Learning View Graphs for Robot Navigation

  • Authors:
  • Matthias O. Franz;Bernhard Schölkopf;Hanspeter A. Mallot;Heinrich H. Bülthoff

  • Affiliations:
  • Max-Planck-Institut für biologische Kybernetik, Spemannstraße 38, 72076 Tübingen, Germany.;Max-Planck-Institut für biologische Kybernetik, Spemannstraße 38, 72076 Tübingen, Germany.;Max-Planck-Institut für biologische Kybernetik, Spemannstraße 38, 72076 Tübingen, Germany.;Max-Planck-Institut für biologische Kybernetik, Spemannstraße 38, 72076 Tübingen, Germany.

  • Venue:
  • Autonomous Robots - Special issue on autonomous agents
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a purely vision-based scheme for learning a topologicalrepresentation of an open environment. The system represents selected placesby local views of the surrounding scene, and finds traversable paths betweenthem. The set of recorded views and their connections are combined into agraph model of the environment. To navigate between views connected in thegraph, we employ a homing strategy inspired by findings of insect ethology.In robot experiments, we demonstrate that complex visual exploration andnavigation tasks can thus be performed without using metric information.