Just got this pieced together...Robot looks around, recognizes words written on walls and determines compass bearings to each. Robot then determines what room it is in based on its memory of visual landmarks, and loads a map for the given room. At this point, the robot calculates its location in the room to within a few inches. Robot then knows where other features are within the room based on its map (Doors, Windows, Obstacles). In the video, the robot announces the heading to the door.