Driving Assistant Companion with Voice Interface Using Long Short-Term Memory Networks

Jehyun Park, Hojoon Son, Jisuk Lee, Jongeun Choi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we propose a driving assistant companion system that provides drivers with useful information using a long short-Term memory network in a data-driven fashion. Our system can be viewed as an advanced driver-Assistance system for faster learning and better driving. The assistant companion predicts upcoming events on the road by using real-Time sensory measurements from range finding sensors and provides informative narrations to enhance learnability and driving performance. In contrast to a conventional navigation system, our system predicts events from the online stream of sensory measurements without resorting to priors and map information. To demonstrate the effectiveness of the proposed system, we implemented our system on The Open Racing Car Simulator and conducted an experimental study with 16 human drivers. Experimental results show that our system enhanced learnability, driving performance, and reliability.

Original languageEnglish
Article number8423671
Pages (from-to)582-590
Number of pages9
JournalIEEE Transactions on Industrial Informatics
Volume15
Issue number1
DOIs
Publication statusPublished - 2019 Jan

Fingerprint

Advanced driver assistance systems
Navigation systems
Railroad cars
Simulators
Sensors
Long short-term memory

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

@article{9b42a81fb6b044148a1b4611ccfed6a4,
title = "Driving Assistant Companion with Voice Interface Using Long Short-Term Memory Networks",
abstract = "In this paper, we propose a driving assistant companion system that provides drivers with useful information using a long short-Term memory network in a data-driven fashion. Our system can be viewed as an advanced driver-Assistance system for faster learning and better driving. The assistant companion predicts upcoming events on the road by using real-Time sensory measurements from range finding sensors and provides informative narrations to enhance learnability and driving performance. In contrast to a conventional navigation system, our system predicts events from the online stream of sensory measurements without resorting to priors and map information. To demonstrate the effectiveness of the proposed system, we implemented our system on The Open Racing Car Simulator and conducted an experimental study with 16 human drivers. Experimental results show that our system enhanced learnability, driving performance, and reliability.",
author = "Jehyun Park and Hojoon Son and Jisuk Lee and Jongeun Choi",
year = "2019",
month = "1",
doi = "10.1109/TII.2018.2861739",
language = "English",
volume = "15",
pages = "582--590",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "IEEE Computer Society",
number = "1",

}

Driving Assistant Companion with Voice Interface Using Long Short-Term Memory Networks. / Park, Jehyun; Son, Hojoon; Lee, Jisuk; Choi, Jongeun.

In: IEEE Transactions on Industrial Informatics, Vol. 15, No. 1, 8423671, 01.2019, p. 582-590.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Driving Assistant Companion with Voice Interface Using Long Short-Term Memory Networks

AU - Park, Jehyun

AU - Son, Hojoon

AU - Lee, Jisuk

AU - Choi, Jongeun

PY - 2019/1

Y1 - 2019/1

N2 - In this paper, we propose a driving assistant companion system that provides drivers with useful information using a long short-Term memory network in a data-driven fashion. Our system can be viewed as an advanced driver-Assistance system for faster learning and better driving. The assistant companion predicts upcoming events on the road by using real-Time sensory measurements from range finding sensors and provides informative narrations to enhance learnability and driving performance. In contrast to a conventional navigation system, our system predicts events from the online stream of sensory measurements without resorting to priors and map information. To demonstrate the effectiveness of the proposed system, we implemented our system on The Open Racing Car Simulator and conducted an experimental study with 16 human drivers. Experimental results show that our system enhanced learnability, driving performance, and reliability.

AB - In this paper, we propose a driving assistant companion system that provides drivers with useful information using a long short-Term memory network in a data-driven fashion. Our system can be viewed as an advanced driver-Assistance system for faster learning and better driving. The assistant companion predicts upcoming events on the road by using real-Time sensory measurements from range finding sensors and provides informative narrations to enhance learnability and driving performance. In contrast to a conventional navigation system, our system predicts events from the online stream of sensory measurements without resorting to priors and map information. To demonstrate the effectiveness of the proposed system, we implemented our system on The Open Racing Car Simulator and conducted an experimental study with 16 human drivers. Experimental results show that our system enhanced learnability, driving performance, and reliability.

UR - http://www.scopus.com/inward/record.url?scp=85050972985&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050972985&partnerID=8YFLogxK

U2 - 10.1109/TII.2018.2861739

DO - 10.1109/TII.2018.2861739

M3 - Article

AN - SCOPUS:85050972985

VL - 15

SP - 582

EP - 590

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

IS - 1

M1 - 8423671

ER -