SPARC: Supervised Progressively Autonomous Robot Competencies

Abstract

The Wizard-of-Oz robot control methodology is widely used and typically places a high burden of effort and attention on the human supervisor to ensure appropriate robot behaviour, which may distract from other aspects of the task engaged in. We propose that this load can be reduced by enabling the robot to learn online from the guidance of the supervisor to become progressively more autonomous: Supervised Progressively Autonomous Robot Competencies (SPARC). Applying this concept to the domain of Robot Assisted Therapy (RAT) for children with Autistic Spectrum Disorder, a novel methodology is employed to assess the effect of a learning robot on the workload of the human supervisor. A user study shows that controlling a learning robot enables supervisors to achieve similar task performance as with a non-learning robot, but with both fewer interventions and a reduced perception of workload. These results demonstrate the utility of the SPARC concept and its potential effectiveness to reduce load on human WoZ supervisors.