Transparency through Explanations and Justifications in Human-Robot Task-Based Communications

Scheutz, Matthias; Thielstrom, Ravenna; Abrams, Mitchell

doi:10.1080/10447318.2022.2091086

Cited by 10 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this view, statements needed to clarify robot legibility or incapability manifest that the utterances spoken or the non-verbal signals expressed adjust any differences between the user and the robot that may cause failures or misunderstandings. This approach does not involve explainability in the form of justifications [24], yet it does involve the indication of reasons for whether something is understood or misunderstood. It also involves the ability of the agent to explain the causes of misunderstanding, mitigate the reasons for failures in a collaborative manner, and communicate its understanding of the user's intent and goals.…”

Section: Explanations As Communicative Actsmentioning

confidence: 99%

Behavioural Responses to Robot Conversational Failures

Kontogiorgos

Pereira

Sahindal

et al. 2020

Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction

View full text Add to dashboard Cite

show abstract

Section: Explanations As Communicative Actsmentioning

confidence: 99%

Behavioural Responses to Robot Conversational Failures

Kontogiorgos

Pereira

Sahindal

et al. 2020

Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction

View full text Add to dashboard Cite

show abstract

“…Studies often focused on narrow aspects of negation, such as affect or volition, as context conditions ( Förster et al, 2019 ). Although recently the focus shifted towards explainable robots with some progress in the direction of explaining why robots reject commands of a human ( Scheutz et al, 2022 ). In social robotics, negation is still generally seen as a device that imparts a “negative” attitude to the interaction and should therefore be avoided.…”

Section: Introductionmentioning

confidence: 99%

Scaffolding the human partner by contrastive guidance in an explanatory human-robot dialogue

Groß,

Singh,

Banh

et al. 2023

Front. Robot. AI

View full text Add to dashboard Cite

Explanation has been identified as an important capability for AI-based systems, but research on systematic strategies for achieving understanding in interaction with such systems is still sparse. Negation is a linguistic strategy that is often used in explanations. It creates a contrast space between the affirmed and the negated item that enriches explaining processes with additional contextual information. While negation in human speech has been shown to lead to higher processing costs and worse task performance in terms of recall or action execution when used in isolation, it can decrease processing costs when used in context. So far, it has not been considered as a guiding strategy for explanations in human-robot interaction. We conducted an empirical study to investigate the use of negation as a guiding strategy in explanatory human-robot dialogue, in which a virtual robot explains tasks and possible actions to a human explainee to solve them in terms of gestures on a touchscreen. Our results show that negation vs. affirmation 1) increases processing costs measured as reaction time and 2) increases several aspects of task performance. While there was no significant effect of negation on the number of initially correctly executed gestures, we found a significantly lower number of attempts—measured as breaks in the finger movement data before the correct gesture was carried out—when being instructed through a negation. We further found that the gestures significantly resembled the presented prototype gesture more following an instruction with a negation as opposed to an affirmation. Also, the participants rated the benefit of contrastive vs. affirmative explanations significantly higher. Repeating the instructions decreased the effects of negation, yielding similar processing costs and task performance measures for negation and affirmation after several iterations. We discuss our results with respect to possible effects of negation on linguistic processing of explanations and limitations of our study.

show abstract