In-the-Wild Learning from Demonstration for Therapies for Autism Spectrum Disorder

Abstract

Current studies have demonstrated that Socially Assistive Robots (SARs) delivering Applied Behavior Analysis (ABA) based interventions can teach individuals with Autism Spectrum Disorder (ASD) valuable social, emotional, communication and academic skills. These robot-mediated interventions (RMIs) are typically delivered via teleoperation, which places additional or similar workloads on therapists as administering interventions directly. The autonomous delivery of ABA therapies to individuals with ASD by a robot could significantly reduce workload and improve the usability as well as acceptance of this technology. However, pre-programming the autonomy of a SAR with a limited set of interventions is not sufficient for clinical practice due to the rapidly changing and different learning needs of individuals with ASD. In order to be applicable in clinical settings, therapists must be capable of customizing and personalizing interventions to the needs of each individual. Towards this goal, in this paper we present the initial development and deployment of a proof-of-concept Learning from Demonstration (LfD) system in-the-wild to learn the verbal behavior of therapists during the delivery of an ABA-based intervention to children with ASD. We also present preliminary data on the results of a policy trained on data collected from demonstrations provided during this in-the-wild deployment of our LfD system.