Towards Spatial Methods for Socially Assistive Robotics: Validation With Children With Autism Spectrum Disorders David Feil-Seifer University of Southern California Los Angeles, CA, USA dfseifer@usc.edu Socially Assistive Robotics (SAR) defines the research re- garding robots which provide assistance to users through so- cial interaction [Feil-Seifer and Matari´ c, 2005]. Socially as- sistive robots are being studied for therapeutic use with chil- dren with autism spectrum disorders (ASD). It has been ob- served that children with ASD interact with robots differently than with people or toys. This may indicate an intrinsic in- terest in such machines, which could be applied as a robot augmentation for an intervention for children with ASD. Pre- liminary studies suggest that robots may act as intrinsically- rewarding social partners for children with autism. However, enabling a robot to understand social behavior, and do so while interacting with the child, is a challenging problem. Children are highly individual and thus technology used for social interaction requires recognition of a wide-range of so- cial behavior. This work addresses the challenge of designing behaviors for socially assistive robots in order to enable them to recog- nize and appropriately respond to a childs free-form behavior in unstructured play contexts. The focus on free-form be- havior is inspired by and grounded in existing approaches to therapeutic intervention with children with ASD. This model emphasizes creating circles of communication and fostering engagement through play. A key aspect of this approach is to recognize social behavior and use engagements to bolster so- cial interaction behavior, and to study the ethical implications of therapeutic robotics applications. This research will present a methodology and a vali- dated experimental framework for enabling fully autonomous robots to interact with both typically developing children and children with autism spectrum disorders (ASD) in undi- rected scenarios using socially appropriate behavior espe- cially where spatial interaction is concerned. This work holds autonomous operation as a critical aspect of the development and implementation of a robot system. Save for safety inter- ventions by a human operator, the robot system presented in this work acts of its own accord. The methodology of this work holds that free-form interaction is best served by allow- ing a child to move about a space as they choose, and we wish to enable a robot that can allow for such freedom and func- tion effectively for its interaction goals. As such, the robot and child interact, in part, though distance-oriented behavior, and the robot must be able to recognize those behaviors and appropriately respond to them. An overarching goal of this work is to develop a method- ology which did not preclude human-human interaction, and in fact encourages human-human interaction. We wish to use this system was to be used as an augmentation, rather than a replacement for a human therapist. There is no substitute for human-human interaction in social interaction. However, the compelling interaction between children with ASD and robots is encouraging for their use as a therapeutic aid. This work aims for the following with an eye toward therapeutic potential: • Detection and mitigation of a childs distress: we de- fine a methodology for learning and applying a data- driven spatio-temporal model of social behavior based on proxemic features to automatically differentiate be- tween typical child-robot interactive behavior and be- havior that would suggest an aversive response. Using a Gaussian Mixture Model learned over proxemic feature data the developed system is able to detect and interpret social behavior of the child with sufficient accuracy to recognize distress on the part of the child. The robot uses this model to change its own behavior to encour- age positive social interaction [Feil-Seifer and Matari´ c, 2011a]. • Encouragement of human-human and human-robot interaction: we aim to demonstrate a global and local motion planner that would use the above spatio-temporal model as part of the determination of a motion trajectory to maintain the robots spatial relationship with the child that sustains interaction while also encouraging the child to move toward another proximal person (usually a par- ent). • Encouragement of turn-taking behavior: we will present a methodology for robot behavior designed to encourage turn-taking behavior, which is based on ther- apeutic interaction between a human behavior therapist and child. This will be validated using an spatial imi- tation game, which can not only be used to gauge the presence of turn-taking behavior, but also the develop- mental level of such turn-taking behavior. These above are being developed and validated in several robot systems employing the Behavior-Based Behavior In- tervention Architecture (B 3 IA), a novel robot control archi- tecture developed for Human-Robot Interaction (HRI). B 3 IA 2800 Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence