Vision-based navigation and environmental representations with an omnidirectional camera

This paper proposes a method for the visual-based navigation of a mobile ro bot in indoor environments, using a single omnidirectional (catadioptric) c amera. The geometry of the catadioptric sensor and the method used to obtai n a bird's eye (orthographic) view of the ground plane are presented. This representation significantly simplifies the solution to navigation problems , by eliminating any perspective effects. The nature of each navigation task is taken into account when designing the required navigation skills and environmental representations. We propose t wo main navigation modalities: topological navigation and visual path follo wing. Topological navigation is used for traveling long distances and does not re quire knowledge of the exact position of the robot but rather, a qualitativ e position on the topological map. The navigation process combines appearan ce based methods and visual servoing upon some environmental features. Visual path following is required for local, very precise navigation, e.g., door traversal, docking. The robot is controlled to follow a prespecified path accurately, by tracking visual landmarks in bird's eye views of the gr ound plane. By clearly separating the nature of these navigation tasks, a simple and ye t powerful navigation system is obtained.