A telepresence robot includes a mobile platform, a camera, and a computer in communication with the platform and the camera. The computer receives video information from a remotely located camera relating to a gesture made by a remote human operator, and the robot is configured to operate based on the gesture. The computer may further predict an emotional state of a person interacting with the robot, based on video information received from the robot camera. A telepresence robot system includes: a telepresence robot having a mobile platform, a robot camera, a robot display, and a robot computer; and a control station, located remote to the robot, having a control station camera, a control station display, and a control station computer.