New framework for simultaneous localization and mapping

Multi map SLAM

Damith C. Herath, S. Kodagoda, Gamini Dissanayake

Research output: A Conference proceeding or a Chapter in BookConference contribution

4 Citations (Scopus)

Abstract

The main contribution of this paper arises from the development of a new framework, which has its inspiration in the mechanics of human navigation, for solving the problem of Simultaneous Localization and Mapping (SLAM). The proposed framework has specific relevance to vision based SLAM, in particular, small baseline stereo vision based SLAM and addresses several key issues relevant to the particular sensor domain. Firstly, as observed in the authors' earlier work, the particular sensing device has a highly nonlinear observation model resulting in inconsistent state estimations when standard recursive estimators such as the Extended Kalman Filter (EKF) or the Unscented variants are used. Secondly, vision based approaches tend to have issues related to large feature density, narrow field of view and the potential requirement of maintaining large databases for vision based data association techniques. The proposed Multi Map SLAM solution addresses the filter inconsistency issue by formulating the SLAM problem as a nonlinear batch optimization. Feature management is addressed through a two tier map representation. The two maps have unique attributes assigned to them. The Global Map (GM) is a compact global representation of the robots environment and the Local Map (LM) is exclusively used for low-level navigation between local points in the robot's navigation horizon.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Robotics and Automation, ICRA 2008
PublisherIEEE
Pages1892-1897
Number of pages6
ISBN (Print)9781424416479
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 IEEE International Conference on Robotics and Automation, ICRA 2008 - Pasadena, CA, United States
Duration: 19 May 200823 May 2008

Conference

Conference2008 IEEE International Conference on Robotics and Automation, ICRA 2008
CountryUnited States
CityPasadena, CA
Period19/05/0823/05/08

Fingerprint

Navigation
Robots
Stereo vision
Extended Kalman filters
State estimation
Mechanics
Sensors

Cite this

Herath, D. C., Kodagoda, S., & Dissanayake, G. (2008). New framework for simultaneous localization and mapping: Multi map SLAM. In 2008 IEEE International Conference on Robotics and Automation, ICRA 2008 (pp. 1892-1897). [4543483] IEEE. https://doi.org/10.1109/ROBOT.2008.4543483
Herath, Damith C. ; Kodagoda, S. ; Dissanayake, Gamini. / New framework for simultaneous localization and mapping : Multi map SLAM. 2008 IEEE International Conference on Robotics and Automation, ICRA 2008. IEEE, 2008. pp. 1892-1897
@inproceedings{584d96ea6faa403392d53dec38d4d66f,
title = "New framework for simultaneous localization and mapping: Multi map SLAM",
abstract = "The main contribution of this paper arises from the development of a new framework, which has its inspiration in the mechanics of human navigation, for solving the problem of Simultaneous Localization and Mapping (SLAM). The proposed framework has specific relevance to vision based SLAM, in particular, small baseline stereo vision based SLAM and addresses several key issues relevant to the particular sensor domain. Firstly, as observed in the authors' earlier work, the particular sensing device has a highly nonlinear observation model resulting in inconsistent state estimations when standard recursive estimators such as the Extended Kalman Filter (EKF) or the Unscented variants are used. Secondly, vision based approaches tend to have issues related to large feature density, narrow field of view and the potential requirement of maintaining large databases for vision based data association techniques. The proposed Multi Map SLAM solution addresses the filter inconsistency issue by formulating the SLAM problem as a nonlinear batch optimization. Feature management is addressed through a two tier map representation. The two maps have unique attributes assigned to them. The Global Map (GM) is a compact global representation of the robots environment and the Local Map (LM) is exclusively used for low-level navigation between local points in the robot's navigation horizon.",
author = "Herath, {Damith C.} and S. Kodagoda and Gamini Dissanayake",
year = "2008",
doi = "10.1109/ROBOT.2008.4543483",
language = "English",
isbn = "9781424416479",
pages = "1892--1897",
booktitle = "2008 IEEE International Conference on Robotics and Automation, ICRA 2008",
publisher = "IEEE",

