A Novel Approach to Efficient Monte-Carlo Localization in RoboCup

Authors:
Patrick Heinemann;Jürgen Haase;Andreas Zell
Affiliations:
Wilhelm-Schickard-Institute, Department of Computer Architecture, University of Tübingen, Sand 1, 72076 Tübingen, Germany;Wilhelm-Schickard-Institute, Department of Computer Architecture, University of Tübingen, Sand 1, 72076 Tübingen, Germany;Wilhelm-Schickard-Institute, Department of Computer Architecture, University of Tübingen, Sand 1, 72076 Tübingen, Germany
Venue:
RoboCup 2006: Robot Soccer World Cup X
Year:
2006

Citing 6
Cited 2

Monte Carlo localization: efficient position estimation for mobile robots

AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
A Two-Tiered Approach to Self-Localization

RoboCup 2001: Robot Soccer World Cup V
Self-Localization in the RoboCup Environment

RoboCup-99: Robot Soccer World Cup III
A Localization Method for a Soccer Robot Using a Vision-Based Omni-Directional Sensor

RoboCup 2000: Robot Soccer World Cup IV
Vision-Based Localization in RoboCup Environments

RoboCup 2000: Robot Soccer World Cup IV
A new omnidirectional vision sensor for monte-carlo localization

RoboCup 2004

Towards a Calibration-Free Robot: The ACT Algorithm for Automatic Online Color Training

RoboCup 2006: Robot Soccer World Cup X
Robot orientation with histograms on MSL

Robot Soccer World Cup XV

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, efficient self-localization methods have been developed, among which probabilistic Monte-Carlo localization (MCL) is one of the most popular. However, standard MCL algorithms need at least 100 samples to compute an acceptable position estimation. This paper presents a novel approach to MCL that uses an adaptive number of samples that drops down to a single sample if the pose estimation is sufficiently accurate. Experiments show that the method remains in this efficient single sample tracking modefor more than 90% of the cycles.