Curvature-optimal path planning and servoing for autonomous vehicles

A neural net implementation

Kari Rintanen (Corresponding Author)

Research output: Contribution to journalArticleScientificpeer-review

3 Citations (Scopus)

Abstract

This paper shows how to implement curvature-optimal solutions of path-planning and trajectoryservoing problems for autonomous vehicles by using neural nets. The neural net is used to implement the nonlinear optimal state-feedback laws. The trained net can be used in real-time control. The net is trained by simulated data generated at random. No two-point boundary-value problems need to be solved. The method presented can, in general, be applied to a wide range of time-invariant terminal control or servo control problems.
Original languageEnglish
Pages (from-to)161-168
Number of pages8
JournalEngineering Applications of Artificial Intelligence
Volume7
Issue number2
DOIs
Publication statusPublished - 1994
MoE publication typeA1 Journal article-refereed

Fingerprint

Motion planning
Neural networks
Real time control
State feedback
Boundary value problems

Cite this

@article{4d508804d68e46aab3ff4128828e8341,
title = "Curvature-optimal path planning and servoing for autonomous vehicles: A neural net implementation",
abstract = "This paper shows how to implement curvature-optimal solutions of path-planning and trajectoryservoing problems for autonomous vehicles by using neural nets. The neural net is used to implement the nonlinear optimal state-feedback laws. The trained net can be used in real-time control. The net is trained by simulated data generated at random. No two-point boundary-value problems need to be solved. The method presented can, in general, be applied to a wide range of time-invariant terminal control or servo control problems.",
author = "Kari Rintanen",
note = "Project code: AUT91082",
year = "1994",
doi = "10.1016/0952-1976(94)90020-5",
language = "English",
volume = "7",
pages = "161--168",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier",
number = "2",

}

Curvature-optimal path planning and servoing for autonomous vehicles : A neural net implementation. / Rintanen, Kari (Corresponding Author).

In: Engineering Applications of Artificial Intelligence, Vol. 7, No. 2, 1994, p. 161-168.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Curvature-optimal path planning and servoing for autonomous vehicles

T2 - A neural net implementation

AU - Rintanen, Kari

N1 - Project code: AUT91082

PY - 1994

Y1 - 1994

N2 - This paper shows how to implement curvature-optimal solutions of path-planning and trajectoryservoing problems for autonomous vehicles by using neural nets. The neural net is used to implement the nonlinear optimal state-feedback laws. The trained net can be used in real-time control. The net is trained by simulated data generated at random. No two-point boundary-value problems need to be solved. The method presented can, in general, be applied to a wide range of time-invariant terminal control or servo control problems.

AB - This paper shows how to implement curvature-optimal solutions of path-planning and trajectoryservoing problems for autonomous vehicles by using neural nets. The neural net is used to implement the nonlinear optimal state-feedback laws. The trained net can be used in real-time control. The net is trained by simulated data generated at random. No two-point boundary-value problems need to be solved. The method presented can, in general, be applied to a wide range of time-invariant terminal control or servo control problems.

U2 - 10.1016/0952-1976(94)90020-5

DO - 10.1016/0952-1976(94)90020-5

M3 - Article

VL - 7

SP - 161

EP - 168

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

IS - 2

ER -