A Supervised Autonomous Approach for Robot Intervention with Children with Autism Spectrum Disorder

Technological solutions such as social robots and Objects based on Playware Technology (OPT) have been used in context of intervention with children with Autism Spectrum Disorder (ASD). Very often in these systems, the social robot is being fully controlled using the Wizard of Woz (WoZ) method. Although reliable, this method increases the cognitive workload on the human operator. They have to pay attention to the child and ensure that the robot is responding correctly to the child's actions. In order to mitigate this, recently, researchers have been proposing the introduction of some autonomy in these systems. Following this trend, the present work targets a supervised behavioural system architecture using a novel hybrid approach with a humanoid robot and OPT to allow the detection of the child behaviour and consequently adapt the robot to the child's action, enabling a more natural interaction. The system was designed for emotion recognition activities with children with ASD. Additionally, this paper provides an overview of the experimental design where the interventions will be carried out in school environments in a triadic setup (child-robot-researcher/therapist).