This file was created by the Typo3 extension sevenpack version 0.7.14 --- Timezone: CEST Creation date: 2013-05-26 Creation time: 05-37-56 --- Number of references 1 inproceedings 668 Proceedings International Conference on Artificial Neural Networks (ICANN 1995 10 381-386 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. http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/pdf668.pdf http://www.kyb.tuebingen.mpg.de http://www.kyb.tuebingen.mpg.de Department Bülthoff Fogelman-Soulié, F. EC2

Paris, France

Biologische Kybernetik Max-Planck-Gesellschaft Paris, France Conférence Internationale sur les Réseaux de Neurones Artificiels (ICANN '95) 2-910085-18-X hamHAMallot hhbHHBülthoff pgPGeorg bsBSchölkopf kyasuharaKYasuhara