Scan-matching based 6dof slam using omnidirectional stereo

Hiroshi Koyasu; Hitoshi Maekawa; Hiroshi Kawasaki; Shintaro Ono; Katsushi Ikeuchi

Scan-matching based 6dof slam using omnidirectional stereo

Hiroshi Koyasu, Hitoshi Maekawa, Hiroshi Kawasaki, Shintaro Ono, Katsushi Ikeuchi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Simultaneous localization and mapping (SLAM) of working environments is one of the important problems in mobile robotics. For the problem, we present a new method using an omnidirectional stereo system. By using 3D range information obtained from the omnidirectional stereo, we construct scan-matching based extended Kalman filter SLAM(EKF-SLAM) system. In the system, the output of the piecewise iterative closest point(ICP) algorithm is used as the observation of the EKF. The global consistency of the robot trajectory is kept by a loop closing method based on the Kalman smoothing. Experimental results of the method are shown for a simulated environment.

Original language	English
Title of host publication	Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013
Publisher	MVA Organization
Pages	306-310
Number of pages	5
ISBN (Print)	9784901122139
Publication status	Published - 2013
Externally published	Yes
Event	13th IAPR International Conference on Machine Vision Applications, MVA 2013 - Kyoto, Japan Duration: May 20 2013 → May 23 2013

Publication series

Name	Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013

Conference

Conference	13th IAPR International Conference on Machine Vision Applications, MVA 2013
Country	Japan
City	Kyoto
Period	5/20/13 → 5/23/13

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Computer Science Applications

Fingerprint Dive into the research topics of 'Scan-matching based 6dof slam using omnidirectional stereo'. Together they form a unique fingerprint.

Cite this

Scan-matching based 6dof slam using omnidirectional stereo. / Koyasu, Hiroshi; Maekawa, Hitoshi; Kawasaki, Hiroshi; Ono, Shintaro; Ikeuchi, Katsushi.

Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013. MVA Organization, 2013. p. 306-310 (Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Koyasu, H, Maekawa, H, Kawasaki, H, Ono, S & Ikeuchi, K 2013, Scan-matching based 6dof slam using omnidirectional stereo. in Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013. Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013, MVA Organization, pp. 306-310, 13th IAPR International Conference on Machine Vision Applications, MVA 2013, Kyoto, Japan, 5/20/13.

Koyasu, Hiroshi ; Maekawa, Hitoshi ; Kawasaki, Hiroshi ; Ono, Shintaro ; Ikeuchi, Katsushi. / Scan-matching based 6dof slam using omnidirectional stereo. Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013. MVA Organization, 2013. pp. 306-310 (Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013).

@inproceedings{3022343faa19456986a38a5663c6b756,

title = "Scan-matching based 6dof slam using omnidirectional stereo",

abstract = "Simultaneous localization and mapping (SLAM) of working environments is one of the important problems in mobile robotics. For the problem, we present a new method using an omnidirectional stereo system. By using 3D range information obtained from the omnidirectional stereo, we construct scan-matching based extended Kalman filter SLAM(EKF-SLAM) system. In the system, the output of the piecewise iterative closest point(ICP) algorithm is used as the observation of the EKF. The global consistency of the robot trajectory is kept by a loop closing method based on the Kalman smoothing. Experimental results of the method are shown for a simulated environment.",

author = "Hiroshi Koyasu and Hitoshi Maekawa and Hiroshi Kawasaki and Shintaro Ono and Katsushi Ikeuchi",

note = "Funding Information: This work was partly supported by JSPS KAKENHI Grant Number 23611006.; 13th IAPR International Conference on Machine Vision Applications, MVA 2013 ; Conference date: 20-05-2013 Through 23-05-2013",

year = "2013",

language = "English",

isbn = "9784901122139",

series = "Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013",

publisher = "MVA Organization",

pages = "306--310",

booktitle = "Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013",

}

TY - GEN

T1 - Scan-matching based 6dof slam using omnidirectional stereo

AU - Koyasu, Hiroshi

AU - Maekawa, Hitoshi

AU - Kawasaki, Hiroshi

AU - Ono, Shintaro

AU - Ikeuchi, Katsushi

N1 - Funding Information: This work was partly supported by JSPS KAKENHI Grant Number 23611006.

PY - 2013

Y1 - 2013

N2 - Simultaneous localization and mapping (SLAM) of working environments is one of the important problems in mobile robotics. For the problem, we present a new method using an omnidirectional stereo system. By using 3D range information obtained from the omnidirectional stereo, we construct scan-matching based extended Kalman filter SLAM(EKF-SLAM) system. In the system, the output of the piecewise iterative closest point(ICP) algorithm is used as the observation of the EKF. The global consistency of the robot trajectory is kept by a loop closing method based on the Kalman smoothing. Experimental results of the method are shown for a simulated environment.

AB - Simultaneous localization and mapping (SLAM) of working environments is one of the important problems in mobile robotics. For the problem, we present a new method using an omnidirectional stereo system. By using 3D range information obtained from the omnidirectional stereo, we construct scan-matching based extended Kalman filter SLAM(EKF-SLAM) system. In the system, the output of the piecewise iterative closest point(ICP) algorithm is used as the observation of the EKF. The global consistency of the robot trajectory is kept by a loop closing method based on the Kalman smoothing. Experimental results of the method are shown for a simulated environment.

UR - http://www.scopus.com/inward/record.url?scp=85083075955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85083075955&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85083075955

SN - 9784901122139

T3 - Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013

SP - 306

EP - 310

BT - Proceedings of the 13th IAPR International Conference on Machine Vision Applications, MVA 2013

PB - MVA Organization

T2 - 13th IAPR International Conference on Machine Vision Applications, MVA 2013

Y2 - 20 May 2013 through 23 May 2013

ER -