A SLAM Method Based On Memory Database of the Features

被引：0

作者：

Liu Jie ^{[1
]}

He Zhendong

Chen Lumin ^{[1
]}

机构：

[1] Zhengzhou Univ Light Ind, Coll Mech & Elect Engn, Zhengzhou 45000, Peoples R China

来源：

PROCEEDINGS OF THE 27TH CHINESE CONTROL CONFERENCE, VOL 5 | 2008年

关键词：

Robot localization; Laser range scanner; Scan matching; Geometric features in environment; Memory database of the features;

D O I：

10.1109/CHICC.2008.4605344

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

a method for simultaneous localization and map based on scan mathcing is presented according to memory database of the features. the steady geometric features are extracted as the natural landmarks according to advanced least square fitting, and the memory database of the features is created and updated for scan matching better, Therefore, it is also valid to dynamic environment. Meanwhile, the belief is imported to reduce the result errors caused by the uncertainty of the sensors. the experiments on mobile robot proved the validity and accuracy.

引用

页码：355 / 360

页数：6

共 6 条

[1] ALTERMATT M, 2004, P 2004 IEEE RSJ INT, P1053
[2] HOWARD A, 2001, LOCALIZATION MOBILE
[3] Simultaneous localization and mapping with unknown data association using FastSLAM
Montemerlo, M
Thrun, S
[J]. 2003 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-3, PROCEEDINGS, 2003, : 1985 - 1991
[4] Sohn HJ, 2005, IEEE INT CONF ROBOT, P3545
[5] Wang CC, 2002, 2002 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS, P2918, DOI 10.1109/ROBOT.2002.1013675
[6] Xu ZZ, 2003, 2003 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS, INTELLIGENT SYSTEMS AND SIGNAL PROCESSING, VOLS 1 AND 2, PROCEEDINGS, P99

← 1 →