Design of the optimal motions of autonomous vehicles in intersections through neural networks

Balázs Németh, P. Gáspár, Dávid Szőcs, András Mihály

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The handling of vehicle interactions is a challenge in the research into the traveling of autonomous vehicles. This paper focuses on collision-free motion design of autonomous vehicles to guarantee their minimum traveling time in intersections. First, a decision logic of the order of the vehicles in intersections is proposed. Based on the decision logic a constrained nonlinear optimization method is also proposed, with which the minimum traveling time of the vehicles without their collision is guaranteed. Since the on-line solution of the nonlinear optimization task can be numerically complex, a neural network based approximation of the optimal solution is developed. The efficiency of the method with various intersection scenarios is shown in the CarSim simulation environment.

Original languageEnglish
Pages (from-to)19-24
Number of pages6
JournalIFAC-PapersOnLine
Volume51
Issue number9
DOIs
Publication statusPublished - Jan 1 2018

Fingerprint

Neural networks

Keywords

  • autonomous vehicles
  • constrained nonlinear optimization
  • intersections
  • neural networks

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Design of the optimal motions of autonomous vehicles in intersections through neural networks. / Németh, Balázs; Gáspár, P.; Szőcs, Dávid; Mihály, András.

In: IFAC-PapersOnLine, Vol. 51, No. 9, 01.01.2018, p. 19-24.

Research output: Contribution to journalArticle

Németh, Balázs ; Gáspár, P. ; Szőcs, Dávid ; Mihály, András. / Design of the optimal motions of autonomous vehicles in intersections through neural networks. In: IFAC-PapersOnLine. 2018 ; Vol. 51, No. 9. pp. 19-24.
@article{aada69e1bfe14fce92c1fd2f66c081da,
title = "Design of the optimal motions of autonomous vehicles in intersections through neural networks",
abstract = "The handling of vehicle interactions is a challenge in the research into the traveling of autonomous vehicles. This paper focuses on collision-free motion design of autonomous vehicles to guarantee their minimum traveling time in intersections. First, a decision logic of the order of the vehicles in intersections is proposed. Based on the decision logic a constrained nonlinear optimization method is also proposed, with which the minimum traveling time of the vehicles without their collision is guaranteed. Since the on-line solution of the nonlinear optimization task can be numerically complex, a neural network based approximation of the optimal solution is developed. The efficiency of the method with various intersection scenarios is shown in the CarSim simulation environment.",
keywords = "autonomous vehicles, constrained nonlinear optimization, intersections, neural networks",
author = "Bal{\'a}zs N{\'e}meth and P. G{\'a}sp{\'a}r and D{\'a}vid Szőcs and Andr{\'a}s Mih{\'a}ly",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.ifacol.2018.07.004",
language = "English",
volume = "51",
pages = "19--24",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "IFAC Secretariat",
number = "9",

}

TY - JOUR

T1 - Design of the optimal motions of autonomous vehicles in intersections through neural networks

AU - Németh, Balázs

AU - Gáspár, P.

AU - Szőcs, Dávid

AU - Mihály, András

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The handling of vehicle interactions is a challenge in the research into the traveling of autonomous vehicles. This paper focuses on collision-free motion design of autonomous vehicles to guarantee their minimum traveling time in intersections. First, a decision logic of the order of the vehicles in intersections is proposed. Based on the decision logic a constrained nonlinear optimization method is also proposed, with which the minimum traveling time of the vehicles without their collision is guaranteed. Since the on-line solution of the nonlinear optimization task can be numerically complex, a neural network based approximation of the optimal solution is developed. The efficiency of the method with various intersection scenarios is shown in the CarSim simulation environment.

AB - The handling of vehicle interactions is a challenge in the research into the traveling of autonomous vehicles. This paper focuses on collision-free motion design of autonomous vehicles to guarantee their minimum traveling time in intersections. First, a decision logic of the order of the vehicles in intersections is proposed. Based on the decision logic a constrained nonlinear optimization method is also proposed, with which the minimum traveling time of the vehicles without their collision is guaranteed. Since the on-line solution of the nonlinear optimization task can be numerically complex, a neural network based approximation of the optimal solution is developed. The efficiency of the method with various intersection scenarios is shown in the CarSim simulation environment.

KW - autonomous vehicles

KW - constrained nonlinear optimization

KW - intersections

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=85050124876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050124876&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2018.07.004

DO - 10.1016/j.ifacol.2018.07.004

M3 - Article

AN - SCOPUS:85050124876

VL - 51

SP - 19

EP - 24

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 9

ER -