An integrated architecture for motion-control and path-planning

Csaba Szepesväri, A. Lőrincz

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We consider the problem of learning how to control a plant with nonlinear control characteristics and solving the path-planning problem at the same time. The solution is based on a path-planning model that designates a speed field to be tracked, the speed field being the gradient of the equilibrium solution of a diffusionlike process which is simulated on an artificial neural network by spreading activation. The relaxed diffusion field serves as the input to the interneurons which detect the strength of activity flow in between neighboring discretizing neurons. These neurons then emit the control signals to control neurons which are linear elements. The interneuron to control-neuron connections are trained by a variant of Hebb's rule during control. The proposed method, whose most attractive feature is that it integrates reactive path-planning and continuous motion control in a natural fashion, can be used for learning redundant control problems.

Original languageEnglish
Pages (from-to)1-15
Number of pages15
JournalJournal of Robotic Systems
Volume15
Issue number1
Publication statusPublished - Jan 1998

Fingerprint

Motion control
Motion planning
Neurons
Chemical activation
Neural networks

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

An integrated architecture for motion-control and path-planning. / Szepesväri, Csaba; Lőrincz, A.

In: Journal of Robotic Systems, Vol. 15, No. 1, 01.1998, p. 1-15.

Research output: Contribution to journalArticle

@article{8851ea9f50cc4578aa5036d738143266,
title = "An integrated architecture for motion-control and path-planning",
abstract = "We consider the problem of learning how to control a plant with nonlinear control characteristics and solving the path-planning problem at the same time. The solution is based on a path-planning model that designates a speed field to be tracked, the speed field being the gradient of the equilibrium solution of a diffusionlike process which is simulated on an artificial neural network by spreading activation. The relaxed diffusion field serves as the input to the interneurons which detect the strength of activity flow in between neighboring discretizing neurons. These neurons then emit the control signals to control neurons which are linear elements. The interneuron to control-neuron connections are trained by a variant of Hebb's rule during control. The proposed method, whose most attractive feature is that it integrates reactive path-planning and continuous motion control in a natural fashion, can be used for learning redundant control problems.",
author = "Csaba Szepesv{\"a}ri and A. Lőrincz",
year = "1998",
month = "1",
language = "English",
volume = "15",
pages = "1--15",
journal = "Journal of Field Robotics",
issn = "1556-4959",
publisher = "John Wiley and Sons Inc.",
number = "1",

}

TY - JOUR

T1 - An integrated architecture for motion-control and path-planning

AU - Szepesväri, Csaba

AU - Lőrincz, A.

PY - 1998/1

Y1 - 1998/1

N2 - We consider the problem of learning how to control a plant with nonlinear control characteristics and solving the path-planning problem at the same time. The solution is based on a path-planning model that designates a speed field to be tracked, the speed field being the gradient of the equilibrium solution of a diffusionlike process which is simulated on an artificial neural network by spreading activation. The relaxed diffusion field serves as the input to the interneurons which detect the strength of activity flow in between neighboring discretizing neurons. These neurons then emit the control signals to control neurons which are linear elements. The interneuron to control-neuron connections are trained by a variant of Hebb's rule during control. The proposed method, whose most attractive feature is that it integrates reactive path-planning and continuous motion control in a natural fashion, can be used for learning redundant control problems.

AB - We consider the problem of learning how to control a plant with nonlinear control characteristics and solving the path-planning problem at the same time. The solution is based on a path-planning model that designates a speed field to be tracked, the speed field being the gradient of the equilibrium solution of a diffusionlike process which is simulated on an artificial neural network by spreading activation. The relaxed diffusion field serves as the input to the interneurons which detect the strength of activity flow in between neighboring discretizing neurons. These neurons then emit the control signals to control neurons which are linear elements. The interneuron to control-neuron connections are trained by a variant of Hebb's rule during control. The proposed method, whose most attractive feature is that it integrates reactive path-planning and continuous motion control in a natural fashion, can be used for learning redundant control problems.

UR - http://www.scopus.com/inward/record.url?scp=0031678862&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031678862&partnerID=8YFLogxK

M3 - Article

VL - 15

SP - 1

EP - 15

JO - Journal of Field Robotics

JF - Journal of Field Robotics

SN - 1556-4959

IS - 1

ER -