Morphological neural networks and vision based simultaneous localization and mapping

Simultaneous Localization and Mapping (SLAM) is a key process in several robotic contexts. In this paper we explore the realization of non-metric SLAM using a visual information based approach relying on the detection of morphologically independent images. Morphologically independent images correspond to approximations to the vertices of the convex hull covering the data points in high dimensional space. The selected images are proposed as the landmarks for localization, building simultaneously a qualitative map of the environment. We report results of some experiments on data gathered from an indoor ambient.