A Convolutional Neural Network-Based End-to-End Self-Driving Using LiDAR and Camera Fusion: Analysis Perspectives in a Real-World Environment

In this paper, we develop end-to-end autonomous driving based on a 2D LiDAR sensor and camera sensor that predict the control value of the vehicle from the input data, instead of modeling rule-based autonomous driving. Different from many studies utilizing simulated data, we created an end-to-end au...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mingyu Park, Hyeonseok Kim, Seongkeun Park
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	end-to-end control convolutional neural network self-driving LiDAR sensor vision sensor Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/1714953ab4284c21a69bc64ff0144aab
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1714953ab4284c21a69bc64ff0144aab
record_format	dspace
spelling	oai:doaj.org-article:1714953ab4284c21a69bc64ff0144aab2021-11-11T15:37:54ZA Convolutional Neural Network-Based End-to-End Self-Driving Using LiDAR and Camera Fusion: Analysis Perspectives in a Real-World Environment10.3390/electronics102126082079-9292https://doaj.org/article/1714953ab4284c21a69bc64ff0144aab2021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2608https://doaj.org/toc/2079-9292In this paper, we develop end-to-end autonomous driving based on a 2D LiDAR sensor and camera sensor that predict the control value of the vehicle from the input data, instead of modeling rule-based autonomous driving. Different from many studies utilizing simulated data, we created an end-to-end autonomous driving algorithm with data obtained from real driving and analyzing the performance of our proposed algorithm. Based on the data obtained from an actual urban driving environment, end-to-end autonomous driving was possible in an informal environment such as a traffic signal by predicting the vehicle control value based on a convolution neural network. In addition, this paper solves the data imbalance problem by eliminating redundant data for each frame during stopping and driving in the driving environment so we can improve the performance of self-driving. Finally, we verified through the activation map how the network predicts the vertical and horizontal control values by recognizing the traffic facilities in the driving environment. Experiments and analysis will be shown to show the validity of the proposed algorithm.Mingyu ParkHyeonseok KimSeongkeun ParkMDPI AGarticleend-to-end controlconvolutional neural networkself-drivingLiDAR sensorvision sensorElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2608, p 2608 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	end-to-end control convolutional neural network self-driving LiDAR sensor vision sensor Electronics TK7800-8360
spellingShingle	end-to-end control convolutional neural network self-driving LiDAR sensor vision sensor Electronics TK7800-8360 Mingyu Park Hyeonseok Kim Seongkeun Park A Convolutional Neural Network-Based End-to-End Self-Driving Using LiDAR and Camera Fusion: Analysis Perspectives in a Real-World Environment
description	In this paper, we develop end-to-end autonomous driving based on a 2D LiDAR sensor and camera sensor that predict the control value of the vehicle from the input data, instead of modeling rule-based autonomous driving. Different from many studies utilizing simulated data, we created an end-to-end autonomous driving algorithm with data obtained from real driving and analyzing the performance of our proposed algorithm. Based on the data obtained from an actual urban driving environment, end-to-end autonomous driving was possible in an informal environment such as a traffic signal by predicting the vehicle control value based on a convolution neural network. In addition, this paper solves the data imbalance problem by eliminating redundant data for each frame during stopping and driving in the driving environment so we can improve the performance of self-driving. Finally, we verified through the activation map how the network predicts the vertical and horizontal control values by recognizing the traffic facilities in the driving environment. Experiments and analysis will be shown to show the validity of the proposed algorithm.
format	article
author	Mingyu Park Hyeonseok Kim Seongkeun Park
author_facet	Mingyu Park Hyeonseok Kim Seongkeun Park
author_sort	Mingyu Park
title	A Convolutional Neural Network-Based End-to-End Self-Driving Using LiDAR and Camera Fusion: Analysis Perspectives in a Real-World Environment
title_short	A Convolutional Neural Network-Based End-to-End Self-Driving Using LiDAR and Camera Fusion: Analysis Perspectives in a Real-World Environment
title_full	A Convolutional Neural Network-Based End-to-End Self-Driving Using LiDAR and Camera Fusion: Analysis Perspectives in a Real-World Environment
title_fullStr	A Convolutional Neural Network-Based End-to-End Self-Driving Using LiDAR and Camera Fusion: Analysis Perspectives in a Real-World Environment
title_full_unstemmed	A Convolutional Neural Network-Based End-to-End Self-Driving Using LiDAR and Camera Fusion: Analysis Perspectives in a Real-World Environment
title_sort	convolutional neural network-based end-to-end self-driving using lidar and camera fusion: analysis perspectives in a real-world environment
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/1714953ab4284c21a69bc64ff0144aab
work_keys_str_mv	AT mingyupark aconvolutionalneuralnetworkbasedendtoendselfdrivingusinglidarandcamerafusionanalysisperspectivesinarealworldenvironment AT hyeonseokkim aconvolutionalneuralnetworkbasedendtoendselfdrivingusinglidarandcamerafusionanalysisperspectivesinarealworldenvironment AT seongkeunpark aconvolutionalneuralnetworkbasedendtoendselfdrivingusinglidarandcamerafusionanalysisperspectivesinarealworldenvironment AT mingyupark convolutionalneuralnetworkbasedendtoendselfdrivingusinglidarandcamerafusionanalysisperspectivesinarealworldenvironment AT hyeonseokkim convolutionalneuralnetworkbasedendtoendselfdrivingusinglidarandcamerafusionanalysisperspectivesinarealworldenvironment AT seongkeunpark convolutionalneuralnetworkbasedendtoendselfdrivingusinglidarandcamerafusionanalysisperspectivesinarealworldenvironment
_version_	1718434843400863744

A Convolutional Neural Network-Based End-to-End Self-Driving Using LiDAR and Camera Fusion: Analysis Perspectives in a Real-World Environment

Ejemplares similares