Your Robot is Watching: Using Surface Cues to Evaluate the Trustworthiness of Human Actions

Surendran, Vidullan; Wagner, Alan R.

doi:10.1109/ro-man46459.2019.8956343

Cited by 6 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although there is some work in this direction, see e.g. [2,27,29], none of these works has tried to deconstruct trustworthiness, but rather looked at it as a simple metric. Instead, we hypothesise that we should take several dimensions into account when determining trustworthiness.…”

Section: Conceptual Modelmentioning

confidence: 99%

Assessing artificial trust in human-agent teams

Jorge

Tielman

Jonker

2022

Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents

View full text Add to dashboard Cite

As intelligent agents are becoming human's teammates, not only do humans need to trust intelligent agents, but an intelligent agent should also be able to form artificial trust, i.e. a belief regarding human's trustworthiness. We see artificial trust as the beliefs of competence and willingness, and we study which internal factors (krypta) of the human may play a role when assessing artificial trust. Furthermore, we investigate which observable measures (manifesta) an agent may take into account as cues for the human teammate's krypta. This paper proposes a conceptual model of artificial trust for a specific task during human-agent teamwork. Our model proposes observable measures related to human trustworthiness (ability, benevolence, integrity) and strategy (perceived cost and benefit) as predictors for willingness and competence, based on literature and a preliminary user study. CCS CONCEPTS• Human-centered computing → Collaborative and social computing.

show abstract

Section: Conceptual Modelmentioning

confidence: 99%

Assessing artificial trust in human-agent teams

Jorge

Tielman

Jonker

2022

Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents

View full text Add to dashboard Cite

show abstract

“…Similarly, in [21], the authors also investigate the effects of robot error on human trust with a specific focus on time-critical situations. Few different works studied trust from a different perspective, such as [24] in which the robot uses surface cues to estimate trustworthiness of the human it interacts with. Other approaches develop methods in which enable the agent to use its own confidence to decide when to ask a human to help it by providing teaching signals [7].…”

Section: Related Workmentioning

confidence: 99%

TIRL: Enriching Actor-Critic RL with non-expert human teachers and a Trust Model

Felix¹,

Sigaud²,

Chétouani³

2020

2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

View full text Add to dashboard Cite

“…[26], [27]), and 4) team trust (still recent but growing in human-AI contexts), there is little research on how an artificial agent should trust its human teammates. However, there is some work in this direction, for instance on how an artificial agent can detect that a situation requires trust [28], [29] and also how an artificial agent can detect whether a human is being trustworthy, based on episodic memory [30] and social cues [31]. Also, Azevedo-Sa et al [2] has recently proposed a model for trusting tasks in human-robot teams, making a clear distinction between natural trust (when the trustor is a human) and artificial trust (when the trustee is an artificial agent).…”

Section: Introductionmentioning

confidence: 99%