Can young children learn words from a robot

1994

2021

We transformed the existing learning program Language Shower, which is used in some Norwegian day-care centers in the Grorud district of Oslo municipality, into a digital solution using an app for smartphone or tablet with the option for further enhancement of presentation by a NAO robot. The solution was tested in several iterations and multiple day-care centers over several weeks. Measurements of the children’s progress across learning sessions indicate a positive impact of the program using a robot as compared to the program without robot. In-situ observations and interviews with day care center staff confirmed the solution’s many advantages, but also revealed some important areas for improvement. In particular, the speech recognition needs to be more flexible and robust, and special measures have to be in place to handle children speaking simultaneously.

Sustainability, 2021

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution

Transforming our World Through Design, Diversity and Education, 2018

A number of studies have found that robots can contribute to engagement and motivation in educational settings. We wanted to explore the possibilities and challenges of using a social robot as an assistive tool for learning and training of basic concepts and words. Robots are considered promising tools in language training because they can contribute to systematic interaction and repetition. A prototype was developed using an Aldebaran NAO robot combined with pictures that could be presented on a tablet, PC or on the wall using a projector. The prototype was piloted in two pre-projects with different groups of children learning Norwegian. One project targeted second language learners in a kindergarten and the other targeted young primary school pupils with autism spectrum disorder. Both of these groups need more systematic training than they usually get during the normal kindergarten and school schedule. We wanted to study whether and how the use of a social robot could contribute to more systematic training, increased learning intensity, more repetitions and ultimately more effective language learning. In this paper we present experiences from developing, implementing and using the prototype in the two different settings. The prototype is described, as well as the pedagogical settings of the two pilots. We present results from observations of the children and interviews with teachers and supporting personnel. We discuss differences between the two cases and methodological limitations. Finally, we discuss possibilities and challenges of using robots in language learning and training of children.

Proceedings of the 9th Nordic Conference on Human-Computer Interaction - NordiCHI '16, 2016

This paper explores children's social engagement to a robotic tutor by analyzing their behavioral reactions to socially significant events initiated by the robot. Specific questions addressed in this paper are whether children express signs of social engagement as a reaction to such events, and if so, in what way. The second question is whether these reactions differ between different types of social events, and finally, whether such reactions disappear or change over time. Our analysis indicates that children indeed show behaviors that indicate social engagement using a range of communicative channels. While gaze towards the robot's face is the most common indication for all types of social events, verbal expressions and nods are especially common for questions, and smiles are most common after positive feedback. Although social responses in general decrease slightly over time, they are still observable after three sessions with the robot.

Procedia - Social and Behavioral Sciences, 2013

Journal of Mechatronics and Artificial Intelligence in Engineering

Humanoid robots have a substantial potential to serve as teaching and social assistants. However, the expectations of the children from robots to interact like humans are huge. This study presents a general model for understanding the natural language in human-robot interaction by applying Generative Pre-trained Transformer (GPT) language models as a service in the Internet of Things. Thus, the physical presence of the robot can help in fine-tuning the GPT model by prompts derived from the environmental context and subsequent robot actions for embodiment understanding of the GPT outputs. The model uses web or cloud services for Natural Language Processing (NLP) to produce and play human-like text, question answering or text generation. Verbal questions are processed either via a local speech recognition software or via a Speech-to-Text (STT) cloud service. The converted question into machine-readable code is sent to one of the GPT language models with zero- or few-shot learning prom...

2013