Appearance-based autonomous robot localization has some advantages over landmark-based localization as, for instance, the simplicity of the processes applied to the sensor readings. The main drawback of appearance-based localization is that it requires a map including images taken at known positions in the environment where the robot is expected to move. In this paper, we describe a concurrent map-building and localization (CML) system developed within the appearance-base robot localization paradigm. This allow us to combine the good features of appearance-base localization without having to deal with its inconveniences. The preliminary results included in this paper qualify this approach as a very promising one.
Josep M. Porta, Ben J. A. Kröse