Neural network learning of variable grid-based maps for the autonomous navigation of robots

Abstract

This paper presents a map learning method that integrates the geometrical and topological paradigms. The geometrical component consists of a feed-forward neural network that interprets the robot's sensor readings eeciently. The topological map is created by learning a variable resolution partitioning of the world. Every partition corresponds to a… (More)
DOI: 10.1109/CIRA.1997.613836

2 Figures and Tables

Topics

  • Presentations referencing similar topics