Omnidirectional vision based topological navigation
This work presents a unique system for autonomous mobile robot navigation. The main sensor is an omnidirectional camera. The proposed system is capable to build automatically a topological map complex, natural environments. It can localise itself using that map on each moment, after startup (kidnapped robot) or using knowledge of former localisations. The topological nature of the map enables fast and simple path planning towards a specified goal. A visual servoing technique is implemented to steer the system along the computed path. The key technology making this all possible is the novel fast wide baseline feature matching, which yields an efficient abstraction of the wealth of information offered by the visual sensor.