Back to results
Bibliographic record · Consultation and access
Document

Modular creation of neuronal networks for autonomous robot control

Osella Massa, Germán Leandro et al · SEDICI UNLP · 2006

Supplementary material available
Quick overview. Review the resource’s basic details, then access the content using the main button. This page shows only the information needed to identify, cite, and open the work.

Resource access

Open the content from the main option or choose another available source.

SEDICI UNLP SEDICI UNLP OAI-PMH
Entrar por SEDICI UNLP
Main access

Supplementary material available

El enlace apunta a material asociado, anexos, tablas, datos o página complementaria. No se marca como libro/texto completo.
Open material

Summary

Descripción general del contenido del recurso.

En general, las tareas de control complejas pueden ser resueltas dividiéndolas en módulos más específicos y fáciles de manejar. Varios autores han desarrollado distintas soluciones que combinan técnicas de Evolución por Capas con Redes Neuronales Evolutivas dando lugar a controladores formados por varias redes. En este tipo de soluciones la elección del módulo a utilizar en cada caso no es un problema de fácil solución. Este artículo está enfocado en la presentación de un nuevo mecanismo evolutivo que permite combinar los módulos que resuelven las distintas partes de un problema dando lugar a una única red neuronal recurrente. De esta forma, se trabaja con módulos simples que son entrenados independientemente del problema a resolver. La comunicación entre ellos se establece por evolución dando lugar a una única red neuronal que representa a la solución deseada. El método propuesto en este artículo ha sido utilizado para resolver el problema de evasión de obstáculos y alcance de objetivos utilizando un robot Khepera II. Las pruebas realizadas tanto en el ambiente simulado como sobre el robot real han arrojado resultados muy satisfactorios. Finalmente se incluyen algunas conclusiones junto con líneas de trabajo futuras In general, complex control tasks can be solved by dividing them into simpler ones which are easier to handle. Several authors have developed different solutions that combine Layer Evolution techniques with Evolving Neural Networks, giving rise to controllers made up by several networks. In this type of solution, the selection of the module to be used in each case is not an easy problem to solve. This paper is focused on the presentation of a new evolving mechanism that allows combining the modules which solve the different parts of a problem, giving place to a single recurrent neural network. In this way, simple modules which are trained independently of the problem to solve are used. The communication among them is established by evolution, which gives rise to a single neural network representing the expected solution. The proposed method in this paper has been used to solve the problem of obstacle evasion and target reaching using a Khepera II robot. The tests carried out, both in the simulated environment and over the real robot, have yielded really successful results. Finally, some conclusions, together some future lines of work, are presented VII Workshop de Agentes y Sistemas Inteligentes (WASI)

How to cite

Elegí el formato que necesitás y copiá la referencia al portapapeles.

APA 7

Osella Massa, G. L. E. A. (2006). Modular creation of neuronal networks for autonomous robot control. SEDICI UNLP. http://sedici.unlp.edu.ar/handle/10915/22662

MLA

Osella Massa, Germán Leandro et al. Modular creation of neuronal networks for autonomous robot control. SEDICI UNLP, 2006. http://sedici.unlp.edu.ar/handle/10915/22662.

Chicago

Osella Massa, Germán Leandro et al. 2006. Modular creation of neuronal networks for autonomous robot control. SEDICI UNLP. http://sedici.unlp.edu.ar/handle/10915/22662.

Harvard

Osella Massa, G. L. E. A. 2006, Modular creation of neuronal networks for autonomous robot control, SEDICI UNLP, available at: http://sedici.unlp.edu.ar/handle/10915/22662 [Accessed 7 Aug. 2026].

Share and print

Save the record, copy its permanent link, or print it as a PDF.

Export reference

You can export the record in common formats for use in a reference manager.

Resource details

Bibliographic information to help confirm that this is the correct material.

Title
Modular creation of neuronal networks for autonomous robot control
Author / contributors
Osella Massa, Germán Leandro et al
Publisher
SEDICI UNLP
Publication year
2006
Language
English

Subjects

Explore related resources through these subjects.

Copied