Trust calibration within a human-robot team: Comparing automatically generated explanations

Wang, Ning; Pynadath, David V.; Hill, Steven C.

doi:10.1109/hri.2016.7451741

Cited by 191 publications

(165 citation statements)

References 33 publications

Supporting

Mentioning

160

Contrasting

Order By: Relevance

“…A majority of prior work has focussed on performance-related factors, particularly robot capabilities; for example, Soh et al [9] examined the dynamics and transfer of trust in robot capabilities across tasks, where transfer is the ability to employ knowledge acquired in one task to improve performance in another [24]. Recent work has explored the role of the robot's intention, e.g., its policy [14], [25] and decision-making process [26]. This work adds to this body of literature and considers both intent and capability across tasks.…”

Section: B Trust In Automation and Robotsmentioning

confidence: 99%

Robot Capability and Intention in Trust-Based Decisions Across Tasks

Xie

Bodala

Ong

et al. 2019

2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

In this paper, we present results from a humansubject study designed to explore two facets of human mental models of robots-inferred capability and intention-and their relationship to overall trust and eventual decisions. In particular, we examine delegation situations characterized by uncertainty, and explore how inferred capability and intention are applied across different tasks. We develop an online survey where human participants decide whether to delegate control to a simulated UAV agent. Our study shows that human estimations of robot capability and intent correlate strongly with overall self-reported trust. However, overall trust is not independently sufficient to determine whether a human will decide to trust (delegate) a given task to a robot. Instead, our study reveals that estimations of robot intention, capability, and overall trust are integrated when deciding to delegate. From a broader perspective, these results suggest that calibrating overall trust alone is insufficient; to make correct decisions, humans need (and use) multi-faceted mental models when collaborating with robots across multiple contexts.

show abstract

Section: B Trust In Automation and Robotsmentioning

confidence: 99%

Robot Capability and Intention in Trust-Based Decisions Across Tasks

Xie

Bodala

Ong

et al. 2019

2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

View full text Add to dashboard Cite

show abstract

“…When humans have an accurate mental model of a robot, their subsequent interactions with this robot are safer and more seamless. This mental model may include the robot's intentions [1], [2], [3], its objectives [4], its capabilities [5], [6], or its decision-making process [7].…”

Section: Introductionmentioning

confidence: 99%

Establishing Appropriate Trust via Critical States

Huang

Bhatia

Abbeel

et al. 2018

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

In order to effectively interact with or supervise a robot, humans need to have an accurate mental model of its capabilities and how it acts. Learned neural network policies make that particularly challenging. We propose an approach for helping end-users build a mental model of such policies.Our key observation is that for most tasks, the essence of the policy is captured in a few critical states: states in which it is very important to take a certain action. Our user studies show that if the robot shows a human what its understanding of the task's critical states is, then the human can make a more informed decision about whether to deploy the policy, and if she does deploy it, when she needs to take control from it at execution time.

show abstract

“…Unlike prevailing approaches (e.g., [17,37]), a key benefit of these trust models is that they are able to leverage intertask structure and can be applied in situations where the agent (our robot) performs actions across many different tasks. As predictive models, they can be operationalized in decisiontheoretic frameworks to calibrate trust during collaboration with human teammates [5,36,23,13]. Trust calibration is crucial for preventing over-trust that engenders unwarranted reliance in robots [28,30], and under-trust that can cause poor utilization [18].…”

Section: Introductionmentioning

confidence: 99%

The Transfer of Human Trust in Robot Capabilities across Tasks

Soh

Pan

Chen

et al. 2018

Robotics: Science and Systems XIV

View full text Add to dashboard Cite

Abstract-Trust is crucial in shaping human interactions with one another and with robots. This work investigates how human trust in robot capabilities transfers across tasks. We present a human-subjects study of two distinct task domains: a Fetch robot performing household tasks and a virtual reality simulation of an autonomous vehicle performing driving and parking maneuvers. Our findings lead to a functional view of trust and two novel predictive models-a recurrent neural network architecture and a Bayesian Gaussian process-that capture trust evolution and transfer via latent task representations. Experiments show that the two proposed models outperform existing approaches when predicting trust across unseen tasks and participants. These results indicate that (i) a task-dependent functional trust model captures human trust in robot capabilities more accurately, and (ii) trust transfer across tasks can be inferred to a good degree. The latter enables trust-based robot decision-making for fluent human-robot interaction. In particular, our models can be used to derive robot policies that mitigate under-trust or over-trust by human teammates in collaborative multi-task settings.

show abstract

Trust calibration within a human-robot team: Comparing automatically generated explanations

Cited by 191 publications

References 33 publications

Robot Capability and Intention in Trust-Based Decisions Across Tasks

Robot Capability and Intention in Trust-Based Decisions Across Tasks

Establishing Appropriate Trust via Critical States

The Transfer of Human Trust in Robot Capabilities across Tasks

Contact Info

Product

Resources

About