Bayesian Landmark Learning for Mobile Robot Localization - Robotics Institute Carnegie Mellon University

Bayesian Landmark Learning for Mobile Robot Localization

Sebastian Thrun
Journal Article, Machine Learning, Vol. 33, No. 1, pp. 41 - 76, October, 1998

Abstract

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 (e.g., 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 outperforms two other recent approaches to mobile robot localization.

BibTeX

@article{Thrun-1998-16535,
author = {Sebastian Thrun},
title = {Bayesian Landmark Learning for Mobile Robot Localization},
journal = {Machine Learning},
year = {1998},
month = {October},
volume = {33},
number = {1},
pages = {41 - 76},
}