The disclosure provides methods and systems for spatial communication in a tele-presence system. In particular, the present technology provides human-robot interaction that allows users to feel a stronger sense of successful communication with a tele-presence system. Various embodiments of the present technology facilitate spatial communication between users via the tele-presence system, including communicating body language, spatial awareness, and improved information display, with a tele-presence device including a camera system and a hub. The methods and systems may include determining a user input, such as a gesture, indicative of an object, and detecting and tracking the object. The methods and systems may further include transmitting at least one control signal to one or more servo motors coupled to the camera system, the at least one control signal configured to reposition the camera system such that the detected object is kept within boundaries of a video signal.