TY - GEN
T1 - Embodied Conversational Agent Teams for Trust Calibration in Automated Vehicles
AU - Premstaller, Marie
AU - Kotsios, Heike
AU - Wintersberger, Philipp
N1 - Publisher Copyright:
© 2023 Owner/Author.
PY - 2023/9/18
Y1 - 2023/9/18
N2 - Representing sub-systems of automated vehicles with a team of conversational agents has been suggested in the past to improve the process of trust calibration. Experiments so far did not include embodied agents. In this work, we present two potential analogies derived from a company hierarchy and a spaceship crew. We developed comic strips showing everyday interactions with these agents in an automated vehicle and evaluated them in a Vignette study in comparison with single-agent approaches. Our results suggest that a multi-agent approach could be beneficial for trust calibration, but only for the company and not the spaceship analogy. Only some of the design decisions regarding the agents' personalities worked out as intended. Still, we believe the concept is promising for future investigations.
AB - Representing sub-systems of automated vehicles with a team of conversational agents has been suggested in the past to improve the process of trust calibration. Experiments so far did not include embodied agents. In this work, we present two potential analogies derived from a company hierarchy and a spaceship crew. We developed comic strips showing everyday interactions with these agents in an automated vehicle and evaluated them in a Vignette study in comparison with single-agent approaches. Our results suggest that a multi-agent approach could be beneficial for trust calibration, but only for the company and not the spaceship analogy. Only some of the design decisions regarding the agents' personalities worked out as intended. Still, we believe the concept is promising for future investigations.
KW - Automated Vehicles
KW - Conversational Agents
KW - Online Survey
KW - Trust Calibration
KW - Trust in Automation
KW - Vignette Study
UR - http://www.scopus.com/inward/record.url?scp=85173705662&partnerID=8YFLogxK
U2 - 10.1145/3581961.3609890
DO - 10.1145/3581961.3609890
M3 - Conference contribution
AN - SCOPUS:85173705662
T3 - ACM International Conference Proceeding Series
SP - 71
EP - 76
BT - 15th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, AutomotiveUI 2023 - Adjunct Conference Proceedings
PB - Association for Computing Machinery
T2 - 15th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, AutomotiveUI 2023
Y2 - 18 September 2023 through 21 September 2023
ER -