Abstract: A method for localizing a robot in a localization plane with a bi-dimentional reference with axis x and y comprises: determining by odometry an estimation of coordinates x1 and y1 and orientation ?1 of the robot; determining an estimation ?2 of the orientation of the robot using a virtual compass; determining an estimation ?3 of the orientation of the robot by correlating parts of a reference and a query panorama; determining an estimation x4, y4 of the robot position using Iterative Closest Points; determining standard deviations ?_x1, ?_x2, ?_?1 ?_?2, ?_?3, ?_x4, ?_y4 of the estimations; determining probability distributions G(x1), G(y1), G(?1), G(?2), G(?3), G(x4), G(y4) of each estimation using standard deviations; determining three global distributions GLOB(x), GLOB(y), GLOB(?) and a global estimation xg, yg of the coordinates of the robot in the localization plane and a global estimation ?g of its orientation by applying maximum likelihood to global distributions.