Engaging Learners in Dialogue Interactivity Development for Mobile Robots

Baxter, Paul; Duchetto, Francesco Del; Hanheide, Marc

doi:10.1007/978-3-030-18141-3_12

Cited by 4 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is known that a higher level of engagement generates better learning outcomes (Ponitz et al, 2009), while engagement with a robot during a learning activity has also been shown to have a similar effect (Gleason and Greenhow, 2017). While there is evidence that the presence of a robot, particularly when novel, is sufficient in itself for higher engagement in educational STEM activities, e.g., Baxter et al, 2018, the focus in the present work is on engagement between individuals and the robot within a direct (social) interaction, for which there is not a universally agreed definition (Glas and Pelachaud, 2015).…”

Section: Assessment Of Engagementmentioning

confidence: 99%

Are You Still With Me? Continuous Engagement Assessment From a Robot's Point of View

2020

Self Cite

View full text Add to dashboard Cite

Continuously measuring the engagement of users with a robot in a Human-Robot Interaction (HRI) setting paves the way toward in-situ reinforcement learning, improve metrics of interaction quality, and can guide interaction design and behavior optimization. However, engagement is often considered very multi-faceted and difficult to capture in a workable and generic computational model that can serve as an overall measure of engagement. Building upon the intuitive ways humans successfully can assess situation for a degree of engagement when they see it, we propose a novel regression model (utilizing CNN and LSTM networks) enabling robots to compute a single scalar engagement during interactions with humans from standard video streams, obtained from the point of view of an interacting robot. The model is based on a long-term dataset from an autonomous tour guide robot deployed in a public museum, with continuous annotation of a numeric engagement assessment by three independent coders. We show that this model not only can predict engagement very well in our own application domain but show its successful transfer to an entirely different dataset (with different tasks, environment, camera, robot and people). The trained model and the software is available to the HRI community, at https://github.com/LCAS/engagement_detector, as a tool to measure engagement in a variety of settings.

show abstract

Section: Assessment Of Engagementmentioning

confidence: 99%

Are You Still With Me? Continuous Engagement Assessment From a Robot's Point of View

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…While there is evidence that the presence of a robot, particularly when novel, is sufficient in itself for higher engagement in educational STEM activities, e.g. [2], the focus in the present work is on engagement between individuals and the robot within a direct (social) interaction, for which there is not a universally agreed definition [12]. Within interactions, engagement has been characterized as a process that can be separated in four stages: point of engagement, period of sustained engagement, disengagement, and re-engagement [20].…”

Section: Assessment Of Engagementmentioning

confidence: 99%

“…This procedure allowed the generation of per-frame annotations of the provided videos, with very little time spent on software training (around 20 minutes per annotator) and on the annotation process itself (not more than the duration of the videos). The annotators were instructed by providing them with a demonstration, and a set of annotation rules based on a set of typical examples 2 .…”

Section: Dataset Codingmentioning

confidence: 99%

Are you still with me? Continuous Engagement Assessment from a Robot's Point of View

Del Duchetto,

Baxter,

Hanheide

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Continuously measuring the engagement of users with a robot in a Human-Robot Interaction (HRI) setting paves the way towards in-situ reinforcement learning, improve metrics of interaction quality, and can guide interaction design and behaviour optimisation. However, engagement is often considered very multi-faceted and difficult to capture in a workable and generic computational model that can serve as an overall measure of engagement. Building upon the intuitive ways humans successfully can assess situation for a degree of engagement when they see it, we propose a novel regression model (utilising CNN and LSTM networks) enabling robots to compute a single scalar engagement during interactions with humans from standard video streams, obtained from the point of view of an interacting robot. The model is based on a long-term dataset from an autonomous tour guide robot deployed in a public museum, with continuous annotation of a numeric engagement assessment by three independent coders. We show that this model not only can predict engagement very well in our own application domain but show its successful transfer to an entirely different dataset (with different tasks, environment, camera, robot and people). The trained model and the software is available to the HRI community as a tool to measure engagement in a variety of settings.

show abstract

“…Eliciting engagement during an interaction, and maintaining it after the initial phase of the interaction, is still an issue to be overcome. There is evidence that engagement in learning activities is higher in the presence of a robot, particularly if novel [1], but after the initial engagement state, long and non-interactive behaviors are detrimental to the continued engagement of the users [5,16]. Overcoming this limitation requires to design robots with enhanced social abilities that go past monolithic behaviours and introduces in-situ learning and adaptation to the specific users and situations.…”

Section: Introductionmentioning

confidence: 99%