Browse > Article
http://dx.doi.org/10.3745/KIPSTB.2012.19B.1.027

Particle Filter Localization Using Noisy Models  

Kim, In-Cheol (경기대학교 컴퓨터과학과)
Kim, Seung-Yeon (경기대학교 컴퓨터과학과)
Kim, Hye-Suk (경기대학교 컴퓨터과학과)
Abstract
One of the most fundamental functions required for an intelligent agent is to estimate its current position based upon uncertain sensor data. In this paper, we explain the implementation of a robot localization system using Particle filters, which are the most effective one of the probabilistic localization methods, and then present the result of experiments for evaluating the performance of our system. Through conducting experiments to compare the effect of the noise-free model with that of the noisy state transition model considering inherent errors of robot actions, we show that it can help improve the performance of the Particle filter localization to apply a state transition model closely approximating the uncertainty of real robot actions.
Keywords
Particle Filter; Uncertainty; Robot Localization System; Noisy Model; Bayes Filter;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Sebastian Thrun, Wolfram Burgard, Dieter Fox, Probabilistic Robotics, MIT Press, 2005.
2 김인철, 오휘경, "모바일 퍼스널 어시스턴트의 지능 행위 구현을 위한 스마트 스크립트 시스템", 정보처리학회논문지 B, 제18-B 권, 제2호, pp.83-86, 2011.
3 Jeong Woo, et al, "Localization of Mobile Robot using Particle Filter", Proc. of SICE-ICASE-2006, 2006.
4 Dieter Fox, Wolfram Burgard, Frank Dellaert and Sebastian Thrun, "Monte Carlo Localization: Efficient Position Estimation of Mobile Robots", Proc. of AAAI-1999, 1999.
5 Brian Bagnall, et al, leJos: Java for Lego Mindstorms, http://lejos.sourceforge.net, 2009.