Artificial Trust as a Tool in Human-AI Teams

Carolina Centeio Jorge; Myrthe L. Tielman; Catholijn M. Jonker

Artificial Trust as a Tool in Human-AI Teams

Carolina Centeio Jorge, Myrthe L. Tielman, Catholijn M. Jonker

Interactive Intelligence

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

93 Downloads (Pure)

Abstract

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.

Original language	English
Title of host publication	HRI '22
Subtitle of host publication	Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot Interaction
Place of Publication	Piscataway
Publisher	IEEE
Pages	1155-1157
Number of pages	3
ISBN (Print)	978-1-5386-8554-9
Publication status	Published - 2022
Event	HRI 2022: 17th Annual ACM/IEEE International Conference on Human-Robot Interaction - Online, Sapporo, Hokkaido, Japan Duration: 7 Mar 2022 → 10 Mar 2022 https://humanrobotinteraction.org/2022/

Conference

Conference	HRI 2022: 17th Annual ACM/IEEE International Conference on Human-Robot Interaction
Abbreviated title	HRI '22
Country/Territory	Japan
City	Sapporo, Hokkaido
Period	7/03/22 → 10/03/22
Internet address	https://humanrobotinteraction.org/2022/

Bibliographical note

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.

Keywords

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

Access to Document

3523760.3523956 (1)Final published version, 178 KB

https://dl.acm.org/doi/abs/10.5555/3523760.3523956

Cite this

@inproceedings{2a4b6138595f44f29d26da0eb2d60d1a,

title = "Artificial Trust as a Tool in Human-AI Teams",

abstract = "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.",

keywords = "HART, trustworthiness, trust, human-robot teams, human-agent, human-AI, hybrid intelligence, intelligent agents",

author = "{Centeio Jorge}, Carolina and Tielman, {Myrthe L.} and Jonker, {Catholijn M.}",

note = "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.; HRI 2022: 17th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI '22 ; Conference date: 07-03-2022 Through 10-03-2022",

year = "2022",

language = "English",

isbn = "978-1-5386-8554-9",

pages = "1155--1157",

booktitle = "HRI '22",

publisher = "IEEE",

address = "United States",

url = "https://humanrobotinteraction.org/2022/",

}

Centeio Jorge, C , Tielman, ML & Jonker, CM 2022, Artificial Trust as a Tool in Human-AI Teams. in HRI '22: Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot Interaction. IEEE, Piscataway, pp. 1155-1157, HRI 2022: 17th Annual ACM/IEEE International Conference on Human-Robot Interaction, Sapporo, Hokkaido, Japan, 7/03/22. <https://dl.acm.org/doi/abs/10.5555/3523760.3523956>

Artificial Trust as a Tool in Human-AI Teams. / Centeio Jorge, Carolina ; Tielman, Myrthe L.; Jonker, Catholijn M.
HRI '22: Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot Interaction. Piscataway: IEEE, 2022. p. 1155-1157.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Artificial Trust as a Tool in Human-AI Teams

AU - Centeio Jorge, Carolina

AU - Tielman, Myrthe L.

AU - Jonker, Catholijn M.

N1 - 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.

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

KW - HART

KW - trustworthiness

KW - trust

KW - human-robot teams

KW - human-agent

KW - human-AI

KW - hybrid intelligence

KW - intelligent agents

M3 - Conference contribution

SN - 978-1-5386-8554-9

SP - 1155

EP - 1157

BT - HRI '22

PB - IEEE

CY - Piscataway

T2 - HRI 2022: 17th Annual ACM/IEEE International Conference on Human-Robot Interaction

Y2 - 7 March 2022 through 10 March 2022

ER -

Artificial Trust as a Tool in Human-AI Teams

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this