View-based cognitive map learning by an autonomous robot

Abstract

This paper presents a view--based approach to map learning and navigation in mazes. By means of graph theory we have shown that the view--graph is a sufficient representation for map behaviour such as path planning. A neural network for unsupervised learning of the view--graph from sequences of views is constructed. We use a modified Kohonen (1988) learning rule that transforms temporal sequence (rather than featural similarity) into connectedness. In the main part of the paper, we present a robot implementation of the scheme. The results show that the proposed network is able to support map behaviour in simple environments. 1 Introduction: The view--graph representation A cognitive map is a neural mechanism supporting navigation and orientation tasks much as a real map of the environment. Scholkopf and Mallot (1995) presented a mechanism for the learning of a cognitive map of a maze from the sequence of local views encountered when exploring the maze. In this approach, the topologic...