The use of humanoid robots as assistants in therapy processes is not new. Several projects in the past several years have achieved promising results when combining human-robot interaction with standard techniques. Moreover, there are multiple screening systems for autism; one of the most used systems is the Quantitative Checklist for Autism in Toddlers (Q-CHAT-10), which includes ten questions to be answered by the parents or caregivers of a child. We present Q-CHAT-NAO, an observation-based autism screening system supported by a NAO robot. It includes the six questions of the Q-CHAT-10 that can be adapted to work in a robotic context; unlike the original system, it obtains information from the toddler instead of from an indirect source. The detection results obtained after applying machine learning models to the six questions in the Autistic Spectrum Disorder Screening Data for Toddlers dataset were almost equivalent to those of the original version with ten questions. These findings indicate that the Q-CHAT-NAO could be a screening option that would exploit all the benefits related to human-robot interaction.

Educational robotics has proven its positive impact on the performances and attitudes of students. However, the educational environments that employ them rarely provide teachers with relevant information that can be used to make an effective monitoring of the student learning progress. To overcome these limitations, in this paper we present IDEE (Integrated Didactic Educational Environment), an educational environment for physics, that uses EV3 LEGO Mindstorms® educational kit as robotic component. To provide support to teachers, IDEE includes a dashboard that provides them with information about the students’ learning process. This analysis is done by means of an Additive Factor Model (AFM). That is a well-known technique in the educational data mining research area. However, it has been usually employed to carry out analysis about students’ performance data outside the system. This can be a burden for the teacher who, in most cases, is not an expert in data analysis. Our goal in this paper is to show how the coefficients of AFM provide valuable information to the teacher without requiring any deep expertise in data analysis. In addition, we show an improved version of the AFM that provides a deeper understanding about the students’ learning process.

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 behaviours in robot tutors, in particular in the emotional dimension, can make a signicant contribution to learning efciency. With the aim of contributing to the rising eld 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 identication 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

Human-Robot Interaction (HRI) is a growing area of interest in Artificial Intelligence that aims to make interaction with robots more natural. In this sense, numerous research studies on verbal and visual interactions with robots have appeared. The p