Machine Vision and Applications

, Volume 13, Issue 2, pp 51–60 | Cite as

Accuracy bounds and optimal computation of robot localization

  • Kenichi Kanatani
  • Naoya Ohta
Original papers


We present an optimal method for estimating the current location of a mobile robot by matching an image of the scene taken by the robot with a model of the known environment. We first derive a theoretical accuracy bound and then give a computational scheme that can attain that bound, which can be viewed as describing the probability distribution of the current location. Using real images, we demonstrate that our method is superior to the naive least-squares method. We also confirm the theoretical predictions of our theory by applying the bootstrap procedure.

Key words: Mobile robot – Localization – Statistical estimation – Theoretical accuracy bound – Bootstrap 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Kenichi Kanatani
    • 1
  • Naoya Ohta
    • 2
  1. 1.Department of Information Technology, Okayama University, Okayama 700-8530, Japan JP
  2. 2.Department of Computer Science, Gunma University, Kiryu, Gunma 376-8515, Japan JP

Personalised recommendations