Author ORCID Identifier
Document Type
Report
Disciplines
Computer Sciences
Abstract
Human-Robot Interaction (HRI) is an important but challenging field focused on improving the interaction between humans and robots such to make the interaction more intelligent and effective. However, building a natural conversational HRI is an interdisciplinary challenge for scholars, engineers, and designers. It is generally assumed that the pinnacle of human- robot interaction will be having fluid naturalistic conversational interaction that in important ways mimics that of how humans interact with each other. This of course is challenging at a number of levels, and in particular there are considerable difficulties when it comes to naturally monitoring and responding to the user’s mental state. On the topic of mental states, one field that has received little attention to date is moni- toring the user for possible confusion states. Confusion is a non-trivial mental state which can be seen as having at least two substates. There two confusion states can be thought of as being associated with either negative or positive emotions. In the former, when people are productively confused, they have a passion to solve any current difficulties. Meanwhile, people who are in unproductive confusion may lose their engagement and motivation to overcome those difficulties, which in turn may even lead them to drop the current conversation. While there has been some research on confusion monitoring and detection, it has been limited with the most focused on evaluating confusion states in online learning tasks. The central hypothesis of this research is that the monitoring and detection of confusion states in users is essential to fluid task-centric HRI and that it should be possible to detect such confusion and adjust policies to mitigate the confusion in users. In this report, I expand on this hypothesis and set out several research questions. I also provide a comprehensive literature review before outlining work done to date towards my research hypothesis, I also set out plans for future experimental work.
DOI
https://doi.org/10.21427/1JFS-4424
Recommended Citation
Li, N. (2023). Confirmation Report: Modelling Interlocutor Confusion in Situated Human Robot Interaction. Technological University Dublin. DOI: 10.21427/1JFS-4424
Funder
Science Foundation Ireland
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.