The head carries the robot's sensing and expression. Cameras and a time-of-flight sensor readfaces, gestures and who is nearby, a display and small actuators give the face its expression and let the head turn to track a person, and the recognition that interprets all of it runs on the device. Microphones and speakers handle conversation, with the voice processing done on the robot; environmental sensors helps to understand the context and respond to people while remaining safe, secure, and robust.