Artificial conciousness: an approach to autonomous agents based in a global workspace model

Mendoza Soto, Francisco Manuel (2020). Artificial conciousness: an approach to autonomous agents based in a global workspace model. Thesis (Master thesis), E.T.S. de Ingenieros Informáticos (UPM).

Description

Title: Artificial conciousness: an approach to autonomous agents based in a global workspace model
Author/s:
  • Mendoza Soto, Francisco Manuel
Contributor/s:
  • Molina González, Martín
Item Type: Thesis (Master thesis)
Masters title: Inteligencia Artificial
Date: July 2020
Subjects:
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Inteligencia Artificial
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

Este proyecto busca estudiar y analizar el estado del arte del campo de la conciencia artificial, centrándose en el estudio de la conciencia de acceso y las múltiples propiedades beneficiosas que pueden obtenerse implementando algunas de las técnicas de procesamiento de la información relacionadas con la conciencia. Se piensa que usar algunas de las técnicas estudiadas en el campo de la conciencia artificial podría permitirnos construir sistemas autónomos más eficientes y robustos. A lo largo de este documento, se presenta un modelo consciente diseñado para construir agentes autónomos basado en un espacio de trabajo global. El objetivo del modelo es crear agentes autónomos que sean capaces de navegar en un entorno compuesto de múltiples magnitudes independientes, adaptándose a sus alrededores para encontrar la mejor posición posible en base a sus preferencias internas. El propósito del modelo es poder probar la efectividad de distintos mecanismos cognitivos que han sido incorporados, tales como el mecanismo de la atención para selección de magnitudes, posesión de sentimientos personales y preferencias, uso de un sistema de memoria para guardado de creencias y pasadas experiencias, y, por supuesto, incorporación de un espacio de trabajo global que controla e integra la información procesada por todos los subsistemas del modelo.---ABSTRACT---This project seeks to study and analyze the state of the art of the field of artificial consciousness, focusing on the search of access consciousness and the beneficial properties that can be obtained implementing some of the information processing techniques related to consciousness. It is thought that using some of the techniques studied in artificial consciousness could allows us to build more effective and robust autonomous systems. Along this document, a conscious model of autonomous agent based in a global workspace architecture is presented. The goal of this model is to create autonomous agents able to navigate within an environment composed of multiple independent magnitudes, adapting to its surroundings in order to find the best possible position in base of its inner preferences. The purpose of the model is to test the effectiveness of many cognitive mechanisms that are incorporated, such as an attention mechanism for magnitude selection, possession of inner feelings and preferences, usage of a memory system to storage beliefs and past experiences, and, of course, incorporation of a global workspace which controls and integrates information processed by all the subsystem of the model.

More information

Item ID: 63756
DC Identifier: http://oa.upm.es/63756/
OAI Identifier: oai:oa.upm.es:63756
Deposited by: Biblioteca Facultad de Informatica
Deposited on: 11 Sep 2020 06:11
Last Modified: 11 Sep 2020 06:11
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM