<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>32</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Daniel Pizarro</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">Manuel Mazo</style></author><author><style face="normal" font="default" size="100%">Enrique Santiso</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">Localización de robots móviles en espacios inteligentes utilizando cámaras externas y marcas naturales</style></title><secondary-title><style face="normal" font="default" size="100%">Electronics</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2009</style></year><pub-dates><date><style  face="normal" font="default" size="100%">01/2009</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://dspace.uah.es/dspace/bitstream/10017/2671/1/tesis.pdf</style></url></web-urls><related-urls><url><style face="normal" font="default" size="100%">https://geintra-uah.org/en/system/files/tesisDanielPizarro.pdf</style></url></related-urls></urls><publisher><style face="normal" font="default" size="100%">Universidad de Alcala</style></publisher><pub-location><style face="normal" font="default" size="100%">Alcala de Henares (Madrid)</style></pub-location><volume><style face="normal" font="default" size="100%">PhD.</style></volume><pages><style face="normal" font="default" size="100%">250</style></pages><language><style face="normal" font="default" size="100%">Spanish</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;This thesis deals with the problem of mobile robot localization using static cameras&lt;br /&gt;
placed in the environment. The presented approach is based in the idea of &amp;ldquo;Intelligent&lt;br /&gt;
Space&amp;rdquo;, where a distributed intelligence controls cameras and robots to serve in a certain&lt;br /&gt;
task. The previous works that shares the same approach are focused on placing artificial&lt;br /&gt;
landmarks on the robots. This thesis focuses on approaches that do not need previous&lt;br /&gt;
knowledge about the robot and make use of the natural appearance of the robot.&lt;br /&gt;
The localization process proposed in this thesis is based on natural landmarks, which&lt;br /&gt;
are detected in the image plane of the set of cameras and correspond to a 3D model of the&lt;br /&gt;
robot.&lt;br /&gt;
The proposed localization system is divided in two steps. Firstly, a initialization step&lt;br /&gt;
obtains the 3D model of the robot and its initial pose. Secondly, using a sequential approach,&lt;br /&gt;
the pose of the robot is obtained at each time instant.&lt;br /&gt;
The initialization step is solved in this thesis for any number of cameras using a&lt;br /&gt;
structure-from-motion approach, where odometry serves as a metric reference in the single&lt;br /&gt;
camera case. Besides, the proposed approach avoids using natural landmark corresponden-&lt;br /&gt;
ces between multiple cameras, which allows to initialize the 3D model for non-overlapping&lt;br /&gt;
views.&lt;br /&gt;
The sequential step proposed in this thesis uses the 3D model, obtained in the afore-&lt;br /&gt;
mentioned initialization step, for retrieving robot&amp;rsquo;s pose in a estimation-correction scheme.&lt;br /&gt;
This step includes robust techniques that remove outliers from the measurements.&lt;br /&gt;
In addition to the filtering approach, a non-iterative and of low complexity solution to&lt;br /&gt;
the mPnP (multiple perspective n point) problem is proposed.&lt;br /&gt;
The probabilistic approach performs coherent data fusion between all information avai-&lt;br /&gt;
lable and it allows to estimate uncertainty in the obtained robot&amp;rsquo;s pose.&lt;br /&gt;
The solution presented in this thesis has been experimentally assessed using synthetic&lt;br /&gt;
generated data and experiments from a real environment with cameras, robots and obs-&lt;br /&gt;
tacles. The resulting method is proved to be stable against occlusions and illumination&lt;br /&gt;
changes, which makes it suitable to real situations.&lt;/p&gt;</style></abstract><work-type><style face="normal" font="default" size="100%">PhD.</style></work-type><custom1><style face="normal" font="default" size="100%">&lt;p&gt;PhD. in Telecommunication Engineering&lt;/p&gt;</style></custom1></record></records></xml>