Stereo SLAM using two estimators

Trung Ngo Thanh, Yusuke Sakaguchi, Hajime Nagahara, Masahiko Yachida

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

3 Citations (Scopus)

Abstract

This paper proposes a new algorithm for Simultaneous Localization and Mapping (SLAM) with omnidirectional stereo vision. In our approach, stereo matching is solved efficiently by using the estimated spatial information of the environment and robot motion. The use of two EKF (Extended Kalman Filter) estimators brings about a more reliable robot trajectory and a better map of the environment with more landmarks. The first estimator (a binocular estimator) mostly focuses on the robot trajectory; the second estimator (a monocular estimator) is devoted to the map building. Reliably matched landmarks are entered into the first estimator to establish the reliable robot position and some of the landmark positions. Other landmarks, which have more uncertainty of stereo combination or are observed by only one camera, are passed to the second estimator to establish their positions. This structure results in more precise estimation of robot trajectory and a map of the environment with more landmarks.

Original languageEnglish
Title of host publication2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006
Pages19-24
Number of pages6
DOIs
Publication statusPublished - 2006
Event2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006 - Kunming, China
Duration: Dec 17 2006Dec 20 2006

Other

Other2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006
CountryChina
CityKunming
Period12/17/0612/20/06

Fingerprint

Robots
Trajectories
Binoculars
Stereo vision
Extended Kalman filters
Cameras

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Thanh, T. N., Sakaguchi, Y., Nagahara, H., & Yachida, M. (2006). Stereo SLAM using two estimators. In 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006 (pp. 19-24). [4141833] https://doi.org/10.1109/ROBIO.2006.340253

Stereo SLAM using two estimators. / Thanh, Trung Ngo; Sakaguchi, Yusuke; Nagahara, Hajime; Yachida, Masahiko.

2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006. 2006. p. 19-24 4141833.

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

Thanh, TN, Sakaguchi, Y, Nagahara, H & Yachida, M 2006, Stereo SLAM using two estimators. in 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006., 4141833, pp. 19-24, 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006, Kunming, China, 12/17/06. https://doi.org/10.1109/ROBIO.2006.340253
Thanh TN, Sakaguchi Y, Nagahara H, Yachida M. Stereo SLAM using two estimators. In 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006. 2006. p. 19-24. 4141833 https://doi.org/10.1109/ROBIO.2006.340253
Thanh, Trung Ngo ; Sakaguchi, Yusuke ; Nagahara, Hajime ; Yachida, Masahiko. / Stereo SLAM using two estimators. 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006. 2006. pp. 19-24
@inproceedings{874c61d690ad477eae66d71ced3a78b4,
title = "Stereo SLAM using two estimators",
abstract = "This paper proposes a new algorithm for Simultaneous Localization and Mapping (SLAM) with omnidirectional stereo vision. In our approach, stereo matching is solved efficiently by using the estimated spatial information of the environment and robot motion. The use of two EKF (Extended Kalman Filter) estimators brings about a more reliable robot trajectory and a better map of the environment with more landmarks. The first estimator (a binocular estimator) mostly focuses on the robot trajectory; the second estimator (a monocular estimator) is devoted to the map building. Reliably matched landmarks are entered into the first estimator to establish the reliable robot position and some of the landmark positions. Other landmarks, which have more uncertainty of stereo combination or are observed by only one camera, are passed to the second estimator to establish their positions. This structure results in more precise estimation of robot trajectory and a map of the environment with more landmarks.",
author = "Thanh, {Trung Ngo} and Yusuke Sakaguchi and Hajime Nagahara and Masahiko Yachida",
year = "2006",
doi = "10.1109/ROBIO.2006.340253",
language = "English",
isbn = "1424405718",
pages = "19--24",
booktitle = "2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006",

}

TY - GEN

T1 - Stereo SLAM using two estimators

AU - Thanh, Trung Ngo

AU - Sakaguchi, Yusuke

AU - Nagahara, Hajime

AU - Yachida, Masahiko

PY - 2006

Y1 - 2006

N2 - This paper proposes a new algorithm for Simultaneous Localization and Mapping (SLAM) with omnidirectional stereo vision. In our approach, stereo matching is solved efficiently by using the estimated spatial information of the environment and robot motion. The use of two EKF (Extended Kalman Filter) estimators brings about a more reliable robot trajectory and a better map of the environment with more landmarks. The first estimator (a binocular estimator) mostly focuses on the robot trajectory; the second estimator (a monocular estimator) is devoted to the map building. Reliably matched landmarks are entered into the first estimator to establish the reliable robot position and some of the landmark positions. Other landmarks, which have more uncertainty of stereo combination or are observed by only one camera, are passed to the second estimator to establish their positions. This structure results in more precise estimation of robot trajectory and a map of the environment with more landmarks.

AB - This paper proposes a new algorithm for Simultaneous Localization and Mapping (SLAM) with omnidirectional stereo vision. In our approach, stereo matching is solved efficiently by using the estimated spatial information of the environment and robot motion. The use of two EKF (Extended Kalman Filter) estimators brings about a more reliable robot trajectory and a better map of the environment with more landmarks. The first estimator (a binocular estimator) mostly focuses on the robot trajectory; the second estimator (a monocular estimator) is devoted to the map building. Reliably matched landmarks are entered into the first estimator to establish the reliable robot position and some of the landmark positions. Other landmarks, which have more uncertainty of stereo combination or are observed by only one camera, are passed to the second estimator to establish their positions. This structure results in more precise estimation of robot trajectory and a map of the environment with more landmarks.

UR - http://www.scopus.com/inward/record.url?scp=46249088163&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46249088163&partnerID=8YFLogxK

U2 - 10.1109/ROBIO.2006.340253

DO - 10.1109/ROBIO.2006.340253

M3 - Conference contribution

SN - 1424405718

SN - 9781424405718

SP - 19

EP - 24

BT - 2006 IEEE International Conference on Robotics and Biomimetics, ROBIO 2006

ER -