Slawomir Grzonka, Christian Plagemann, Giorgio Grisetti, Wolfram Burgard
Look-ahead Proposals for Robust Grid-based SLAM with Rao-Blackwellized
Particle Filters
Abstract:
Simultaneous Localization and Mapping (SLAM) is one of the classical
problems in mobile robotics. The task is to build a map of the environ-
ment using on-board sensors while at the same time localizing the robot
relative to this map. Rao-Blackwellized particle filters have emerged as a
powerful technique for solving the SLAMproblem in a wide variety of envi-
ronments. It is a well-known fact for sampling-based approaches that the
choice of the proposal distribution greatly influences robustness and effi-
ciency achievable by the algorithm. In this paper, we present an improved
proposal distribution for grid-based SLAM with Rao-Blackwellized parti-
cle filters, which utilizes whole sequences of sensor measurements rather
than only the most recent one. We have implemented our system on a
real robot and evaluated its performance on standard data sets as well as
in hard outdoor settings with few and ambiguous features. Our approach
improves the localization accuracy and the map quality and substantially
reduces the risk of mapping failures.
Bibtex:
@article{grzonka09ijrr,
author = {Grzonka, S. and Plagemann, C. and Grisetti, G. and Burgard, W.},
title = {Look-ahead Proposals for Robust Grid-based SLAM with
Rao-Blackwellized Particle Filters},
booktitle = {International Journal of Robotics Research (IJRR)},
year = {2009},
month= {Feb},
pages= {191-200}
}
Paper (pdf file):
full paper