Impacts of humanoid robots on improvement of eye contact in children with autism

This research evaluated the effects of humanoid robots on improvement of eye contact in autistic children.Methods and Materials: This research used a multiple baseline, single-subject design with control to test 5 autistic children (2 girls and 3 boys) in Tehran during 2010. The children aged 7 to 9 years and were tested by Gilliam Autism Rating Scales (GARS) to ensure the presence of substantial autistic symptoms. A semi-automatic humanoid robotic doll with remote control was used in this study. A short scenario was designed for the primary experimental sessions before the main test. The scenario was established by 3 pilot sessions on an autistic child. We observed children for 15 sessions. The experimental sessions were held twice a week for 7 weeks. Each session lasted for 30 minutes, i.e. 15 minutes for eye contact between robot-human and 15 minutes to observe human-human eye contact development. All sessions were recorded by two cameras and finally rated by independent observers based on the number of seconds of human-human eye contact in each session. The results showed that the duration of eye contact increased during the course of 15 sessions. This change could have been resulted from the effect of the independent variable. Robots have been shown to be a catalyst to improve some skills in autistic children. However, they need to be further studied in order to be effectively employed as a therapeutic intervention. In addition, many children may require extensive therapy for years to improve their behavior and facilitate integration in society.