}

Herath, DC, Kodagoda, S & Dissanayake, G 2008, New framework for simultaneous localization and mapping: Multi map SLAM. in 2008 IEEE International Conference on Robotics and Automation, ICRA 2008., 4543483, IEEE, pp. 1892-1897, 2008 IEEE International Conference on Robotics and Automation, ICRA 2008, Pasadena, CA, United States, 19/05/08. https://doi.org/10.1109/ROBOT.2008.4543483

New framework for simultaneous localization and mapping : Multi map SLAM. / Herath, Damith C.; Kodagoda, S.; Dissanayake, Gamini.

2008 IEEE International Conference on Robotics and Automation, ICRA 2008. IEEE, 2008. p. 1892-1897 4543483.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - New framework for simultaneous localization and mapping

T2 - Multi map SLAM

AU - Herath, Damith C.

AU - Kodagoda, S.

AU - Dissanayake, Gamini

PY - 2008

Y1 - 2008

N2 - The main contribution of this paper arises from the development of a new framework, which has its inspiration in the mechanics of human navigation, for solving the problem of Simultaneous Localization and Mapping (SLAM). The proposed framework has specific relevance to vision based SLAM, in particular, small baseline stereo vision based SLAM and addresses several key issues relevant to the particular sensor domain. Firstly, as observed in the authors' earlier work, the particular sensing device has a highly nonlinear observation model resulting in inconsistent state estimations when standard recursive estimators such as the Extended Kalman Filter (EKF) or the Unscented variants are used. Secondly, vision based approaches tend to have issues related to large feature density, narrow field of view and the potential requirement of maintaining large databases for vision based data association techniques. The proposed Multi Map SLAM solution addresses the filter inconsistency issue by formulating the SLAM problem as a nonlinear batch optimization. Feature management is addressed through a two tier map representation. The two maps have unique attributes assigned to them. The Global Map (GM) is a compact global representation of the robots environment and the Local Map (LM) is exclusively used for low-level navigation between local points in the robot's navigation horizon.

AB - The main contribution of this paper arises from the development of a new framework, which has its inspiration in the mechanics of human navigation, for solving the problem of Simultaneous Localization and Mapping (SLAM). The proposed framework has specific relevance to vision based SLAM, in particular, small baseline stereo vision based SLAM and addresses several key issues relevant to the particular sensor domain. Firstly, as observed in the authors' earlier work, the particular sensing device has a highly nonlinear observation model resulting in inconsistent state estimations when standard recursive estimators such as the Extended Kalman Filter (EKF) or the Unscented variants are used. Secondly, vision based approaches tend to have issues related to large feature density, narrow field of view and the potential requirement of maintaining large databases for vision based data association techniques. The proposed Multi Map SLAM solution addresses the filter inconsistency issue by formulating the SLAM problem as a nonlinear batch optimization. Feature management is addressed through a two tier map representation. The two maps have unique attributes assigned to them. The Global Map (GM) is a compact global representation of the robots environment and the Local Map (LM) is exclusively used for low-level navigation between local points in the robot's navigation horizon.

UR - http://www.scopus.com/inward/record.url?scp=51649113485&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.2008.4543483

DO - 10.1109/ROBOT.2008.4543483

M3 - Conference contribution

SN - 9781424416479

SP - 1892

EP - 1897

BT - 2008 IEEE International Conference on Robotics and Automation, ICRA 2008

PB - IEEE

ER -

Herath DC, Kodagoda S, Dissanayake G. New framework for simultaneous localization and mapping: Multi map SLAM. In 2008 IEEE International Conference on Robotics and Automation, ICRA 2008. IEEE. 2008. p. 1892-1897. 4543483 https://doi.org/10.1109/ROBOT.2008.4543483