Real-time . . . Monte Carlo Localization

A new technique for vision processing is presented which lets a mobile robot equipped with an omnidirectional camera perform appearance-based global localization in real-time. The technique is applied directly to the omnidirectional camera images, producing low-dimensional rotation invariant feature vectors without any training or setup phase. Using the feature vectors, particle lters can accurately estimate the location of a continuously moving real robot, processing 5 000 simultaneous localization hypotheses on-line. Estimated body positions overlap the actual ones in over 95 % of the time steps. The feature vectors show a graceful degradation against increasing levels of simulated noise and occlusion