Modeling the Interplay between Human Trust and Monitoring

Zahedi, Zahra; Sreedharan, Sarath; Verma, Mudit; Kambhampati, Subbarao

doi:10.1109/hri53351.2022.9889475

Cited by 5 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most prominently, recent works have tried to map trust in human‐aware terms (cf. Zahedi, Sreedharan, and Kambhampati 2023). Also, while the basic psychological validity of the framework has been established through multiple user studies that have been performed over the years (Chakraborti et al.…”

Section: Discussionmentioning

confidence: 98%

“…Most prominently, recent works have tried to map trust in human-aware terms (cf. Zahedi, Sreedharan, and Kambhampati 2023). Also, while the basic psychological validity of the framework has been established through multiple user studies that have been performed over the years Grover et al 2020), there is always scope to further build and expand the framework as we uncover more insights into the human mental processes driving these interactions.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Human‐aware AI —A foundational framework for human–AI interaction

Sreedharan

2023

AI Magazine

View full text Add to dashboard Cite

We are living through a revolutionary moment in AI history. Users from diverse walks of life are adopting and using AI systems for their everyday use cases at a pace that has never been seen before. However, with this proliferation, there is also a growing recognition that many of the central open problems within AI are connected to how the user interacts with these systems. To name two prominent examples, consider the problems of explainability and value alignment. Each problem has received considerable attention within the wider AI community, and much promising progress has been made in addressing each of these individual problems. However, each of these problems tends to be studied in isolation, using very different theoretical frameworks, while a closer look at each easily reveals striking similarities between the two problems. In this article, I wish to discuss the framework of human‐aware AI (HAAI) that aims to provide a unified formal framework to understand and evaluate human–AI interaction. We will see how this framework can be used to both understand explainability and value alignment and how the framework also lays out potential novel avenues to address these problems.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Discussionmentioning

confidence: 99%

Human‐aware AI —A foundational framework for human–AI interaction

Sreedharan

2023

AI Magazine

View full text Add to dashboard Cite

show abstract

“…However, most of their work considers humans as observers without much humanrobot cooperation. In (Zahedi, Sreedharan, and Kambhampati 2022), the authors pointed out the importance of a richer mental modeling framework that allows human-robot collaboration, which we provide a viable way of filling the gap.…”

Section: Related Workmentioning

confidence: 99%

Adaptation and Communication in Human-Robot Teaming to Handle Discrepancies in Agents’ Beliefs about Plans

Zhang

Williams

2023

ICAPS

View full text Add to dashboard Cite

When agents collaborate on a task, it is important that they have some shared mental model of the task routines -- the set of feasible plans towards achieving the goals. However, in reality, situations often arise that such a shared mental model cannot be guaranteed, such as in ad-hoc teams where agents may follow different conventions or when contingent constraints arise that only some agents are aware of. Previous work on human-robot teaming has assumed that the team has a set of shared routines, which breaks down in these situations. In this work, we leverage epistemic logic to enable agents to understand the discrepancy in each other's beliefs about feasible plans and dynamically plan their actions to adapt or communicate to resolve the discrepancy. We propose a formalism that extends conditional doxastic logic to describe knowledge bases in order to explicitly represent agents' nested beliefs on the feasible plans and state of execution. We provide an online execution algorithm based on Monte Carlo Tree Search for the agent to plan its action, including communication actions to explain the feasibility of plans, announce intent, and ask questions. Finally, we evaluate the success rate and scalability of the algorithm and show that our agent is better equipped to work in teams without the guarantee of a shared mental model.

show abstract

“…Theory of Mind becomes all the more important in Human-Robot Interaction to facilitate improved behavior synthesis [8, 9, 11, 26-28, 47, 48, 69] and engender Human-Robot trust [14,[65][66][67][68]. Prior works have either assumed a human mental model [9] or learned it through interaction [56,69].…”

Section: Introductionmentioning

confidence: 99%

Theory of Mind Abilities of Large Language Models in Human-Robot Interaction: An Illusion?

Verma,

Bhambri,

Kambhampati

2024

Companion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction

Self Cite

View full text Add to dashboard Cite

Figure 1: Fetch executes the maneuver to pick the block and takes a step (towards robot's) left indicating its choice of goal as Loc2 (instead of the alternative Loc3) thereby being legible. Left : Fetch executes the maneuver. Center : Fetch has a label on its head stating "Not a Legible robot" in a small font which the human observer is unable to read. Right : Human has a blurred view of Fetch making them unable to comment on whether the robot is being legible. Robot expects the LLM (human proxy) to "think what the 'human would think of the robot's behavior'"

show abstract

Modeling the Interplay between Human Trust and Monitoring

Cited by 5 publications

References 10 publications

Human‐aware AI —A foundational framework for human–AI interaction

Human‐aware AI —A foundational framework for human–AI interaction

Adaptation and Communication in Human-Robot Teaming to Handle Discrepancies in Agents’ Beliefs about Plans

Theory of Mind Abilities of Large Language Models in Human-Robot Interaction: An Illusion?

Contact Info

Product

Resources

About