Towards Transparent Robot Learning Through TDRL-Based Emotional Expressions

Broekens, Joost; Chétouani, Mohamed

doi:10.1109/taffc.2019.2893348

Cited by 26 publications

(24 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned by Broekens and Chetouani [10], most of computational approaches for social agents consider a primary task, e.g., learning to pick an object, and explainability arises as a secondary task by either communicating the agent's internal states, intentions, or future goals. Given the literature, it is possible to distinguish the nature of actions performed by the agent such as task oriented actions a T and communication oriented actions a C .…”

Section: Methods To Achieve Explainabilitymentioning

confidence: 99%

Explainable Agents Through Social Cues: A Review

Wallkotter,

Tulli,

Castellano

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

How to provide explanations has experienced a surge of interest in Human-Robot Interaction (HRI) over the last three years. In HRI this is known as explainability, expressivity, transparency or sometimes legibility, and the challenge for embodied agents is that they offer a unique array of modalities to communicate this information thanks to their embodiment. Responding to this surge of interest, we review the existing literature in explainability and organize it by (1) providing an overview of existing definitions, (2)showing how explainability is implemented and how it exploits different modalities, and (3) showing how the impact of explainability is measured. Additionally, we present a list of open questions and challenges that highlight areas that require further investigation by the community. This provides the interested scholar with an overview of the current state-of-the-art. CCS Concepts: • Computing methodologies → Intelligent agents; Reasoning about belief and knowledge; • Computer systems organization → Robotics; • General and reference → Metrics; • Human-centered computing → User models.

show abstract

Section: Methods To Achieve Explainabilitymentioning

confidence: 99%

Explainable Agents Through Social Cues: A Review

Wallkotter,

Tulli,

Castellano

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…As mentioned by Broekens and Chetouani [11], most of computational approaches for social agents consider a primary task, such as learning to pick an object, and explainability arises as a secondary task by either communicating the agent's internal states, intentions, or future goals. Existing works distinguish the nature of actions performed by the agent, such as task-oriented actions a T and communication-oriented actions a C .…”

Section: Explainability Mechanismsmentioning

confidence: 99%

“…In RL, theoretical links between (task) learning schemes and emotional theories could be performed. Broekens and Chetouani [11] investigated how temporal difference learning [70] could be employed to develop an emotionally expressive learning robot that is capable of generating explainable behaviors via emotions.…”

Section: Explainability Mechanismsmentioning

confidence: 99%

Explainable Embodied Agents Through Social Cues

Wallkotter

Tulli

Castellano

et al. 2021

J. Hum.-Robot Interact.

Self Cite

View full text Add to dashboard Cite

The issue of how to make embodied agents explainable has experienced a surge of interest over the past 3 years, and there are many terms that refer to this concept, such as transparency and legibility. One reason for this high variance in terminology is the unique array of social cues that embodied agents can access in contrast to that accessed by non-embodied agents. Another reason is that different authors use these terms in different ways. Hence, we review the existing literature on explainability and organize it by (1) providing an overview of existing definitions, (2) showing how explainability is implemented and how it exploits different social cues, and (3) showing how the impact of explainability is measured. Additionally, we present a list of open questions and challenges that highlight areas that require further investigation by the community. This provides the interested reader with an overview of the current state of the art.

show abstract

“…However, developing computational models that are able to adapt on-line to non-verbal cues is a current challenge in machine learning. The few attempts to exploit non-verbal cues for adaptation and learning require the prior definition of a communication protocol (i.e., meaning of non-verbal cues) between the human and the machine (Broekens and Chetouani, 2019 ). Training adaptive machine learning with non-verbal cues are facilitated by the prior categorization of limited discrete signals such as pointing or stop hand gesture (Najar et al, 2016 ).…”

Section: Open Questionsmentioning

confidence: 99%

Engagement in Human-Agent Interaction: An Overview

et al. 2020

Self Cite

View full text Add to dashboard Cite

Engagement is a concept of the utmost importance in human-computer interaction, not only for informing the design and implementation of interfaces, but also for enabling more sophisticated interfaces capable of adapting to users. While the notion of engagement is actively being studied in a diverse set of domains, the term has been used to refer to a number of related, but different concepts. In fact it has been referred to across different disciplines under different names and with different connotations in mind. Therefore, it can be quite difficult to understand what the meaning of engagement is and how one study relates to another one accordingly. Engagement has been studied not only in human-human, but also in human-agent interactions i.e., interactions with physical robots and embodied virtual agents. In this overview article we focus on different factors involved in engagement studies, distinguishing especially between those studies that address task and social engagement, involve children and adults, are conducted in a lab or aimed for long term interaction. We also present models for detecting engagement and for generating multimodal behaviors to show engagement.

show abstract

Towards Transparent Robot Learning Through TDRL-Based Emotional Expressions

Cited by 26 publications

References 67 publications

Explainable Agents Through Social Cues: A Review

Explainable Agents Through Social Cues: A Review

Explainable Embodied Agents Through Social Cues

Engagement in Human-Agent Interaction: An Overview

Contact Info

Product

Resources

About