Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/13038
Title: Sensor Based Localization of a Mobile Robot
Authors: LEE GIM HEE
Keywords: Localization, Kidnapped Problem, SLAM, Scan Matching, Particle Filter, Loop Closure Problem
Issue Date: 2-Jan-2008
Source: LEE GIM HEE (2008-01-02). Sensor Based Localization of a Mobile Robot. ScholarBank@NUS Repository.
Abstract: Localization is the process of determining the pose of a mobile robot with respect to a given map of the environment (known environment). The localization problem can be made more difficult in cases where the map of the environment is not given (unknown environment) to the robot. This is the simultaneous localization and mapping (SLAM) problem where the robot has to simultaneously build a map of its environment and localizes itself with respect to this map. Some of the sensors that are commonly used for mobile robot localization are evaluated in this thesis. The odometer and laser range finder are found to be the most suitable sensors for implementing the localization algorithms. A probabilistic algorithm - The Particle Filter has been chosen over other algorithms for localization of a mobile robot in a known environment due to its robustness, effectiveness and ease of implementation.The most significant contribution of this thesis is a novel solution for the SLAM problem. This novel SLAM algorithm uses a laser scan matching algorithm to align consecutive laser scans, loop closure detection algorithm to detect loop closure opportunity, and loop closure algorithm to close any detected loops in the map.
URI: http://scholarbank.nus.edu.sg/handle/10635/13038
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
GimHee_MEng_Thesis.pdf2.12 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

293
checked on Dec 18, 2017

Download(s)

285
checked on Dec 18, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.