Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloDifferent Genetic Algorithms and the Evolution of Specialization: A Study with Groups of Simulated Neural Robots
Anno di pubblicazione2013
Formato-
Autore/iFerrauto, Tomassino; Parisi, Domenico; Di Stefano, Gabriele; Baldassarre, Gianluca
Affiliazioni autoriConsiglio Nazionale delle Ricerche (CNR); University of Aquila
Autori CNR e affiliazioni
  • DOMENICO PARISI
  • TOMASSINO FERRAUTO
  • GIANLUCA BALDASSARRE
Lingua/e
  • inglese
AbstractOrganisms that live in groups, from microbial symbionts to social insects and schooling fish, exhibit a number of highly efficient cooperative behaviors, often based on role taking and specialization. These behaviors are relevant not only for the biologist but also for the engineer interested in decentralized collective robotics. We address these phenomena by carrying out experiments with groups of two simulated robots controlled by neural networks whose connection weights are evolved by using genetic algorithms. These algorithms and controllers are well suited to autonomously find solutions for decentralized collective robotic tasks based on principles of self-organization. The article first presents a taxonomy of role-taking and specialization mechanisms related to evolved neural network controllers. Then it introduces two cooperation tasks, which can be accomplished by either role taking or specialization, and uses these tasks to compare four different genetic algorithms to evaluate their capacity to evolve a suitable behavioral strategy, which depends on the task demands. Interestingly, only one of the four algorithms, which appears to have more biological plausibility, is capable of evolving role taking or specialization when they are needed. The results are relevant for both collective robotics and biology, as they can provide useful hints on the different processes that can lead to the emergence of specialization in robots and organisms.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da221
Pagine a253
Pagine totali33
RivistaArtificial life
Attiva dal 1994
Editore: MIT Press, - Cambridge, MA
Paese di pubblicazione: Stati Uniti d'America
Lingua: inglese
ISSN: 1064-5462
Titolo chiave: Artificial life
Titolo proprio: Artificial life.
Titolo abbreviato: Artif. life
Numero volume della rivista19
Fascicolo della rivista2
DOI10.1162/ARTL_a_00106
Verificato da referee-
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • ISI Web of Science (WOS) (Codice:000319210400002)
Parole chiaveCooperation, role taking and specialization, individual and group selection, temporary and stable groups, evolutionary regimes, navigation
Link (URL, URI)-
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • ISTC — Istituto di scienze e tecnologie della cognizione
Moduli/Attività/Sottoprogetti CNR-
Progetti Europei-
Allegati
Different Genetic Algorithms and the Evolution of Specialization: A Study with Groups of Simulated Neural Robots
Descrizione: Article 2013 Baldassarre Different Genetic Algorithms and the Evolution of Specialization: A Study with Groups of Simulated Neural Robots
Tipo documento: application/pdf