Solving the Global Localization Problem for Indoor Mobile Robots

Abstract

Abstract. Global localization is the problem of determining the position of a robot under global uncertainty. This problem can be divided in two phases: 1) from the sensor data (or sensor view), determine clusters of hypotheses where the robot can be; and 2) devise a strategy by which the robot can correctly eliminate all but the right location. In the second phase, previous approaches consider an ideal robot, a robot with a perfect odometer, to predict robot movements. This paper introduces a non deterministic prediction approach based on a Markov localization that include an uncertainty model for the movements of the robot. The non deterministic model can help to solve situations where a deterministic or ideal model fails. Hypotheses are clustered and a greedy search algorithm determines the robot movements to reduce the number of clusters of hypotheses. This approach is tested using a simulated mobile robot with promising results.