Human–Robot Gesture Analysis for Objective Assessment of Autism Spectrum Disorder

Abstract

In this paper we study the use of human robot interaction as a mean to objectively evaluate imitation deficits in children with autism. Robot control and data analysis methods were combined to assess the quality of interaction between the robot and the subjects. Humanoid robot Zeno was used to execute upper body gestures which the subjects were asked to imitate. The resulting motion of the subject was acquired through a motion capture system and compared with the intended motion performed by Zeno using the dynamic time warping (DTW) algorithm. During this study, the clinical hypothesis was that the resulting DTW cost can serve as a quantitative measure for the similarity between the motions, and thus can be used to objectively assess the severity of imitation deficits exhibited by the child. To validate this hypothesis, we present two sets of experiments, one with a set of healthy adults and the other with a group of children, some with autism spectrum disorder. The experiment with adult subjects serves as a statistically significant test to demonstrate the viability of the DTW cost as a similarity measure for the gesture analysis, whereas the experiment with child subjects is a pilot study to differentiate imitation performance for children with autism.