Multi-hypothesis localization with a rough map using multiple visual features for outdoor navigation

摘要: We describe a method of mobile robot localization based on rough map using stereo vision, which uses multiple visual features to detect and segment the buildings in robot's field view. The is an inaccurate with large uncertainties shapes, dimensions locations objects so that it can be built easily. fuses odometry vision information extended Kalman filters update pose associated uncertainty recognition map. use multi-hypothesis filter generate track Gaussian hypotheses. An experimental result shows feasibility our outdoor environment.