A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots

  • Authors:
  • Sebastian Thrun;Wolfram Burgard;Dieter Fox

  • Affiliations:
  • Computer Science Department and Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213-3891. http://www.cs.cmu.edu/∼thrun;Institut für Informatik III, Universität Bonn, D-53117 Bonn, Germany. http://www.cs.uni-bonn.de/∼wolfram;Institut für Informatik III, Universität Bonn, D-53117 Bonn, Germany. http://www.cs.uni-bonn.de/∼fox

  • Venue:
  • Machine Learning - Special issue on learning in autonomous robots
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper addresses the problem of building large-scalegeometric maps of indoor environments with mobile robots. It posesthe map building problem as a constrained, probabilisticmaximum-likelihood estimation problem. It then devises a practicalalgorithm for generating the most likely map from data, along with themost likely path taken by the robot. Experimental results in cyclicenvironments of size up to 80 by 25 meter illustrate theappropriateness of the approach.