To operate successfully in indoor environments, mobile robots must be able to localize themselves. Most current localization algorithms lack flexibility, autonomy, and often optimality, since they rely on a human to determine what aspects of the sensor data to use in localization (\eg what landmarks to use). This paper describes a learning algorithm, called BaLL, that enables mobile robots to learn what features/landmarks are best suited for localization, and also to train artificial neural networks for extracting them from the sensor data. A rigorous Bayesian analysis of probabilistic localization is presented, which produces a rational argument for evaluating features, for selecting them optimally, and for training the networks that approximate the optimal solution. In a systematic experimental study, BaLL is found to outperform two other recent approaches to mobile robot localization.
Click here to obtain the full paper in gzipped postscript format and PDF
@ARTICLE{Thrun98b,
AUTHOR = {S. Thrun},
YEAR = {1998},
TITLE = {{B}ayesian Landmark Learning for Mobile Robot
Localization},
JOURNAL = {Machine Learning},
VOLUME = {33},
NUMBER = {1},
PAGES = {41--76}
}