Improved adaptive particle filter using adjusted variance and gradient data

Sang Hyuk Park; Young Joong Kim; Hoo Cheol Lee; Myo Taeg Lim

doi:10.1109/MFI.2008.4648018

Improved adaptive particle filter using adjusted variance and gradient data

Sang Hyuk Park, Young Joong Kim, Hoo Cheol Lee, Myo Taeg Lim

School of Electrical Engineering

Research output: Contribution to conference › Paper › peer-review

8 Citations (Scopus)

Abstract

Precise estimation of the position of robots, which is essential in mobile robotics, is difficult. However, particle filter shows great promise in such area. The number of samples is closely related to the operation time in particle filtering. The main issue in real-time situation with regard to particle filtering is to reduce the operation time, which led to the development of adaptive particle filter (APF). We propose a new APF, which adjusts the variance and then, uses the gradient data to generate samples near the high likelihood region. The simulation results show that the new APF performs better, in terms of the total operation time and sample set size, than the standard particle filter and the APF using Kullback-Leibler Distance (KLD) sampling.

Original language	English
Pages	650-655
Number of pages	6
DOIs	https://doi.org/10.1109/MFI.2008.4648018
Publication status	Published - 2008
Event	2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI - Seoul, Korea, Republic of Duration: 2008 Aug 20 → 2008 Aug 22

Other

Other	2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI
Country/Territory	Korea, Republic of
City	Seoul
Period	08/8/20 → 08/8/22

ASJC Scopus subject areas

Control and Systems Engineering
Software
Computer Science Applications

Access to Document

10.1109/MFI.2008.4648018

Cite this

@conference{cb4924a05906415580319176ac9b2e09,

title = "Improved adaptive particle filter using adjusted variance and gradient data",

abstract = "Precise estimation of the position of robots, which is essential in mobile robotics, is difficult. However, particle filter shows great promise in such area. The number of samples is closely related to the operation time in particle filtering. The main issue in real-time situation with regard to particle filtering is to reduce the operation time, which led to the development of adaptive particle filter (APF). We propose a new APF, which adjusts the variance and then, uses the gradient data to generate samples near the high likelihood region. The simulation results show that the new APF performs better, in terms of the total operation time and sample set size, than the standard particle filter and the APF using Kullback-Leibler Distance (KLD) sampling.",

author = "Park, {Sang Hyuk} and Kim, {Young Joong} and Lee, {Hoo Cheol} and Lim, {Myo Taeg}",

year = "2008",

doi = "10.1109/MFI.2008.4648018",

language = "English",

pages = "650--655",

note = "2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI ; Conference date: 20-08-2008 Through 22-08-2008",

}

TY - CONF

T1 - Improved adaptive particle filter using adjusted variance and gradient data

AU - Park, Sang Hyuk

AU - Kim, Young Joong

AU - Lee, Hoo Cheol

AU - Lim, Myo Taeg

PY - 2008

Y1 - 2008

N2 - Precise estimation of the position of robots, which is essential in mobile robotics, is difficult. However, particle filter shows great promise in such area. The number of samples is closely related to the operation time in particle filtering. The main issue in real-time situation with regard to particle filtering is to reduce the operation time, which led to the development of adaptive particle filter (APF). We propose a new APF, which adjusts the variance and then, uses the gradient data to generate samples near the high likelihood region. The simulation results show that the new APF performs better, in terms of the total operation time and sample set size, than the standard particle filter and the APF using Kullback-Leibler Distance (KLD) sampling.

AB - Precise estimation of the position of robots, which is essential in mobile robotics, is difficult. However, particle filter shows great promise in such area. The number of samples is closely related to the operation time in particle filtering. The main issue in real-time situation with regard to particle filtering is to reduce the operation time, which led to the development of adaptive particle filter (APF). We propose a new APF, which adjusts the variance and then, uses the gradient data to generate samples near the high likelihood region. The simulation results show that the new APF performs better, in terms of the total operation time and sample set size, than the standard particle filter and the APF using Kullback-Leibler Distance (KLD) sampling.

UR - http://www.scopus.com/inward/record.url?scp=67650514818&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650514818&partnerID=8YFLogxK

U2 - 10.1109/MFI.2008.4648018

DO - 10.1109/MFI.2008.4648018

M3 - Paper

AN - SCOPUS:67650514818

SP - 650

EP - 655

T2 - 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI

Y2 - 20 August 2008 through 22 August 2008

ER -

Improved adaptive particle filter using adjusted variance and gradient data

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this