - 2:30pm MST
LocationFlagstaff
Tracks
Human AI Robot Teaming (AI)