AUTONOMOUS MOBILE ROBOT GLOBAL SELF-LOCALIZATION USING KOHONEN AND REGION-FEATURE NEURAL NETWORKS

This article presents and compares two neural network-based approaches to global self-localization (GSL) for autonomous mobile robots using: (1) a Kohonen neural network; and (2) a region-feature neural network (RFNN). Both approaches categorize discrete regions of space (topogra phical nodes) in a manner similar to optical character recognition (OC R). That is, the mapped sonar data assumes the form of a character uni que to that region. Hence, it is believed that an autonomous vehicle c an determine which room it is in from sensory data gathered from explo ration. With a robust exploration routine, the GSL solution can be tim e-, translation-, and rotation-invariant. The GSL solution can also be come independent of the mobile robot used to collect the sensor data. This suggests that a single robot can transfer its knowledge of variou s learned regions to other mobile robots. The classification rate of b oth approaches are comparable and, thus, worthy of presentation. The o bserved pros and cons of both approaches are also discussed. (C) 1997 John Wiley & Sons, Inc.