Search

BACKGROUND: Rapid technological development has been opening new possibilities for children with disabilities. In particular, robots can enable and create new opportunities in therapy, rehabilitation, education, or leisure. OBJECTIVE: The aim of this article is to share experiences, challenges and learned lessons by the authors, all of them with experience conducting research in the field of robotics for children with disabilities, and to propose future directions for research and development. METHODS: The article is the result of several consensus meetings to establish future research priorities in this field. RESULTS: Robots have a huge potential to support children with disabilities: they can play the role of a play buddy, of a mediator when interacting with other children or adults, they can promote social interaction, and transfer children from the role of a spectator of the surrounding world to the role of an active participant. To fulfill their potential, robots have to be “smart”, stable and reliable, easy to use and program, and give the just-right amount of support adapted to the needs of the child. Interdisciplinary collaboration combined with user centered design is necessary to make robotic applications successful. Furthermore, real-life contexts to test and implement robotic interventions are essential to refine them according to real needs. CONCLUSIONS: This article outlines a research agenda for the future of robotics in childcare and supports the establishment of R4C – Robots for Children, a network of experts aimed at sharing ideas, promoting innovative research, and developing good practices on the use of robots for children with disabilities.

Aggression in children is frequent during the early years of childhood. Among children with psychiatric disorders in general, and autism in particular, challenging behaviours and aggression rates are higher. These can take on different forms, such as hitting, kicking, and throwing objects. Social robots that are able to detect undesirable interactions within its surroundings can be used to target such behaviours. In this study, we evaluate the performance of five machine learning techniques in characterizing five possible undesired interactions between a child and a social robot. We examine the effects of adding different combinations of raw data and extracted features acquired from two sensors on the performance and speed of prediction. Additionally, we evaluate the performance of the best developed model with children. Machine learning algorithms experiments showed that XGBoost achieved the best performance across all metrics (e.g., accuracy of 90%) and provided fast predictions (i.e., 0.004 s) for the test samples. Experiments with features showed that acceleration data were the most contributing factor on the prediction compared to gyroscope data and that combined data of raw and extracted features provided a better overall performance. Testing the best model with data acquired from children performing interactions with toys produced a promising performance for the shake and throw behaviours. The findings of this work can be used by social robot developers to address undesirable interactions in their robotic designs.Other Information Published in: International Journal of Social Robotics License: https://creativecommons.org/licenses/by/4.0See article on publisher's website: http://dx.doi.org/10.1007/s12369-022-00889-8