Artificial Trust as a Tool in Human-AI Teams

Artificial Trust as a Tool in Human-AI Teams

Centeio Jorge, C. (TU Delft Interactive Intelligence)
Tielman, M.L. (TU Delft Interactive Intelligence)
Jonker, C.M. (TU Delft Interactive Intelligence; Universiteit Leiden)

2022

Mutual trust is considered a required coordinating mechanism for achieving effective teamwork in human teams. However, it is still a challenge to implement such mechanisms in teams composed by both humans and AI (human-AI teams), even though those are becoming increasingly prevalent. Agents in such teams should not only be trustworthy and promote appropriate trust from the humans, but also know when to trust a human teammate to perform a certain task. In this project, we study trust as a tool for artificial agents to achieve better team work. In particular, we want to build mental models of humans so that agents can understand human trustworthiness in the context of human-AI teamwork, taking into account factors such as human teammates', task's and environment's characteristics.

HART
trustworthiness
trust
human-robot teams
human-agent
human-AI
hybrid intelligence
intelligent agents

http://resolver.tudelft.nl/uuid:2a4b6138-595f-44f2-9d26-da0eb2d60d1a

IEEE Press, Piscataway

2022-09-07

978-1-5386-8554-9

HRI '22: Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot Interaction

HRI 2022: 17th Annual ACM/IEEE International Conference on Human-Robot Interaction, 2022-03-07 → 2022-03-10, Online, Sapporo, Hokkaido, Japan

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2022 C. Centeio Jorge, M.L. Tielman, C.M. Jonker