A new cvSLAM exploiting a partially known landmark association

Dong Yeop Kim; Hyukdoo Choi; Heesung Lee; Euntai Kim

doi:10.1080/01691864.2013.805470

A new cvSLAM exploiting a partially known landmark association

Dong Yeop Kim, Hyukdoo Choi, Heesung Lee, Euntai Kim

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

There are some situations in which the landmarks used in simultaneous localization and mapping (SLAM) have their own classes and for ceiling view (CV)-based navigation, this is usually the case. Ceilings in the home or the office have circular landmarks, such as lamps, speakers, fire alarms, smoke alarms, and so on, but to our knowledge, their classes have not been fully exploited in the data association of SLAM. In this paper, a new SLAM method that exploits the class of the landmarks is proposed and is applied to ceiling view-based SLAM (cvSLAM). The fact that the landmark classification cannot always be correct is also taken into account in the new SLAM and is formulated in the FastSLAM framework. Finally, simulations and experiments are conducted and the validity of the proposed method is demonstrated.

Original language	English
Pages (from-to)	1073-1086
Number of pages	14
Journal	Advanced Robotics
Volume	27
Issue number	14
DOIs	https://doi.org/10.1080/01691864.2013.805470
Publication status	Published - 2013 Oct 1

Bibliographical note

Funding Information:
This work was supported by the ‘Cognitive model-based global localization for indoor robots’ project (number: 10031687) of the Ministry of Knowledge Economy, Republic of Korea.

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Software
Human-Computer Interaction
Hardware and Architecture
Computer Science Applications

Access to Document

10.1080/01691864.2013.805470

Cite this

@article{03140c2c572a473d9435f92e767f3108,

title = "A new cvSLAM exploiting a partially known landmark association",

abstract = "There are some situations in which the landmarks used in simultaneous localization and mapping (SLAM) have their own classes and for ceiling view (CV)-based navigation, this is usually the case. Ceilings in the home or the office have circular landmarks, such as lamps, speakers, fire alarms, smoke alarms, and so on, but to our knowledge, their classes have not been fully exploited in the data association of SLAM. In this paper, a new SLAM method that exploits the class of the landmarks is proposed and is applied to ceiling view-based SLAM (cvSLAM). The fact that the landmark classification cannot always be correct is also taken into account in the new SLAM and is formulated in the FastSLAM framework. Finally, simulations and experiments are conducted and the validity of the proposed method is demonstrated.",

author = "Kim, {Dong Yeop} and Hyukdoo Choi and Heesung Lee and Euntai Kim",

note = "Funding Information: This work was supported by the {\textquoteleft}Cognitive model-based global localization for indoor robots{\textquoteright} project (number: 10031687) of the Ministry of Knowledge Economy, Republic of Korea.",

year = "2013",

month = oct,

day = "1",

doi = "10.1080/01691864.2013.805470",

language = "English",

volume = "27",

pages = "1073--1086",

journal = "Advanced Robotics",

issn = "0169-1864",

publisher = "Taylor & Francis",

number = "14",

}

TY - JOUR

T1 - A new cvSLAM exploiting a partially known landmark association

AU - Kim, Dong Yeop

AU - Choi, Hyukdoo

AU - Lee, Heesung

AU - Kim, Euntai

N1 - Funding Information: This work was supported by the ‘Cognitive model-based global localization for indoor robots’ project (number: 10031687) of the Ministry of Knowledge Economy, Republic of Korea.

PY - 2013/10/1

Y1 - 2013/10/1

N2 - There are some situations in which the landmarks used in simultaneous localization and mapping (SLAM) have their own classes and for ceiling view (CV)-based navigation, this is usually the case. Ceilings in the home or the office have circular landmarks, such as lamps, speakers, fire alarms, smoke alarms, and so on, but to our knowledge, their classes have not been fully exploited in the data association of SLAM. In this paper, a new SLAM method that exploits the class of the landmarks is proposed and is applied to ceiling view-based SLAM (cvSLAM). The fact that the landmark classification cannot always be correct is also taken into account in the new SLAM and is formulated in the FastSLAM framework. Finally, simulations and experiments are conducted and the validity of the proposed method is demonstrated.

AB - There are some situations in which the landmarks used in simultaneous localization and mapping (SLAM) have their own classes and for ceiling view (CV)-based navigation, this is usually the case. Ceilings in the home or the office have circular landmarks, such as lamps, speakers, fire alarms, smoke alarms, and so on, but to our knowledge, their classes have not been fully exploited in the data association of SLAM. In this paper, a new SLAM method that exploits the class of the landmarks is proposed and is applied to ceiling view-based SLAM (cvSLAM). The fact that the landmark classification cannot always be correct is also taken into account in the new SLAM and is formulated in the FastSLAM framework. Finally, simulations and experiments are conducted and the validity of the proposed method is demonstrated.

UR - http://www.scopus.com/inward/record.url?scp=84882455021&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882455021&partnerID=8YFLogxK

U2 - 10.1080/01691864.2013.805470

DO - 10.1080/01691864.2013.805470

M3 - Article

AN - SCOPUS:84882455021

SN - 0169-1864

VL - 27

SP - 1073

EP - 1086

JO - Advanced Robotics

JF - Advanced Robotics

IS - 14

ER -

A new cvSLAM exploiting a partially known landmark association

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this