Mirjam de Haas

Child-Robot Interactions for Second Language Tutoring to Preschool Children

In this digital age social robots will increasingly be used for educational purposes, such as second language tutoring. In this perspective article, we propose a number of design features to develop a child-friendly social robot that can effectively support children in second language learning, and we discuss some technical challenges for developing these. The features we propose include choices to develop the robot such that it can act as a peer to motivate the child during second language learning and build trust at the same time, while still being more knowledgeable than the child and scaffolding that knowledge in adult-like manner. We also believe that the first impressions children have about robots are crucial for them to build trust and common ground, which would support child-robot interactions in the long term. We therefore propose a strategy to introduce the robot in a safe way to toddlers. Other features relate to the ability to adapt to individual children’s language proficiency, respond contingently, both temporally and semantically, establish joint attention, use meaningful gestures, provide effective feedback and monitor children’s learning progress. Technical challenges we observe include automatic speech recognition (ASR) for children, reliable object recognition to facilitate semantic contingency and establishing joint attention, and developing human-like gestures with a robot that does not have the same morphology humans have. We briefly discuss an experiment in which we investigate how children respond to different forms of feedback the robot can give.

Guidelines for Designing Social Robots as Second Language Tutors

In recent years, it has been suggested that social robots have potential as tutors and educators for both children and adults. While robots have been shown to be effective in teaching knowledge and skill-based topics, we wish to explore how social robots can be used to tutor a second language to young children. As language learning relies on situated, grounded and social learning, in which interaction and repeated practice are central, social robots hold promise as educational tools for supporting second language learning. This paper surveys the developmental psychology of second language learning and suggests an agenda to study how core concepts of second language learning can be taught by a social robot. It suggests guidelines for designing robot tutors based on observations of second language learning in human–human scenarios, various technical aspects and early studies regarding the effectiveness of social robots as second language tutors.

The Effect of a Robot's Gestures and Adaptive Tutoring on Children's Acquisition of Second Language Vocabularies

This paper presents a study in which children, four to six years old, were taught words in a second language by a robot tutor. The goal is to evaluate two ways for a robot to provide scaffolding for students: the use of iconic gestures, combined with adaptively choosing the next learning task based on the child»s past performance. The results show a positive effect on long-term memorization of novel words, and an overall higher level of engagement during the learning activities when gestures are used. The adaptive tutoring strategy reduces the extent to which the level of engagement is diminishing during the later part of the interaction.

Workshop on Robots for Learning: R4L

While robots have been popular as a tool for STEM teaching, the use of robots in other learning scenarios is novel. The field of HRI has started to report on how to make effective robots usable in educational contexts. However, many challenges remain. For instance, which interaction strategies aid learning, and which hamper learning? How can we deal with the current technical limitations of robots? Answering these and other questions requires a multidisciplinary effort, including contributions from pedagogy, developmental psychology, (computational) linguistics, artificial intelligence and HRI, among others. This abstract provides a brief overview of the current state-of-the-art in social robots designed for learning and describes the aims of the Robots for Learning (R4L) workshop in bringing together a multidisciplinary audience for furthering the development of market-ready educational robots.

Exploring Different Types of Feedback in Preschooler and Robot Interaction

This study considered the feedback of a robot during second language tutoring. Traditionally, robots are programmed to provide feedback as teacher; we propose a robot that acts as a peer to motivate preschoolers during the tutoring. We conducted an experiment with 65 preschoolers (M = 3.6 years) in which the robot varied feedback in three conditions: peer-like (explicit negative), adult-like (explicit positive and implicit negative) and no feedback. The results suggest that feedback did not influence childrens engagement (measured via eye-gaze), although children who received peer-like feedback seemed to perform more independently during the learning task (requiring less interventions from the experimenter).

Comparing Robots with Different Levels of Autonomy in Educational Setting

Robots’ ability to learn and show autonomous/intelligent behavior is expected to bring a breakthrough in usage of robots in education and assistive technologies. We compared a fully remotely operated robot (e. g. a robot with low autonomy) with one that could recognize cards and develop a playing strategy (i.e. highly autonomous) in a quartet game. We tested whether children perceive the robot in both conditions differently. Using a within-subject design, fourteen typically developed children played with a robot with high or low autonomy. The results show that both robots were evaluated equally engaging for the children. However, the introduction of more autonomy in robot’s behavior and interaction increased the time that the educator or therapist can pay attention to the child. Consequentially, the perceived usefulness of the robot and the triadic interaction between the robot, child and educator or therapist were considerably improved from the perspective of the educator.

Personalizing Educational Game Play with a Robot Partner

Personalization of educational and behavioral training to the developmental stage of the individual child is common practice in educational and therapeutic settings. Research on robot-based education training is only just starting to adopt this approach. We present a pilot study on a behavioral intervention design in which Pivotal Response Training (PRT) elements are embedded into a game played by a robot and a child. Seven game levels are designed to cover different levels of communication skills that are targeted by PRT. The levels do not differ with respect to the logical steps in the game that the children should take, only with respect to the social competence that the child has. The behaviors displayed at each stage were observed and analyzed using qualitative and quantitative methods. Our results indicate that the more socially challenging a game is, the happier children are and the more children engage with playing the game, although the game challenge remains the same.