Bearing-only landmark initialization with unknown data association

被引：18

作者：

Costa, A ^{[1
]}

Kantor, G ^{[1
]}

Choset, H ^{[1
]}

机构：

[1] Carnegie Mellon Univ, Dept Mech Engn, Pittsburgh, PA 15213 USA

来源：

2004 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1- 5, PROCEEDINGS | 2004年

关键词：

D O I：

10.1109/ROBOT.2004.1308079

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

It is essential in many applications that mobile robots localize themselves with respect to an unknown environment. This means that the robot must build a map of its environment and then localize using the map. This process is called simultaneous localization and mapping (SLAM). This paper presents an iterative solution to the landmark initialization problem inherent in a bearing-only implementation of SLAM. No prior knowledge of the environment is required, and furthermore, there are no requirements about having the data association problem solved. Once landmarks are initialized, they are inserted into an extended Kalman Filter (EKF) to solve the SLAM problem. Both indoor and outdoor experiments are presented to validate the method.

引用

页码：1764 / 1770

页数：7

共 16 条

[1]

Bailey T., 2003, P 2003 IEEE INT C RO

[2]

Bhattacharyya A., 1943, B CALCUTTA MATH SOC, V35, P99, DOI DOI 10.1038/157869B0

[3]

DEANS MC, 2002, THESIS CARNEGIE MELL

[4]

DELLAERT F, 2002, P IEEE INT C ROB AUT

[5]

DELLAERT F, 2000, P IEEE COMP SOC C CO

[6] A solution to the simultaneous localization and map building (SLAM) problem [J].

Dissanayake, MWMG ;

Newman, P ;

Clark, S ;

Durrant-Whyte, HF ;

Csorba, M .

IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, 2001, 17 (03) :229-241

[7]

FITZGIBBONS T, 2002, P AUSTR C ROB AUT AU

[8]

FOX D, 2000, SEQUENTIAL MONTE CAR

[9]

JULIER S, 1997, INT SAER DEF SENS SI

[10]

Leonard J. J., 1991, Proceedings IROS '91. IEEE/RSJ International Workshop on Intelligent Robots and Systems '91. Intelligence for Mechanical Systems (Cat. No.91TH0375-6), P1442, DOI 10.1109/IROS.1991.174711

← 1 2 →