Practical extensions to vision-based monte carlo localization methods for robot soccer domain

Authors:
Kemal Kaplan;Buluç Çelik;Tekin Meriçli;Çetin Meriçli;H. Levent Akın
Affiliations:
Department of Computer Engineering, Boğaziçi University, Bebek, Ístanbul, Turkey;Department of Computer Engineering, Boğaziçi University, Bebek, Ístanbul, Turkey;Department of Computer Engineering, Marmara University, Göztepe, Ístanbul, Turkey;Department of Computer Engineering, Boğaziçi University, Bebek, Ístanbul, Turkey;Department of Computer Engineering, Boğaziçi University, Bebek, Ístanbul, Turkey
Venue:
RoboCup 2005
Year:
2006

Citing 2
Cited 4

Robust Monte Carlo localization for mobile robots

Artificial Intelligence
Particle filters in robotics

UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence

CooperativeWorld Modeling in Dynamic Multi-Robot Environments

Fundamenta Informaticae - New Frontiers in Scientific Discovery - Commemorating the Life and Work of Zdzislaw Pawlak
Cooperative Object Localization Using Line-Based Percept Communication

RoboCup 2007: Robot Soccer World Cup XI
CooperativeWorld Modeling in Dynamic Multi-Robot Environments

Fundamenta Informaticae - New Frontiers in Scientific Discovery - Commemorating the Life and Work of Zdzislaw Pawlak
Multi-observation sensor resetting localization with ambiguous landmarks

Autonomous Robots

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a set of practical extensions to the vision-based Monte Carlo localization (MCL) for RoboCup Sony AIBO legged robot soccer domain. The main disadvantage of AIBO robots is that they have a narrow field of view so the number of landmarks seen in one frame is usually not enough for geometric calculation. MCL methods have been shown to be accurate and robust in legged robot soccer domain but there are some practical issues that should be handled in order to maintain stability/elasticity ratio in a reasonable level. In this work, we presented four practical extensions in which two of them are novel approaches and the remaining ones are different from the previous implementations.