Non-metrical navigation through visual path control

We describe a new method for wide-area, non-metrical robot navigation which enables useful, purposeful motion indoors. Our method has two phases: a training phase, in which a human user directs a wheeled robot with an attached camera through an environment while occasionally supplying textual place names; and a navigation phase in which the user specifies goal place names (again as text), and the robot issues low-level motion control in order to move to the specified place. We show that differences in the visual-field locations and scales of features matched across training and navigation can be used to construct a simple and robust control rule that guides the robot onto and along the training motion path. Our method uses an omnidirectional camera, requires ap-proximate intrinsic and extrinsic camera calibration, and is ca-pable of effective motion control within an extended, minimally-prepared building environment floorplan. We give results for deployment within a single building floor with 7 rooms, 6 corridor segments, and 15 distinct place names. I