Spatial learning with perceptually grounded representations

The goal of this paper is to develop the foundation for a spatial navigation without objective representations. Rather than building the spatial representations on a Euclidean space, a weaker conception of space is used. A type of spatial representation is described that uses perceptual information directly to define the regions in space. By combining such regions, it is possible to derive a number of useful spatial representations such as place-fields, paths and topological maps. Compared to other methods, the representations of the present approach have the advantage that they are always grounded in the perceptual abilities of the robot.