The interventions conducted by a robot and a human trainer were both effective in promoting self-initiated questions in children with ASD. No conclusion with regard to the differential effectiveness of both interventions could be drawn. Implications of the results and directions for future research are discussed.

This paper provides a framework for recording, analyzing and modeling of 3 dimensional emotional movements for embodied game applications. To foster embodied interaction, we need interfaces that can develop a complex, meaningful understanding of intention-both kinesthetic and emotional-as it emerges through natural human movement. The movements are emulated on robots or other devices with sensory-motor features as a part of games that aim improving the social interaction skills of children. The design of an example game platform that is used for training of children with autism is described since the type of the emotional behaviors depends on the embodiment of the robot and the context of the game. The results show that quantitative movement parameters can be matched to emotional state of the embodied agent (human or robot) using the Laban movement analysis. Emotional movements that were emulated on robots using this principle were tested with children in the age group 7-9. The tests show reliable recognition on most of the behaviors.

The aim of the study was to investigate the effectiveness of a brief robot-mediated intervention based on Lego(®) therapy on improving collaborative behaviors (i.e., interaction initiations, responses, and play together) between children with ASD and their siblings during play sessions, in a therapeutic setting. A concurrent multiple baseline design across three child-sibling pairs was in effect. The robot-intervention resulted in no statistically significant changes in collaborative behaviors of the children with ASD. Despite limited effectiveness of the intervention, this study provides several practical implications and directions for future research.

To utilise the knowledge gained from highly specialised domains as autism therapy to robot‐based interactive training platforms, an innovative design approach is needed. We present the process of content creation and co‐design of LEGO therapy for children with autism spectrum disorders performed by a humanoid robot. The co‐creation takes place across the disciplines of autism therapy, and behavioural robotics, and applies methods from design and human–robot interaction, in order to connect state‐of‐the‐art developments in these disciplines. We designed, carried out and analyzed a pilot and final experiment, in which a robot mediated LEGO therapy between pairs of children was mediated by a robot over the course of 10 to 12 sessions. The impact of the training on the children was then analysed from a clinical and human–robot interaction perspective. Our major findings are as follows: first, game‐based robot scenarios in which the game continues over the sessions opened possibilities for long‐term interventions using robots and led to a significant increase in social initiations during the intervention in natural settings; and second, including dyadic interactions between robot and child within triadic games with robots has positive effects on the children's engagement and on creating learning moments that comply with the chosen therapy framework.

No abstract