View-based cognitive map learning by an autonomous robot

Mallot, HA; Bülthoff, HH; Georg, P; Schölkopf, B; Yasuhara, K

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

会議論文

View-based cognitive map learning by an autonomous robot

MPS-Authors

/persons/resource/persons84072

Mallot, HA
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83839

Bülthoff, HH
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83930

Georg, P
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84193

Schölkopf, B
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84322

Yasuhara, K
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

https://www.semanticscholar.org/paper/View-based-cognitive-map-learning-by-an-autonomous-Mallot-B%C3%BClthoff/86a50d6cd893ad5337e752cf83af99a50738b431
(要旨)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

pdf668.pdf
(全文テキスト（全般）), 194KB

付随資料 (公開)

There is no public supplementary material available

引用

Mallot, H., Bülthoff, H., Georg, P., Schölkopf, B., & Yasuhara, K. (1995). View-based cognitive map learning by an autonomous robot. In F., Fogelman-Soulié, & R., Gallinari (Eds.), Conférence Internationale sur les Réseaux de Neurones Artificiels (ICANN 1995) (pp. 381-386). Paris, France: EC2.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-EC58-1

要旨

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.