DNN-assisted cooperative localization in vehicular networks

Jewon Eom, Hyowon Kim, Sang Hyun Lee, Sunwoo Kim

Research output: Contribution to journalArticle

Abstract

This work develops a deep-learning-based cooperative localization technique for high localization accuracy and real-time operation in vehicular networks. In cooperative localization, the noisy observation of the pairwise distance and the angle between vehicles causes nonlinear optimization problems. To handle such a nonlinear optimization task at each vehicle, a deep neural network (DNN) technique is to replace a cumbersome solution of nonlinear optimization along with the saving of the computational loads. Simulation results demonstrate that the proposed technique attains some performance gain in localization accuracy and computational complexity as compared to existing cooperative localization techniques.

Original languageEnglish
Article number2758
JournalEnergies
Volume12
Issue number14
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Vehicular Networks
Neural Networks
Nonlinear Optimization
Computational complexity
Nonlinear Problem
Pairwise
Computational Complexity
Deep neural networks
Optimization Problem
Real-time
Angle
Demonstrate
Simulation

Keywords

  • Cooperative localization
  • Deep neural network
  • Internet of vehicle
  • Multilateration
  • Vehicular networks

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Energy Engineering and Power Technology
  • Energy (miscellaneous)
  • Control and Optimization
  • Electrical and Electronic Engineering

Cite this

DNN-assisted cooperative localization in vehicular networks. / Eom, Jewon; Kim, Hyowon; Lee, Sang Hyun; Kim, Sunwoo.

In: Energies, Vol. 12, No. 14, 2758, 01.01.2019.

Research output: Contribution to journalArticle

Eom, Jewon ; Kim, Hyowon ; Lee, Sang Hyun ; Kim, Sunwoo. / DNN-assisted cooperative localization in vehicular networks. In: Energies. 2019 ; Vol. 12, No. 14.
@article{0d9a3a239f9249f4b3352a4f49150a33,
title = "DNN-assisted cooperative localization in vehicular networks",
abstract = "This work develops a deep-learning-based cooperative localization technique for high localization accuracy and real-time operation in vehicular networks. In cooperative localization, the noisy observation of the pairwise distance and the angle between vehicles causes nonlinear optimization problems. To handle such a nonlinear optimization task at each vehicle, a deep neural network (DNN) technique is to replace a cumbersome solution of nonlinear optimization along with the saving of the computational loads. Simulation results demonstrate that the proposed technique attains some performance gain in localization accuracy and computational complexity as compared to existing cooperative localization techniques.",
keywords = "Cooperative localization, Deep neural network, Internet of vehicle, Multilateration, Vehicular networks",
author = "Jewon Eom and Hyowon Kim and Lee, {Sang Hyun} and Sunwoo Kim",
year = "2019",
month = "1",
day = "1",
doi = "10.3390/en12142758",
language = "English",
volume = "12",
journal = "Energies",
issn = "1996-1073",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "14",

}

TY - JOUR

T1 - DNN-assisted cooperative localization in vehicular networks

AU - Eom, Jewon

AU - Kim, Hyowon

AU - Lee, Sang Hyun

AU - Kim, Sunwoo

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This work develops a deep-learning-based cooperative localization technique for high localization accuracy and real-time operation in vehicular networks. In cooperative localization, the noisy observation of the pairwise distance and the angle between vehicles causes nonlinear optimization problems. To handle such a nonlinear optimization task at each vehicle, a deep neural network (DNN) technique is to replace a cumbersome solution of nonlinear optimization along with the saving of the computational loads. Simulation results demonstrate that the proposed technique attains some performance gain in localization accuracy and computational complexity as compared to existing cooperative localization techniques.

AB - This work develops a deep-learning-based cooperative localization technique for high localization accuracy and real-time operation in vehicular networks. In cooperative localization, the noisy observation of the pairwise distance and the angle between vehicles causes nonlinear optimization problems. To handle such a nonlinear optimization task at each vehicle, a deep neural network (DNN) technique is to replace a cumbersome solution of nonlinear optimization along with the saving of the computational loads. Simulation results demonstrate that the proposed technique attains some performance gain in localization accuracy and computational complexity as compared to existing cooperative localization techniques.

KW - Cooperative localization

KW - Deep neural network

KW - Internet of vehicle

KW - Multilateration

KW - Vehicular networks

UR - http://www.scopus.com/inward/record.url?scp=85069619139&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069619139&partnerID=8YFLogxK

U2 - 10.3390/en12142758

DO - 10.3390/en12142758

M3 - Article

VL - 12

JO - Energies

JF - Energies

SN - 1996-1073

IS - 14

M1 - 2758

ER -