Monocular vision-based localization using ORB-SLAM with LIDAR-Aided mapping in real-world robot challenge

Adi Sujiwo; Tomohito Ando; Eijiro Takeuchi; Yoshiki Ninomiya; Masato Edahiro

doi:10.20965/jrm.2016.p0479

Monocular vision-based localization using ORB-SLAM with LIDAR-Aided mapping in real-world robot challenge

Adi Sujiwo, Tomohito Ando, Eijiro Takeuchi, Yoshiki Ninomiya, Masato Edahiro

Green Computing Systems Research Organization

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

19 Citations (Scopus)

Abstract

For the 2015 Tsukuba Challenge, we realized an implementation of vision-based localization based on ORB-SLAM. Our method combined mapping based on ORB-SLAM and Velodyne LIDAR SLAM, and utilized these maps in a localization process using only a monocular camera. We also apply sensor fusion method of odometer and ORB-SLAM from all maps. The combined method delivered better accuracy than the original ORB-SLAM, which suffered from scale ambiguities and map distance distortion. This paper reports on our experience when using ORB-SLAM for visual localization, and describes the difficulties encountered.

Original language	English
Pages (from-to)	479-490
Number of pages	12
Journal	Journal of Robotics and Mechatronics
Volume	28
Issue number	4
DOIs	https://doi.org/10.20965/jrm.2016.p0479
Publication status	Published - 2016 Aug

Keywords

Autonomous vehicle
Field robotics
Tsukuba Challenge
Visual localization

ASJC Scopus subject areas

Computer Science(all)
Electrical and Electronic Engineering

Access to Document

10.20965/jrm.2016.p0479

Fingerprint Dive into the research topics of 'Monocular vision-based localization using ORB-SLAM with LIDAR-Aided mapping in real-world robot challenge'. Together they form a unique fingerprint.

Cite this

@article{a1b786ae84ea4cf58576fc2b5eb79060,

title = "Monocular vision-based localization using ORB-SLAM with LIDAR-Aided mapping in real-world robot challenge",

abstract = "For the 2015 Tsukuba Challenge, we realized an implementation of vision-based localization based on ORB-SLAM. Our method combined mapping based on ORB-SLAM and Velodyne LIDAR SLAM, and utilized these maps in a localization process using only a monocular camera. We also apply sensor fusion method of odometer and ORB-SLAM from all maps. The combined method delivered better accuracy than the original ORB-SLAM, which suffered from scale ambiguities and map distance distortion. This paper reports on our experience when using ORB-SLAM for visual localization, and describes the difficulties encountered.",

keywords = "Autonomous vehicle, Field robotics, Tsukuba Challenge, Visual localization",

author = "Adi Sujiwo and Tomohito Ando and Eijiro Takeuchi and Yoshiki Ninomiya and Masato Edahiro",

year = "2016",

month = aug,

doi = "10.20965/jrm.2016.p0479",

language = "English",

volume = "28",

pages = "479--490",

journal = "Journal of Robotics and Mechatronics",

issn = "0915-3942",

publisher = "Fuji Technology Press",

number = "4",

}

TY - JOUR

T1 - Monocular vision-based localization using ORB-SLAM with LIDAR-Aided mapping in real-world robot challenge

AU - Sujiwo, Adi

AU - Ando, Tomohito

AU - Takeuchi, Eijiro

AU - Ninomiya, Yoshiki

AU - Edahiro, Masato

PY - 2016/8

Y1 - 2016/8

N2 - For the 2015 Tsukuba Challenge, we realized an implementation of vision-based localization based on ORB-SLAM. Our method combined mapping based on ORB-SLAM and Velodyne LIDAR SLAM, and utilized these maps in a localization process using only a monocular camera. We also apply sensor fusion method of odometer and ORB-SLAM from all maps. The combined method delivered better accuracy than the original ORB-SLAM, which suffered from scale ambiguities and map distance distortion. This paper reports on our experience when using ORB-SLAM for visual localization, and describes the difficulties encountered.

AB - For the 2015 Tsukuba Challenge, we realized an implementation of vision-based localization based on ORB-SLAM. Our method combined mapping based on ORB-SLAM and Velodyne LIDAR SLAM, and utilized these maps in a localization process using only a monocular camera. We also apply sensor fusion method of odometer and ORB-SLAM from all maps. The combined method delivered better accuracy than the original ORB-SLAM, which suffered from scale ambiguities and map distance distortion. This paper reports on our experience when using ORB-SLAM for visual localization, and describes the difficulties encountered.

KW - Autonomous vehicle

KW - Field robotics

KW - Tsukuba Challenge

KW - Visual localization

UR - http://www.scopus.com/inward/record.url?scp=84983542326&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983542326&partnerID=8YFLogxK

U2 - 10.20965/jrm.2016.p0479

DO - 10.20965/jrm.2016.p0479

M3 - Article

AN - SCOPUS:84983542326

VL - 28

SP - 479

EP - 490

JO - Journal of Robotics and Mechatronics

JF - Journal of Robotics and Mechatronics

SN - 0915-3942

IS - 4

ER -