Enhanced Simultaneous Localization and Mapping (ESLAM) for Mobile Robots

Chen Chien Hsu, Wei Yen Wang, Tung Yuan Lin, Yin Tien Wang, Teng Wei Huang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

FastSLAM, such as FastSLAM 1.0 and FastSLAM 2.0, is a popular algorithm to solve the simultaneous localization and mapping (SLAM) problem for mobile robots. In real environments, however, the execution speed by FastSLAM would be too slow to achieve the objective of real-time design with a satisfactory accuracy because of excessive comparisons of the measurement with all the existing landmarks in particles, particularly when the number of landmarks is drastically increased. In this paper, an enhanced SLAM (ESLAM) is proposed, which uses not only odometer information but also sensor measurements to estimate the robot's pose in the prediction step. Landmark information that has the maximum likelihood is then used to update the robot's pose before updating the landmarks' location. Compared to existing FastSLAM algorithms, the proposed ESLAM algorithm has a better performance in terms of computation efficiency as well as localization and mapping accuracy as demonstrated in the illustrated examples.

Original languageEnglish
Article number1750007
JournalInternational Journal of Humanoid Robotics
Volume14
Issue number2
DOIs
Publication statusPublished - 2017 Jun 1

Fingerprint

Mobile robots
Robots
Maximum likelihood
Sensors

Keywords

  • extended Kalman filter
  • FastSLAM
  • navigation
  • particle filter
  • Simultaneous localization and mapping
  • SLAM

ASJC Scopus subject areas

  • Mechanical Engineering
  • Artificial Intelligence

Cite this

Enhanced Simultaneous Localization and Mapping (ESLAM) for Mobile Robots. / Hsu, Chen Chien; Wang, Wei Yen; Lin, Tung Yuan; Wang, Yin Tien; Huang, Teng Wei.

In: International Journal of Humanoid Robotics, Vol. 14, No. 2, 1750007, 01.06.2017.

Research output: Contribution to journalArticle

@article{182bd496cfa94dee9ec72a861786ea5e,
title = "Enhanced Simultaneous Localization and Mapping (ESLAM) for Mobile Robots",
abstract = "FastSLAM, such as FastSLAM 1.0 and FastSLAM 2.0, is a popular algorithm to solve the simultaneous localization and mapping (SLAM) problem for mobile robots. In real environments, however, the execution speed by FastSLAM would be too slow to achieve the objective of real-time design with a satisfactory accuracy because of excessive comparisons of the measurement with all the existing landmarks in particles, particularly when the number of landmarks is drastically increased. In this paper, an enhanced SLAM (ESLAM) is proposed, which uses not only odometer information but also sensor measurements to estimate the robot's pose in the prediction step. Landmark information that has the maximum likelihood is then used to update the robot's pose before updating the landmarks' location. Compared to existing FastSLAM algorithms, the proposed ESLAM algorithm has a better performance in terms of computation efficiency as well as localization and mapping accuracy as demonstrated in the illustrated examples.",
keywords = "extended Kalman filter, FastSLAM, navigation, particle filter, Simultaneous localization and mapping, SLAM",
author = "Hsu, {Chen Chien} and Wang, {Wei Yen} and Lin, {Tung Yuan} and Wang, {Yin Tien} and Huang, {Teng Wei}",
year = "2017",
month = "6",
day = "1",
doi = "10.1142/S0219843617500074",
language = "English",
volume = "14",
journal = "International Journal of Humanoid Robotics",
issn = "0219-8436",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "2",

}

TY - JOUR

T1 - Enhanced Simultaneous Localization and Mapping (ESLAM) for Mobile Robots

AU - Hsu, Chen Chien

AU - Wang, Wei Yen

AU - Lin, Tung Yuan

AU - Wang, Yin Tien

AU - Huang, Teng Wei

PY - 2017/6/1

Y1 - 2017/6/1

N2 - FastSLAM, such as FastSLAM 1.0 and FastSLAM 2.0, is a popular algorithm to solve the simultaneous localization and mapping (SLAM) problem for mobile robots. In real environments, however, the execution speed by FastSLAM would be too slow to achieve the objective of real-time design with a satisfactory accuracy because of excessive comparisons of the measurement with all the existing landmarks in particles, particularly when the number of landmarks is drastically increased. In this paper, an enhanced SLAM (ESLAM) is proposed, which uses not only odometer information but also sensor measurements to estimate the robot's pose in the prediction step. Landmark information that has the maximum likelihood is then used to update the robot's pose before updating the landmarks' location. Compared to existing FastSLAM algorithms, the proposed ESLAM algorithm has a better performance in terms of computation efficiency as well as localization and mapping accuracy as demonstrated in the illustrated examples.

AB - FastSLAM, such as FastSLAM 1.0 and FastSLAM 2.0, is a popular algorithm to solve the simultaneous localization and mapping (SLAM) problem for mobile robots. In real environments, however, the execution speed by FastSLAM would be too slow to achieve the objective of real-time design with a satisfactory accuracy because of excessive comparisons of the measurement with all the existing landmarks in particles, particularly when the number of landmarks is drastically increased. In this paper, an enhanced SLAM (ESLAM) is proposed, which uses not only odometer information but also sensor measurements to estimate the robot's pose in the prediction step. Landmark information that has the maximum likelihood is then used to update the robot's pose before updating the landmarks' location. Compared to existing FastSLAM algorithms, the proposed ESLAM algorithm has a better performance in terms of computation efficiency as well as localization and mapping accuracy as demonstrated in the illustrated examples.

KW - extended Kalman filter

KW - FastSLAM

KW - navigation

KW - particle filter

KW - Simultaneous localization and mapping

KW - SLAM

UR - http://www.scopus.com/inward/record.url?scp=85017506496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017506496&partnerID=8YFLogxK

U2 - 10.1142/S0219843617500074

DO - 10.1142/S0219843617500074

M3 - Article

AN - SCOPUS:85017506496

VL - 14

JO - International Journal of Humanoid Robotics

JF - International Journal of Humanoid Robotics

SN - 0219-8436

IS - 2

M1 - 1750007

ER -