Parameterizing value functions as a representation of robotic tasks in different domains allows for their generalization, and can provide a way to transfer knowledge to new situations. To this end, in this paper we propose a modulation based mechanism embedded within a cognitive architecture for robots. It makes use of the combined operation of the long-term memory and the motivational system in order to select candidate primitive value functions for transfer. These are then adapted to the new situation through the addition of modulatory ANNs to progressively conform new parameterized value functions able to address more complex situations in a developmental manner. The proposed method is tested in a Baxter robot, which must solve different tasks in a cooking setup.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Producing Parameterized Value Functions Through Modulation for Cognitive Developmental Robots


    Weitere Titelangaben:

    Advs in Intelligent Syst., Computing


    Beteiligte:
    Silva, Manuel F. (Herausgeber:in) / Luís Lima, José (Herausgeber:in) / Reis, Luís Paulo (Herausgeber:in) / Sanfeliu, Alberto (Herausgeber:in) / Tardioli, Danilo (Herausgeber:in) / Romero, Alejandro (Autor:in) / Bellas, Francisco (Autor:in) / Becerra, Jose A. (Autor:in) / Duro, Richard J. (Autor:in)

    Kongress:

    Iberian Robotics conference ; 2019 ; Porto, Portugal November 20, 2019 - November 22, 2019



    Erscheinungsdatum :

    20.11.2019


    Format / Umfang :

    13 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch