Cargando…

An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms

In this paper, one solution for an end-to-end deep neural network for autonomous driving is presented. The main objective of our work was to achieve autonomous driving with a light deep neural network suitable for deployment on embedded automotive platforms. There are several end-to-end deep neural...

Descripción completa

Detalles Bibliográficos
Autores principales: Kocić, Jelena, Jovičić, Nenad, Drndarević, Vujo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6539483/
https://www.ncbi.nlm.nih.gov/pubmed/31058820
http://dx.doi.org/10.3390/s19092064
_version_ 1783422399464603648
author Kocić, Jelena
Jovičić, Nenad
Drndarević, Vujo
author_facet Kocić, Jelena
Jovičić, Nenad
Drndarević, Vujo
author_sort Kocić, Jelena
collection PubMed
description In this paper, one solution for an end-to-end deep neural network for autonomous driving is presented. The main objective of our work was to achieve autonomous driving with a light deep neural network suitable for deployment on embedded automotive platforms. There are several end-to-end deep neural networks used for autonomous driving, where the input to the machine learning algorithm are camera images and the output is the steering angle prediction, but those convolutional neural networks are significantly more complex than the network architecture we are proposing. The network architecture, computational complexity, and performance evaluation during autonomous driving using our network are compared with two other convolutional neural networks that we re-implemented with the aim to have an objective evaluation of the proposed network. The trained model of the proposed network is four times smaller than the PilotNet model and about 250 times smaller than AlexNet model. While complexity and size of the novel network are reduced in comparison to other models, which leads to lower latency and higher frame rate during inference, our network maintained the performance, achieving successful autonomous driving with similar efficiency compared to autonomous driving using two other models. Moreover, the proposed deep neural network downsized the needs for real-time inference hardware in terms of computational power, cost, and size.
format Online
Article
Text
id pubmed-6539483
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-65394832019-06-04 An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms Kocić, Jelena Jovičić, Nenad Drndarević, Vujo Sensors (Basel) Article In this paper, one solution for an end-to-end deep neural network for autonomous driving is presented. The main objective of our work was to achieve autonomous driving with a light deep neural network suitable for deployment on embedded automotive platforms. There are several end-to-end deep neural networks used for autonomous driving, where the input to the machine learning algorithm are camera images and the output is the steering angle prediction, but those convolutional neural networks are significantly more complex than the network architecture we are proposing. The network architecture, computational complexity, and performance evaluation during autonomous driving using our network are compared with two other convolutional neural networks that we re-implemented with the aim to have an objective evaluation of the proposed network. The trained model of the proposed network is four times smaller than the PilotNet model and about 250 times smaller than AlexNet model. While complexity and size of the novel network are reduced in comparison to other models, which leads to lower latency and higher frame rate during inference, our network maintained the performance, achieving successful autonomous driving with similar efficiency compared to autonomous driving using two other models. Moreover, the proposed deep neural network downsized the needs for real-time inference hardware in terms of computational power, cost, and size. MDPI 2019-05-03 /pmc/articles/PMC6539483/ /pubmed/31058820 http://dx.doi.org/10.3390/s19092064 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kocić, Jelena
Jovičić, Nenad
Drndarević, Vujo
An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms
title An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms
title_full An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms
title_fullStr An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms
title_full_unstemmed An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms
title_short An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms
title_sort end-to-end deep neural network for autonomous driving designed for embedded automotive platforms
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6539483/
https://www.ncbi.nlm.nih.gov/pubmed/31058820
http://dx.doi.org/10.3390/s19092064
work_keys_str_mv AT kocicjelena anendtoenddeepneuralnetworkforautonomousdrivingdesignedforembeddedautomotiveplatforms
AT jovicicnenad anendtoenddeepneuralnetworkforautonomousdrivingdesignedforembeddedautomotiveplatforms
AT drndarevicvujo anendtoenddeepneuralnetworkforautonomousdrivingdesignedforembeddedautomotiveplatforms
AT kocicjelena endtoenddeepneuralnetworkforautonomousdrivingdesignedforembeddedautomotiveplatforms
AT jovicicnenad endtoenddeepneuralnetworkforautonomousdrivingdesignedforembeddedautomotiveplatforms
AT drndarevicvujo endtoenddeepneuralnetworkforautonomousdrivingdesignedforembeddedautomotiveplatforms