Universidad Complutense de Madrid
E-Prints Complutense

Simple Agents Benefit Only From Simple Brains



Último año

Makarov, Valeri A. y Castellanos, Nazareth P. y Velarde, Manuel G. (2006) Simple Agents Benefit Only From Simple Brains. Proceedings of World Academy of Science Engineering and Technology, 15 . 25-30 . ISSN 1307-6884

[img] PDF
Restringido a Sólo personal autorizado del repositorio hasta 31 Diciembre 2020.


URL Oficial: http://www.waset.org/journals/waset/v15/v15-121.pdf

URLTipo de URL


In order to answer the general question: "What does a simple agent with a limited life-time require for constructing a useful representation of the environment?" we propose a robot platform including the simplest probabilistic sensory and motor layers. Then we use the platform as a test-bed for evaluation of the navigational capabilities of the robot with different "brains". We claim that a protocognitive behavior is not a consequence of highly sophisticated sensory-motor organs but instead emerges through an increment of the internal complexity and reutilization of the minimal sensory information. We show that the most fundamental robot element, the short-time memory, is essential in obstacle avoidance. However, in the simplest conditions of no obstacles the straightforward memory-less robot is usually superior. We also demonstrate how a low level action planning. involving essentially nonlinear dynamics, provides a considerable gain to the robot performance dynamically changing the robot strategy. Still, however, for very short life time the brainless robot is superior. Accordingly we suggest that small organisms (or agents) with short life-time does not require complex brains and even can benefit from simple brain-like (reflex) structures. To some extend this may mean that controlling blocks of modern robots are too complicated comparative to their life-time and mechanical abilities.

Tipo de documento:Artículo
Información Adicional:

Conference of the World-Academy-of-Science-Engineering-and-Technology. Barcelona, SPAIN. OCT 22-24, 2006.

Palabras clave:Neural network; Probabilistic control; Robot navigation
Materias:Ciencias > Informática > Programación de ordenadores
Código ID:16812
Depositado:23 Oct 2012 08:26
Última Modificación:28 Jun 2016 14:32

Descargas en el último año

Sólo personal del repositorio: página de control del artículo