This study delves into integrating Large Language Models (LLMs), particularly ChatGPT-powered robots, as educational tools in primary school mathematics. Against the backdrop of Artificial Intelligence (AI) increasingly permeating educational settings, our investigation focuses on the response of young learners to errors made by these LLM-powered robots. Employing a user study approach, we conducted an experiment using the Pepper robot in a primary school classroom environment, where 77 primary school students from multiple grades (Year 3 to 5) took part in interacting with the robot. Our statistically significant findings highlight that most students, regardless of the year group, could discern between correct and incorrect responses generated by the robots, demonstrating a promising level of understanding and engagement with the AI-driven educational tool. Additionally, we observed that students' correctness in answering the Maths questions significantly influenced their ability to identify errors, underscoring the importance of prior knowledge in verifying LLM responses and detecting errors. Additionally, we examined potential confounding factors such as age and gender. Our findings underscore the importance of gradually integrating AI-powered educational tools under the guidance of domain experts following thorough verification processes. Moreover, our study calls for further research to establish best practices for implementing AI-driven pedagogical approaches in educational settings,

This paper presents an investigation into the effectiveness of introducing explicit causal explanations in a child-robot interaction setting to help children with autism improve their Visual Perspective Taking (VPT) skills. A sample of ten children participated in three sessions with a social robot on different days, during which they played several games consisting of VPT tasks. In some of the sessions, the robot provided constructive feedback to the children by giving causal explanations related to VPT; other sessions were control sessions without explanations. An analysis of the children’s learning progress revealed that they improved their VPT abilities faster when the robot provided causal explanations. However, both groups ultimately reach a similar ratio of correct answers in later sessions. These findings suggest that providing causal explanations using a social robot can be effective to teach VPT to children with autism. This study paves the way for further exploring a robot’s ability to provide causal explanations in other educational scenarios.

The research presented in this paper investigates the feasibility of using humanoid robots like Kaspar as assistive tools in Speech, Language and Communication (SLC) therapy for children with learning disabilities. The study aims to answer two research questions: RQ1. Can a social robot be used to improve SLC skills of children with learning disabilities? RQ2. What is the measurable impact of interacting with a humanoid robot on children with learning disability and SLC needs? A co-creation approach was followed, three therapeutic educational games were developed and implemented on the Kaspar robot in collaboration with experienced SLC experts. Twenty children from two different special educational needs schools participated in the games in 9 sessions over a period of 3 weeks. Results showed significant improvement in participants’ SLC skills – i.e. language comprehension and production skills– over the intervention. Findings of this research affirms feasibility, suggesting that this type of robotic interaction is the right path to follow to help the children improve their SLC skills.

This paper presents a study conducted in a United Kingdom primary school with the Maqueen BBC micro:bit robot. The purpose was to explore whether easy-to-fix hardware issues affected the children's perception of the robot or their enjoyment of the session, and whether the children could cope with these failures and/or repair them. As with any piece of technology, robots break down and are in regular need of reparation, but this technical issue could be a disadvantage in a classroom setting, as it might impact the children's enjoyment and confidence in their abilities to carry out the given task; potentially this could deter teachers from using this technology. 128 children participated in this study, aged 7–12 years old (M $$=$$ 9,18; SD $$=$$ 1,061). While children did perceive robots to be faulty less times than the faults were present in the robots, they did consider themselves capable of solving these issues and enjoyed doing so. Their perception of a faulty robot also did not impact significantly in their enjoyment nor in their consideration of the robot as a machine or a friend.

The Trust, Acceptance and Social Cues in Human-Robot Interaction - SCRITA is the 5th edition of a series of workshops held in conjunction with the IEEE RO-MAN conference. This workshop focuses on addressing the challenges and development of the dynamics between people and robots in order to foster short interactions and long-lasting relationships in different fields, from educational, service, collaborative, companion, care-home and medical robotics. In particular, we aimed in investigating how robots can manipulate (i.e. creating, improving, and recovering) people's ability of accepting and trusting them for a fruitful and successful coexistence between humans and people. While advanced progresses are reached in studying and evaluating the factors affecting acceptance and trust of people in robots in controlled or short-term (repeated interactions) setting, developing service and personal robots, that are accepted and trusted by people where the supervision of operators is not possible, still presents an open challenge for scientists in robotics, AI and HRI fields. In such unstructured static and dynamic human-centred environments scenarios, robots should be able to learn and adapt their behaviours to the situational context, but also to people's prior experiences and learned associations, their expectations, and their and the robot's ability to predict and understand each other's behaviours. Although the previous editions valued the participation of leading researchers in the field and several exceptional invited speakers who tackled down some fundamental points in this research domains, we wish to continue to further explore the role of trust in robotics to present groundbreaking research to effectively design and develop socially acceptable and trustable robots to be deployed "in the wild". Website: https://scrita.herts.ac.uk

This workshop focused on identifying the challenges and dynamics between people and robots to foster short interactions and long-lasting relationships in different fields, from educational, service, collaborative, companion, care-home and medical robotics. For that, this workshop facilitated a discussion about people's trust towards robots "in the field", inviting workshop participants to contribute their past experiences and lessons learnt.

In this paper we present a novel approach to programme Kaspar, a 22 DOF humanoid robot used for robot-assisted therapy with children with Autism Spectrum Disorder (ASD). The original software used to programme Kaspar was developed to primarily be used in research. However, Kaspar is now used increasingly in other environments, operated by non-roboticists. While Kaspar has a user-friendly interface to be operated by non-programmers, new games or behaviours were mainly created by the research team; thus, we needed to develop an interface that would allow non-roboticists to programme Kaspar. As a solution, we used the Scratch programming language. We tested the Scratch interface with over 170 school children aged 7 to 10, who had the chance to programme Kaspar and give their feedback. In general terms, Scratch was thought to be a fun, useful and easy way to programme Kaspar, and the majority of the children were willing to use it again.