A study of children with autism spectrum disorder found that a therapeutic intervention using robots was effective in improving their social development and participation in social activities. After the intervention, participants showed greater improvement in communication and reciprocal social interaction compared to both a control group and a group that received a comparable intervention delivered by a human therapist. The paper was published in the Journal of Autism and Developmental Disorders.
Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by difficulties in social communication and by restricted, repetitive patterns of behavior, interests, or activities. Symptoms usually emerge in early childhood but can vary widely in severity. Some individuals with ASD have intellectual and language impairments, while others have average or above-average intelligence and advanced verbal skills.
People with ASD often struggle with interpreting social cues, forming relationships, or adapting to changes in routine. Sensory sensitivities—such as being overwhelmed by certain sounds, lights, or textures—are also common. Although ASD is a lifelong condition, many individuals can lead independent lives with appropriate support.
Early diagnosis and intervention are associated with better outcomes. Prior research has found that some children with ASD respond more positively to robots than to human interaction. Building on this, study author Eva Yin-han Chung and her colleagues investigated whether a robotic intervention program could enhance social engagement in children with ASD. Social engagement refers to the development of skills that allow a child to participate in reciprocal interactions with others, which is a key component of broader social participation.
The study involved 60 children with ASD between the ages of 5 and 11. All had an IQ of at least 70 and were able to follow simple commands. Six participants were girls. The children were randomly assigned to one of three groups: a robotic intervention group, a human-instructed group, or a control group.
The robotic intervention group used the humanoid NAO robot to assist the therapist in delivering the sessions. The program taught two-way communication, basic emotions, imitation, and reciprocal responses. Over 12 weekly sessions, children engaged in structured social games, story-based activities, and singing and dancing routines. The NAO robot features a simplified face with multicolored blinking eyes and is roughly the size of a two-year-old child, making it approachable and engaging for young participants.
The human-instructed group received the same content, delivered by a therapist without the aid of a robot. Children in the control group did not receive any intervention during the study period. All children were assessed before and after the 12-week program using the Autism Diagnostic Observation Schedule (ADOS) and the Social Responsiveness Scale (SRS), which measured social communication and parent-reported social responsiveness, respectively.
Results showed that children in the robotic intervention group had significantly greater improvements in social communication compared to the other two groups. They demonstrated the most substantial gains in communication and reciprocal social interaction on the ADOS. Parent-reported improvements on the SRS also favored the robotic and human-instructed groups over the control group, though the difference between the robotic and human groups was not statistically significant in that measure.
“The effectiveness of [the] robotic intervention programme to enhance the social communication and participation was confirmed. Future studies may also consider adding a maintenance phase to document how the effects of the intervention carry over to the participants over a longer period,” the authors wrote.
While the study offers promising evidence for the use of robots in autism therapy, it has several limitations. The sample size was relatively small, and the researchers did not assess whether the observed benefits were maintained over time. Future research could investigate the long-term effects of such interventions and explore whether they translate to real-world social settings beyond the treatment environment.
The paper, “Effectiveness of Robotic Intervention on Improving Social Development and Participation of Children with Autism Spectrum Disorder – A Randomised Controlled Trial,” was authored by Eva Yin-han Chung, Kenneth Kuen-fung Sin, and Daniel Hung-kay Chow.