Non-uniform image sampling for robot motion control by the GFS neural algorithm

The purpose of this work is to give a neural algorithm that allows a controller to determine robot's location within an environment like a building, by observing through a camera some elements of the rooms, as for instance the ceiling or the floor; it is natural to suppose that different parts of the digital image sequence coming from the camera would contain less or more useful information to the end of robot motion control: this suggests that in order to improve the efficiency of the control system and to reduce the size of the incoming data, it would be useful to perform a nonuniform image sampling, that is, to extract from the original image some features computed on a number of images' regions.