Enabling Synchronous Joint Action in Human-Robot Teams

Abstract

Joint action is an increasing area of interest for HRI researchers. To be effective team members, robots need to be able to understand, anticipate, and react appropriately to high-level human social behavior. We have designed a new approach to enable an autonomous robot to act fluently within a synchronous human-robot team. We present an initial description and validation study of this approach. Using a synchronous dance scenario as an experimental testbed, we found that our robot was able to execute appropriate actions using our method. Moving forward, we aim to extend this method by developing predictions for the robot's actions using an understanding of the group's dynamics. Our method will be helpful to other researchers working to achieve fluency of action within human-robot groups.