A fast, three-layer neural network for path finding

Kindermann T, Cruse H, Dautenhahn K (1996)
Network. Computation in neural systems 7(2): 423-436.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Kindermann, T.; Cruse, HolkUniBi; Dautenhahn, K.
Abstract / Bemerkung
A path-planning algorithm is proposed to find a path based on local rules applied to a three-layer artificial neural network. Each layer consists of two-dimensionally arranged neurons with recurrent connections within a limited neighbourhood. The output of one layer determines the weights of the connections in the next layer. In principle, the method is based on a diffusion process, but is modified such that it does not suffer from several drawbacks involved in this algorithm. By application of a nonlinear transformation in layer 2, the diffusion front has the qualitative properties of a propagation wave. Therefore, limited resolution of the units is not critical, in contrast to classical diffusion algorithms. Furthermore, the algorithm generally does not suffer from the superposition of diffusion gradients when several paths are possible. The diffusion takes place in a space covered with 'obstacle potentials' which decrease the velocity of the diffusion front. In this way the path can maintain an adjustable safety margin in relation to the obstacles, for example, to cope with problems of incomplete knowledge of the obstacle's position. The algorithm thus combines the advantages of the diffusion algorithm, namely avoidance of local minima of wave propagation, i.e. coping with limited resolution, and the potential field approach, i.e. maintaining a safety margin in relation to obstacles. The distributed architecture also allows for 'spatial interpolation' between the units (coarse coding), thereby providing smooth path forms. A comparison with paths developed by human subjects shows some similarity on the qualitative level, but there are also obvious differences.
Erscheinungsjahr
1996
Zeitschriftentitel
Network. Computation in neural systems
Band
7
Ausgabe
2
Seite(n)
423-436
ISSN
0954-898X
eISSN
1361-6536
Page URI
https://pub.uni-bielefeld.de/record/1638979

Zitieren

Kindermann T, Cruse H, Dautenhahn K. A fast, three-layer neural network for path finding. Network. Computation in neural systems. 1996;7(2):423-436.
Kindermann, T., Cruse, H., & Dautenhahn, K. (1996). A fast, three-layer neural network for path finding. Network. Computation in neural systems, 7(2), 423-436. https://doi.org/10.1088/0954-898X/7/2/022
Kindermann, T., Cruse, Holk, and Dautenhahn, K. 1996. “A fast, three-layer neural network for path finding”. Network. Computation in neural systems 7 (2): 423-436.
Kindermann, T., Cruse, H., and Dautenhahn, K. (1996). A fast, three-layer neural network for path finding. Network. Computation in neural systems 7, 423-436.
Kindermann, T., Cruse, H., & Dautenhahn, K., 1996. A fast, three-layer neural network for path finding. Network. Computation in neural systems, 7(2), p 423-436.
T. Kindermann, H. Cruse, and K. Dautenhahn, “A fast, three-layer neural network for path finding”, Network. Computation in neural systems, vol. 7, 1996, pp. 423-436.
Kindermann, T., Cruse, H., Dautenhahn, K.: A fast, three-layer neural network for path finding. Network. Computation in neural systems. 7, 423-436 (1996).
Kindermann, T., Cruse, Holk, and Dautenhahn, K. “A fast, three-layer neural network for path finding”. Network. Computation in neural systems 7.2 (1996): 423-436.

15 References

Daten bereitgestellt von Europe PubMed Central.


AUTHOR UNKNOWN, 0

AUTHOR UNKNOWN, 0

AUTHOR UNKNOWN, 0

AUTHOR UNKNOWN, 0

Hinton, 1986

AUTHOR UNKNOWN, 0

AUTHOR UNKNOWN, 0

AUTHOR UNKNOWN, 0

Tietz, Dissertation (), 1995
How vernier acuity depends on contrast.
Wehrhahn C, Westheimer G., Exp Brain Res 80(3), 1990
PMID: 2387359
Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®
Quellen

PMID: 16754402
PubMed | Europe PMC

Suchen in

Google Scholar