• 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.45.2023.tde-19072023-053510
Document
Author
Full name
Adauton Machado Heringer
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2023
Supervisor
Committee
Silva, Flavio Soares Correa da (President)
Cunha, Claudio Barbieri da
Gorrini, Andrea
Title in English
End-to-end learning for autonomous vehicles: a narrow approach
Keywords in English
Artificial general intelligence
Autonomous vehicles
Convolutional neural networks
End-to-end learning
Narrow autonomy
Sociotechnical imaginary
Abstract in English
Autonomous vehicles are long promised to revolutionize our civilization. Nevertheless, it has consistently failed to meet expectations in the past two decades. Based on the fundamental difference between narrow and general artificial intelligence and equipped with the theoretical approach of sociotechnical imaginaries, we criticize general autonomy: the study of autonomous vehicles as envisaged by its artificially fabricated sociotechnical imaginary utopia. By contrast, we conceptualize narrow autonomy as the study of context-limited autonomous vehicles. Accordingly, we propose a narrow approach: instead of training a vehicle in a context-free environment, we set clear boundaries for the path the vehicle is supposed to drive. Using the latest advancements in end-to-end deep learning, we trained a convolutional neural network to map images and high-level commands straight to vehicle control, such as steering angle, throttle, and brake, in a simulated environment. Although this is a multidisciplinary conceptual work, our results indicate that by delimiting its path we can significantly improve performance and contribute to the advancements of autonomous technology.
Title in Portuguese
Aprendizado end-to-end para veículos autônomos: uma abordagem restrita
Keywords in Portuguese
Aprendizado end-to-end
Autonomia restrita
Imaginário sociotécnico
Inteligência artificial geral
Redes neurais convolucionais
Veículos autônomos
Abstract in Portuguese
Veículos autônomos tem prometido revolucionar nossa civilização. Contudo, nas últimas duas décadas as expectativas tem sido consistentemente frustradas. Baseado na diferença entre inteligência artificial geral e restrita, e equipado com o arcabouço teórico dos imaginários sociotécnicos, criticamos a autonomia geral: o estudo dos veículos autonomos como previsto por seu artificialmente fabricado imaginário sociotécnico utópico. Por outro lado, conceitualizamos autonomia restrita como o estudo de veículos autônomos em contextos limitados. Desta forma, propomos uma abordagem restrita: em vez de treinar um veículo em um contexto ilimitado, delimitamos precisamente o caminho em que ele deve dirigir. Acompanhando os últimos avanços no aprendizado profundo end-to-end, treinamos uma rede neural convolucional para mapear imagens e comandos de alto nível diretamente para o controle do veículo como esterçamento, aceleração e frenagem em um ambiente simulado. Embora este seja um trabalho conceitual e multidisciplinar, nossos resultados indicam que podemos melhorar significativamente o desempenho do veículo ao delimitar seu caminho, e dessa forma contribuir com o avanço da tecnologia autônoma.
 
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.
Publishing Date
2023-07-19
 
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.