• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.55.2018.tde-19012018-164030
Document
Author
Full name
Denis Fernando Wolf
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2001
Supervisor
Committee
Marques, Eduardo (President)
Costa, Anna Helena Reali
Romero, Roseli Aparecida Francelin
Title in Portuguese
Projeto de uma rede neural usada no reconhecimento de gestos por robôs móveis utilizando-se computação reconfigurável
Keywords in Portuguese
Não disponível
Abstract in Portuguese
A Robótica é uma área de pesquisa que tem evoluído muito nas décadas, e tem recebido grande atenção pela comunidade científica. As principais limitações dos sistemas robóticos atuais estão no controle dessas máquinas complexas. É importante que sejam desenvolvidos algoritmos inteligentes e suficiente para controlar os robôs de maneira apropriada, e que esses algoritmos sejam executados de maneira eficiente. A utilizaçõa de hardware para a execução desses algoritmos é uma alternativa interessante para se conseguir um bom desempenho. Essa dissertação apresenta a implementação de neural artificial, utilizada no reconhecimento de gestos por robôs móveis. Para tanto, é utilizada a tecnologia FPGA, que pérmite o desenvolvimento de hardware com rapidez, eficiência e baixo custo. Após o desenvolvimento, são apresentadas comparações de desempenho e conclusões sobre as implementações.
Title in English
Not available
Keywords in English
Not available
Abstract in English
Robotics is a resarch area that has been growing in the last decades, and it has been receiving much attention by the scientific academy. The main limitations of the current robotics systems remain the control to those complex nmchines. li is important to develop algorithms inteligent enough to handle the robots in an appropriate way, and these algorithms must be executed in an efficient way too. The utilization of hardware implementation is an interesting manner to acquire good performance in the algorithms execution. This work presets a hardware model of an artificial neural network used in the gesture recognizing by iobi1e robots. Thus, FPGA technology has been used. It allows quickiiess, efficiency, and low prices. After the hardware development, some performance comparisons and conclusions about the implementation are shown.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
DenisFernandoWolf.pdf (1.69 Mbytes)
Publishing Date
2018-01-22
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.