ARTIE: An Integrated Environment for the Development of Affective Robot Tutors

Abstract

Over the last decade robotics has attracted a great deal of interest from teachers and researchers as a valuable educational tool from preschool to highschool levels. The implementation of social-support behaviors in robot tutors, in particular in the emotional dimension, can make a significant contribution to learning efficiency. With the aim of contributing to the rising field of affective robot tutors we have developed ARTIE (Affective Robot Tutor Integrated Environment). We offer an architectural pattern which integrates any given educational software for primary school children with a component whose function is to identify the emotional state of the students who are interacting with the software, and with the driver of a robot tutor which provides personalized emotional pedagogical support to the students. In order to support the development of affective robot tutors according to the proposed architecture, we also provide a methodology which incorporates a technique for eliciting pedagogical knowledge from teachers, and a generic development platform. This platform contains a component for identiying emotional states by analysing keyboard and mouse interaction data, and a generic affective pedagogical support component which specifies the affective educational interventions (including facial expressions, body language, tone of voice,…) in terms of BML (a Behavior Model Language for virtual agent specification) files which are translated into actions of a robot tutor. The platform and the methodology are both adapted to primary school students. Finally, we illustrate the use of this platform to build a prototype implementation of the architecture, in which the educational software is instantiated with Scratch and the robot tutor with NAO. We also report on a user experiment we carried out to orient the development of the platform and of the prototype. We conclude from our work that, in the case of primary school students, it is possible to identify, without using intrusive and expensive identification methods, the emotions which most affect the character of educational interventions. Our work also demonstrates the feasibility of a general-purpose architecture of decoupled components, in which a wide range of educational software and robot tutors can be integrated and then used according to different educational criteria.

Using LSTM to Identify Help Needs in Primary School Scratch Students

“…We will also refine and validate the model in a real learning environment, and a more in-depth analysis of the impact of the different attributes in determining whether a student needs help will be conducted. Finally, this work will also support the ARTIE project [13], introduced in Section 1, so that the system will be able to automatically identify when a primary school student needs help during block-based programming exercises, and send the appropriate pedagogical intervention to the affective tutor robot.…”

“…The work presented here was carried out in the context of the project Affective Robot Tutor Integrated Environment (ARTIE), in which we are developing an environment for configuring an affective robot tutor, to be used to teach block-based programming in primary school education. This environment must be able to identify when a student needs help, what their emotional state is, and how the robot should act according to each situation and emotional state [13,14]. Therefore, the robot is "affective" because it deals with or arouses emotions.…”

10 Years of Human-NAO Interaction Research: A Scoping Review

“…NAO as demonstrator or presenter performs actions in front of the participants (Krogsager et al, 2014;Wang et al, 2014;Kaptein et al, 2017). Learner-tutor interaction occurs in educational settings where NAO is engaged with language teaching (Kose et al, 2014;de Wit et al, 2020) and providing emotional support (Miskam et al, 2015;Cuadrado et al, 2016). NAO as a mediator predominantly helps children with autism or learning disabilities to scaffold social and communication skills (Shamsuddin et al, 2012;Huskens et al, 2016;Ioannou and Andreva, 2019).…”

Conflict and Reconciliation Processes Between Affective/Social Robots and Humans

“…While this study did not count on various control groups, it did show how students improved their performance after working with the robot and reported high satisfaction and an overwhelming desire to take more lessons of this type. [7] points out that common affective measures based on physiological and psychological responses usually require intrusive and expensive tools that are impractical in real settings. In response, the authors propose an emotion recognition system based on typing dynamics and mouse interactions.…”