Using the Behavior Markup Language for human-robot interaction

This paper describes a Behavior Markup Language (BML) realizer that we developed for use in our research on human-robot interaction. Existing BML realizers used with virtual agents are based on fixed-timing algorithms and because of that are not suitable for robotic applications. Our realizer uses an event-driven architecture, based on Petri nets, to guarantee the specified synchronization constraints in the presence of unpredictable variability in robot control systems. Our implementation is robot independent, open source and uses the Robot Operating System (ROS).