Vision-based extended Monte Carlo localization for mobile robot

Extended Monte Carlo localization, augmentation of conventional Monte Carlo localization (MCL) appropriately with triangulation-based re-sampling, is proposed in this paper in order to increase computational efficiency and avoid over-convergence. The over-convergence and uniformity validations are used to verify correspondence between sample distribution and sensor information for the integration of different resampling processes. Vision-based extended MCL is realized that is applied to a networked robotic system, in which Bayesian networks are introduced to recognize polyhedron features in office environments for localization. Experimental results demonstrate the validity of the approach.