大規模な三次元環境地図とRGB-Dカメラを用いた移動ロボットの広域位置同定

Translated title of the contribution: Global Localization for Mobile Robot using Large-scale 3D Environmental Map and RGB-D Camera

鄭 龍振, 倉爪 亮, 岩下 友美, 長谷川 勉

Research output: Contribution to journalArticle

Abstract

We proposed a global positioning technique in 3D environment using 3D geometrical map and a RGB-D camera based on a ND (Normal Distributions) voxel matching. Firstly, a 3D geometrical map represented by point-cloud is converted to ND voxels, and eigen ellipses are extracted. Meanwhile, ND voxels are also created from a range image captured by a RGB-D camera, and eigen ellipses and seven representative points are calculated in each ND voxel. For global localization, point-plane and plane-plane correspondences are tested and an optimum global position is determined using a particle filter. Experimental results show that the proposed technique is robust for the similarity in a 3D map and converges more stably than a standard maximum likelihood method using a beam model.
Original languageJapanese
Pages (from-to)896-906
Number of pages11
Journal日本ロボット学会誌
Volume31
Issue number9
DOIs
Publication statusPublished - 2013

Fingerprint

Normal distribution
Mobile robots
Cameras
Maximum likelihood

Cite this

大規模な三次元環境地図とRGB-Dカメラを用いた移動ロボットの広域位置同定. / 鄭龍振; 倉爪亮; 岩下友美; 長谷川勉.

In: 日本ロボット学会誌, Vol. 31, No. 9, 2013, p. 896-906.

Research output: Contribution to journalArticle

@article{00dbeb0303634338b380b09565dcb84f,
title = "大規模な三次元環境地図とRGB-Dカメラを用いた移動ロボットの広域位置同定",
abstract = "We proposed a global positioning technique in 3D environment using 3D geometrical map and a RGB-D camera based on a ND (Normal Distributions) voxel matching. Firstly, a 3D geometrical map represented by point-cloud is converted to ND voxels, and eigen ellipses are extracted. Meanwhile, ND voxels are also created from a range image captured by a RGB-D camera, and eigen ellipses and seven representative points are calculated in each ND voxel. For global localization, point-plane and plane-plane correspondences are tested and an optimum global position is determined using a particle filter. Experimental results show that the proposed technique is robust for the similarity in a 3D map and converges more stably than a standard maximum likelihood method using a beam model.",
author = "龍振 鄭 and 亮 倉爪 and 友美 岩下 and 勉 長谷川",
year = "2013",
doi = "10.7210/jrsj.31.896",
language = "Japanese",
volume = "31",
pages = "896--906",
journal = "日本ロボット学会誌",
issn = "0289-1824",
publisher = "一般社団法人 日本ロボット学会",
number = "9",

}

TY - JOUR

T1 - 大規模な三次元環境地図とRGB-Dカメラを用いた移動ロボットの広域位置同定

AU - 鄭, 龍振

AU - 倉爪, 亮

AU - 岩下, 友美

AU - 長谷川, 勉

PY - 2013

Y1 - 2013

N2 - We proposed a global positioning technique in 3D environment using 3D geometrical map and a RGB-D camera based on a ND (Normal Distributions) voxel matching. Firstly, a 3D geometrical map represented by point-cloud is converted to ND voxels, and eigen ellipses are extracted. Meanwhile, ND voxels are also created from a range image captured by a RGB-D camera, and eigen ellipses and seven representative points are calculated in each ND voxel. For global localization, point-plane and plane-plane correspondences are tested and an optimum global position is determined using a particle filter. Experimental results show that the proposed technique is robust for the similarity in a 3D map and converges more stably than a standard maximum likelihood method using a beam model.

AB - We proposed a global positioning technique in 3D environment using 3D geometrical map and a RGB-D camera based on a ND (Normal Distributions) voxel matching. Firstly, a 3D geometrical map represented by point-cloud is converted to ND voxels, and eigen ellipses are extracted. Meanwhile, ND voxels are also created from a range image captured by a RGB-D camera, and eigen ellipses and seven representative points are calculated in each ND voxel. For global localization, point-plane and plane-plane correspondences are tested and an optimum global position is determined using a particle filter. Experimental results show that the proposed technique is robust for the similarity in a 3D map and converges more stably than a standard maximum likelihood method using a beam model.

U2 - 10.7210/jrsj.31.896

DO - 10.7210/jrsj.31.896

M3 - 記事

VL - 31

SP - 896

EP - 906

JO - 日本ロボット学会誌

JF - 日本ロボット学会誌

SN - 0289-1824

IS - 9

ER -