Understanding Fine Motor Patterns in Children with Autism Using a Haptic-Gripper Virtual Reality System

Many children with Autism Spectrum Disorders (ASD) experience deficits in fine motor skills as compared to their typically developing (TD) peers. It is possible that the differences in fine motor patterns of children with ASD may provide useful insight into clinical diagnosis and intervention of ASD. This paper presents a preliminary study that used machine learning approaches to recognize the motor patterns exhibited by children with ASD based on their fine motor data obtained during carefully designed manipulation tasks in a virtual haptic environment. Six children with ASD and six TD children (aged 8-12) participated in a study that presented a series of fine motor tasks using a novel Haptic-Gripper virtual reality system. The results revealed that the identification accuracy of several machine learning approaches such as k-Nearest Neighbor (k-NN) and Artificial Neural Network (ANN) are encouraging and can reach up to 80%, indicating the potential of such an approach in ASD identification and intervention.