Joint Mind Modeling for Explanation Generation in Complex Human-Robot Collaborative Tasks

Gao, Xiaofeng; Gong, Ran; Zhao, Yizhou; Wang, Shu; Shu, Tianmin; Zhu, Song‐Chun

doi:10.1109/ro-man47096.2020.9223595

Cited by 28 publications

(25 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In therapeutic and medical settings, a robot can administer routine medical surveys (Varrasi et al, 2019) independent of the doctor's social biases (Briggs et al, 2015), provide therapy sessions for routine cognitive behavioral therapy (Dino et al, 2019) or physical therapy (Meyer and Fricke, 2017), and perform other general therapeutic tasks (Agrigoroaie et al, 2016;Fan et al, 2016;Salichs et al, 2018;Alimardani et al, 2020). Finally, a robot's assistance can vary based on its social role, such as a concierge robot performing different social behaviors when responding to children or adults (Mussakhojayeva et al, 2017), an advicegiving robot providing explanations when a user's behaviors become non-optimal (Gao et al, 2020) or a robot that gives cooking advice varying its strategies so that the advice is more readily received (Torrey et al, 2013).…”

Section: Human Brainmentioning

confidence: 99%

Helping People Through Space and Time: Assistance as a Perspective on Human-Robot Interaction

2022

View full text Add to dashboard Cite

As assistive robotics has expanded to many task domains, comparing assistive strategies among the varieties of research becomes increasingly difficult. To begin to unify the disparate domains into a more general theory of assistance, we present a definition of assistance, a survey of existing work, and three key design axes that occur in many domains and benefit from the examination of assistance as a whole. We first define an assistance perspective that focuses on understanding a robot that is in control of its actions but subordinate to a user’s goals. Next, we use this perspective to explore design axes that arise from the problem of assistance more generally and explore how these axes have comparable trade-offs across many domains. We investigate how the assistive robot handles other people in the interaction, how the robot design can operate in a variety of action spaces to enact similar goals, and how assistive robots can vary the timing of their actions relative to the user’s behavior. While these axes are by no means comprehensive, we propose them as useful tools for unifying assistance research across domains and as examples of how taking a broader perspective on assistance enables more cross-domain theorizing about assistance.

show abstract

Section: Human Brainmentioning

confidence: 99%

Helping People Through Space and Time: Assistance as a Perspective on Human-Robot Interaction

2022

View full text Add to dashboard Cite

show abstract

“…Dearth, capture the gunner, defend the pass, don't starve together, reconnaissance missions overcooked [22,23,31,[36][37][38] PO: Score [36], efficiency [37],…”

Section: Real-time Cooperative Games and Simulationsmentioning

confidence: 99%

“…mission success [38] PB: Protecting or sacrificing teammate [22,23] AP: Player identity (humanness) [31], perceived helpfulness, efficiency [37], trust, understandability [38] I-TC: AI vs. human [31,36] I-TC: AI vs. presumed-human [22,23] I-E: Score visible [23] M-TP: Communication: different modalities [36]/ explanation types [37,38]/ skill, reliability [38] Dependability: Visibility of score on treatment of AI teammate [23] Humans act differently in presumed social context [22] Online players value co-presence [36] Positive effect: Staying close to other player on correct identification (AI or human) [31] Positive effect: explanation on non-experts' performance [37]/on performance if facilitating decision-making [38] Design Mood board-, bridge-, drone-, accessory-, game level-design [24-26, 39, 40] PO: Strength mass ratio [25], quality, novelty [40], range, velocity, payload, cost [26] PB: Design effort, search strategy, mental workload [26], solution exploration [24] AP: Usefulness, inspirational [24], fun,…”

Section: Real-time Cooperative Games and Simulationsmentioning

confidence: 99%

Complex Problem Solving through Human-AI Collaboration: Literature Review on Research Contexts

Memmert¹,

Bittner²

2022

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Solving complex problems has been proclaimed as one major challenge for hybrid teams of humans and artificial intelligence (AI) systems. Human-AI collaboration brings immense opportunities in these complex tasks, in which humans struggle, but full automation is also impossible. Understanding and designing human-AI collaboration for complex problem solving is a wicked and multifaceted research problem itself. We contribute to this emergent field by reviewing to what extent existing research on instantiated human-AI collaboration already addresses this challenge. After clarifying the two key concepts (complex problem solving and human-AI collaboration), we perform a systematic literature review. We extract research contexts and assess them considering different complexity features. We thereby provide an overview of existing and guidance for designing new, suitable research contexts for studying complex problem solving through human-AI collaboration and present an outlook for further work on this research challenge.

show abstract

“…It is also possible that the AI agent may be trying to update both M R h and M H . This might be the case in joint workspaces where the AI agent needs to both communicate its intentions and actions to update M R h and express what it expects the human to do and thus update M H [15].…”

Section: Updating M R Hmentioning

confidence: 99%

A Mental-Model Centric Landscape of Human-AI Symbiosis

Abbaszadeh¹,

Sreedharan²,

Kambhampati³

2022

Preprint

View full text Add to dashboard Cite

There has been significant recent interest in developing AI agents capable of effectively interacting and teaming with humans. While each of these works try to tackle a problem quite central to the problem of human-AI interaction, they tend to rely on myopic formulations that obscure the possible inter-relatedness and complementarity of many of these works. The human-aware AI framework was a recent effort to provide a unified account for human-AI interaction by casting them in terms of their relationship to various mental models. Unfortunately, the current accounts of human-aware AI are insufficient to explain the landscape of the work doing in the space of human-AI interaction due to their focus on limited settings. In this paper, we aim to correct this shortcoming by introducing a significantly general version of human-aware AI interaction scheme, called generalized human-aware interaction (GHAI), that talks about (mental) models of six types. Through this paper, we will see how this new framework allows us to capture the various works done in the space of human-AI interaction and identify the fundamental behavioral patterns supported by these works. We will also use this framework to identify potential gaps in the current literature and suggest future research directions to address these shortcomings.

show abstract

Joint Mind Modeling for Explanation Generation in Complex Human-Robot Collaborative Tasks

Cited by 28 publications

References 24 publications

Helping People Through Space and Time: Assistance as a Perspective on Human-Robot Interaction

Helping People Through Space and Time: Assistance as a Perspective on Human-Robot Interaction

Complex Problem Solving through Human-AI Collaboration: Literature Review on Research Contexts

A Mental-Model Centric Landscape of Human-AI Symbiosis

Contact Info

Product

Resources

About