東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Autonomous robot navigation based on...

Monjazeb, Amirhossein.

Linked to FindBook

Google Book

Amazon

博客來

Autonomous robot navigation based on Simultaneous Localization and Mapping (SLAM), and particle filtering.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Autonomous robot navigation based on Simultaneous Localization and Mapping (SLAM), and particle filtering./
Author:	Monjazeb, Amirhossein.
Description:	201 p.
Notes:	Source: Masters Abstracts International, Volume: 46-05, page: 2836.
Contained By:	Masters Abstracts International46-05.
Subject:	Engineering, Mechanical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR36829
ISBN:	9780494368299

Autonomous robot navigation based on Simultaneous Localization and Mapping (SLAM), and particle filtering.
Monjazeb, Amirhossein.

Autonomous robot navigation based on Simultaneous Localization and Mapping (SLAM), and particle filtering. - 201 p.

Source: Masters Abstracts International, Volume: 46-05, page: 2836.

Thesis (M.A.Sc.)--Carleton University (Canada), 2008.

This thesis provides a brief introduction to Simultaneous Localization and Mapping (SLAM) in extensive outdoor environments, a process that recently has made mobile robots truly autonomous. SLAM is a process in which localization and mapping are done simultaneously in an unknown environment without an access to a priori map. To solve the SLAM problem, sensor information and mathematical motion models are extensively used. This research introduces a probabilistic approach to a SLAM problem and under Gaussian and non-Gaussian conditions offers alternative solutions. Due to the non-linearity of the real systems, which are always subject to noise, an Extended Kalman Filter algorithm for the SLAM problem under Gaussian condition will be shown. Then an alternative way of dealing with SLAM problem with assumption of non-Gaussian and called FAST-SLAM will be analyzed. FAST-SLAM is an algorithm that using Rao-Blackwellised method for particle filtering, estimates the path of robot while the landmarks positions which are mutually independent and with no correlation, can be estimated by EKF. This process is doable using a factorization that fits very well in SLAM problem since there will be a representation of SLAM through out a Bayesian network. A solution to SLAM problem can be worthy if a proper representation of motion and sensor of a robot is accessible. In this thesis, a real outdoor autonomous robot is presented and the related equations are derived. Then simulated examples based on both filters are represented and results are discussed and compared.

ISBN: 9780494368299Subjects--Topical Terms:

783786
Engineering, Mechanical.

Autonomous robot navigation based on Simultaneous Localization and Mapping (SLAM), and particle filtering.
LDR:02384nam 2200253 a 45 001 940787
005 20110518
008 110518s2008 ||||||||||||||||| ||eng d
020 $a 9780494368299
035 $a (UMI)AAIMR36829
035 $a AAIMR36829
040 $a UMI $c UMI
100 1 $a Monjazeb, Amirhossein. $3 1264916
245 1 0 $a Autonomous robot navigation based on Simultaneous Localization and Mapping (SLAM), and particle filtering.
300 $a 201 p.
500 $a Source: Masters Abstracts International, Volume: 46-05, page: 2836.
502 $a Thesis (M.A.Sc.)--Carleton University (Canada), 2008.
520 $a This thesis provides a brief introduction to Simultaneous Localization and Mapping (SLAM) in extensive outdoor environments, a process that recently has made mobile robots truly autonomous. SLAM is a process in which localization and mapping are done simultaneously in an unknown environment without an access to a priori map. To solve the SLAM problem, sensor information and mathematical motion models are extensively used. This research introduces a probabilistic approach to a SLAM problem and under Gaussian and non-Gaussian conditions offers alternative solutions. Due to the non-linearity of the real systems, which are always subject to noise, an Extended Kalman Filter algorithm for the SLAM problem under Gaussian condition will be shown. Then an alternative way of dealing with SLAM problem with assumption of non-Gaussian and called FAST-SLAM will be analyzed. FAST-SLAM is an algorithm that using Rao-Blackwellised method for particle filtering, estimates the path of robot while the landmarks positions which are mutually independent and with no correlation, can be estimated by EKF. This process is doable using a factorization that fits very well in SLAM problem since there will be a representation of SLAM through out a Bayesian network. A solution to SLAM problem can be worthy if a proper representation of motion and sensor of a robot is accessible. In this thesis, a real outdoor autonomous robot is presented and the related equations are derived. Then simulated examples based on both filters are represented and results are discussed and compared.
590 $a School code: 0040.
650 4 $a Engineering, Mechanical. $3 783786
650 4 $a Engineering, Robotics. $3 1018454
690 $a 0548
690 $a 0771
710 2 $a Carleton University (Canada). $3 1018407
773 0 $t Masters Abstracts International $g 46-05.
790 $a 0040
791 $a M.A.Sc.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR36829