An efficient ceiling-view SLAM using relational constraints between landmarks

Hyukdoo Choi, Ryunseok Kim, Euntai Kim

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In this paper, we present a new indoor 'simultaneous localization and mapping' (SLAM) technique based on an upward-looking ceiling camera. Adapted from our previous work [17], the proposed method employs sparsely-distributed line and point landmarks in an indoor environment to aid with data association and reduce extended Kalman filter computation as compared with earlier techniques. Further, the proposed method exploits geometric relationships between the two types of landmarks to provide added information about the environment. This geometric information is measured with an upward-looking ceiling camera and is used as a constraint in Kalman filtering. The performance of the proposed ceiling-view (CV) SLAM is demonstrated through simulations and experiments. The proposed method performs localization and mapping more accurately than those methods that use the two types of landmarks without taking into account their relative geometries.

Original languageEnglish
Article number4
JournalInternational Journal of Advanced Robotic Systems
Volume11
Issue number1
DOIs
Publication statusPublished - 2014 Jan 28

Fingerprint

Ceilings
Cameras
Extended Kalman filters
Geometry
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{a4d198e6d8244270a75229f504bfc987,
title = "An efficient ceiling-view SLAM using relational constraints between landmarks",
abstract = "In this paper, we present a new indoor 'simultaneous localization and mapping' (SLAM) technique based on an upward-looking ceiling camera. Adapted from our previous work [17], the proposed method employs sparsely-distributed line and point landmarks in an indoor environment to aid with data association and reduce extended Kalman filter computation as compared with earlier techniques. Further, the proposed method exploits geometric relationships between the two types of landmarks to provide added information about the environment. This geometric information is measured with an upward-looking ceiling camera and is used as a constraint in Kalman filtering. The performance of the proposed ceiling-view (CV) SLAM is demonstrated through simulations and experiments. The proposed method performs localization and mapping more accurately than those methods that use the two types of landmarks without taking into account their relative geometries.",
author = "Hyukdoo Choi and Ryunseok Kim and Euntai Kim",
year = "2014",
month = "1",
day = "28",
doi = "10.5772/57225",
language = "English",
volume = "11",
journal = "International Journal of Advanced Robotic Systems",
issn = "1729-8806",
publisher = "Vienna University of Technology",
number = "1",

}

An efficient ceiling-view SLAM using relational constraints between landmarks. / Choi, Hyukdoo; Kim, Ryunseok; Kim, Euntai.

In: International Journal of Advanced Robotic Systems, Vol. 11, No. 1, 4, 28.01.2014.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An efficient ceiling-view SLAM using relational constraints between landmarks

AU - Choi, Hyukdoo

AU - Kim, Ryunseok

AU - Kim, Euntai

PY - 2014/1/28

Y1 - 2014/1/28

N2 - In this paper, we present a new indoor 'simultaneous localization and mapping' (SLAM) technique based on an upward-looking ceiling camera. Adapted from our previous work [17], the proposed method employs sparsely-distributed line and point landmarks in an indoor environment to aid with data association and reduce extended Kalman filter computation as compared with earlier techniques. Further, the proposed method exploits geometric relationships between the two types of landmarks to provide added information about the environment. This geometric information is measured with an upward-looking ceiling camera and is used as a constraint in Kalman filtering. The performance of the proposed ceiling-view (CV) SLAM is demonstrated through simulations and experiments. The proposed method performs localization and mapping more accurately than those methods that use the two types of landmarks without taking into account their relative geometries.

AB - In this paper, we present a new indoor 'simultaneous localization and mapping' (SLAM) technique based on an upward-looking ceiling camera. Adapted from our previous work [17], the proposed method employs sparsely-distributed line and point landmarks in an indoor environment to aid with data association and reduce extended Kalman filter computation as compared with earlier techniques. Further, the proposed method exploits geometric relationships between the two types of landmarks to provide added information about the environment. This geometric information is measured with an upward-looking ceiling camera and is used as a constraint in Kalman filtering. The performance of the proposed ceiling-view (CV) SLAM is demonstrated through simulations and experiments. The proposed method performs localization and mapping more accurately than those methods that use the two types of landmarks without taking into account their relative geometries.

UR - http://www.scopus.com/inward/record.url?scp=84894490917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894490917&partnerID=8YFLogxK

U2 - 10.5772/57225

DO - 10.5772/57225

M3 - Article

AN - SCOPUS:84894490917

VL - 11

JO - International Journal of Advanced Robotic Systems

JF - International Journal of Advanced Robotic Systems

SN - 1729-8806

IS - 1

M1 - 4

ER -