S. Thrun, W. Burgard, and D. Fox

A Probabilistic Approach toConcurrent Mapping and Localization for Mobile Robots

Machine Learning / Autonomous Robots (joint issue)


 

Abstract

This paper addresses the problem of building large-scalegeometric maps of indoor environments with mobile robots. It poses themap building problemas a constrained, probabilisticmaximum-likelihood estimation problem. Itthen devises a practicalalgorithm for generating the most likely map fromdata, along with themost likely path taken by the robot. Experimental resultsin cyclicenvironments of size up to 80 by 25 meter illustrate theappropriateness of the approach.

Download

Full paper [.ps.gz](2201 kb, 25 pages)

Bibtex

@ARTICLE{Thr98Pro,
  AUTHOR  = {Thrun, S. and Burgard, W. and Fox, D.},
  TITLE   = {A Probabilistic Approach to Concurrent Mapping and Localization for MobileRobots},
  JOURNAL = {MachineLearning and Autonomous Robots (joint issue)},
  NUMBER  = {31/5},
  YEAR    = {1998}
}