A new global localization algorithm based on feature extraction and particle filter

Daniele Caltabiano, Giovanni Muscato, Salvatore Sessa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper describes a new global localization algorithm based on feature extraction and particle filter. This algorithm uses two kinds of sensors: wheels encoders and a laser scanner. A map of the environment is built by taking laser readings of the environment from well-known poses of the robot. The resulting map is composed by a list of features, representing the position of clusters obtained by using the mean shift algorithm. The mean shift algorithm is also applied for each sampling step in order to calculate the importance factor of the particles. The trials have been conducted by using a simulator of a differential drive robot.

Original languageEnglish
Title of host publication14th Mediterranean Conference on Control and Automation, MED'06
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event14th Mediterranean Conference on Control and Automation, MED'06 - Ancona
Duration: 2006 Jun 282006 Jun 30

Other

Other14th Mediterranean Conference on Control and Automation, MED'06
CityAncona
Period06/6/2806/6/30

Fingerprint

Feature extraction
Robots
Lasers
Wheels
Simulators
Sampling
Sensors

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Caltabiano, D., Muscato, G., & Sessa, S. (2006). A new global localization algorithm based on feature extraction and particle filter. In 14th Mediterranean Conference on Control and Automation, MED'06 [1700761] https://doi.org/10.1109/MED.2006.328798

A new global localization algorithm based on feature extraction and particle filter. / Caltabiano, Daniele; Muscato, Giovanni; Sessa, Salvatore.

14th Mediterranean Conference on Control and Automation, MED'06. 2006. 1700761.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Caltabiano, D, Muscato, G & Sessa, S 2006, A new global localization algorithm based on feature extraction and particle filter. in 14th Mediterranean Conference on Control and Automation, MED'06., 1700761, 14th Mediterranean Conference on Control and Automation, MED'06, Ancona, 06/6/28. https://doi.org/10.1109/MED.2006.328798
Caltabiano D, Muscato G, Sessa S. A new global localization algorithm based on feature extraction and particle filter. In 14th Mediterranean Conference on Control and Automation, MED'06. 2006. 1700761 https://doi.org/10.1109/MED.2006.328798
Caltabiano, Daniele ; Muscato, Giovanni ; Sessa, Salvatore. / A new global localization algorithm based on feature extraction and particle filter. 14th Mediterranean Conference on Control and Automation, MED'06. 2006.
@inproceedings{00b2c75ff8d0491baad087155ef58fa2,
title = "A new global localization algorithm based on feature extraction and particle filter",
abstract = "This paper describes a new global localization algorithm based on feature extraction and particle filter. This algorithm uses two kinds of sensors: wheels encoders and a laser scanner. A map of the environment is built by taking laser readings of the environment from well-known poses of the robot. The resulting map is composed by a list of features, representing the position of clusters obtained by using the mean shift algorithm. The mean shift algorithm is also applied for each sampling step in order to calculate the importance factor of the particles. The trials have been conducted by using a simulator of a differential drive robot.",
author = "Daniele Caltabiano and Giovanni Muscato and Salvatore Sessa",
year = "2006",
doi = "10.1109/MED.2006.328798",
language = "English",
isbn = "0978672003",
booktitle = "14th Mediterranean Conference on Control and Automation, MED'06",

}

TY - GEN

T1 - A new global localization algorithm based on feature extraction and particle filter

AU - Caltabiano, Daniele

AU - Muscato, Giovanni

AU - Sessa, Salvatore

PY - 2006

Y1 - 2006

N2 - This paper describes a new global localization algorithm based on feature extraction and particle filter. This algorithm uses two kinds of sensors: wheels encoders and a laser scanner. A map of the environment is built by taking laser readings of the environment from well-known poses of the robot. The resulting map is composed by a list of features, representing the position of clusters obtained by using the mean shift algorithm. The mean shift algorithm is also applied for each sampling step in order to calculate the importance factor of the particles. The trials have been conducted by using a simulator of a differential drive robot.

AB - This paper describes a new global localization algorithm based on feature extraction and particle filter. This algorithm uses two kinds of sensors: wheels encoders and a laser scanner. A map of the environment is built by taking laser readings of the environment from well-known poses of the robot. The resulting map is composed by a list of features, representing the position of clusters obtained by using the mean shift algorithm. The mean shift algorithm is also applied for each sampling step in order to calculate the importance factor of the particles. The trials have been conducted by using a simulator of a differential drive robot.

UR - http://www.scopus.com/inward/record.url?scp=35948950335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35948950335&partnerID=8YFLogxK

U2 - 10.1109/MED.2006.328798

DO - 10.1109/MED.2006.328798

M3 - Conference contribution

AN - SCOPUS:35948950335

SN - 0978672003

SN - 9780978672003

BT - 14th Mediterranean Conference on Control and Automation, MED'06

ER -