Ultrasonic robot localization using Dempster-Shafer theory

Abstract

A localization algorithm for ultrasonic robot described is based on range readings from wide beam ultrasonic transducers to built a model of the empty regions in the room. The method is incorporated into a move-to-station behavior which was demonstrated on the Georgia Tech mobile robot. A belief model of the range of readings that was based on Dempster-Shafer theory was used to compute the belief of points in the environment being empty, occupied, or unknown. The current belief in the empty space was used to construct a weighted centroid of the empty space after each move of the robot. By moving toward this center of mass and continually adding to the beliefs of the point in the environment the robot iteratively moved to the center of the open space.