Trabajo presentado en la IEEE/RSJ International Conference on Intelligent Robots and System, celebrada en Las Vegas (Estados Unidos), del 25 L 29 de octubre de 2020 ; Learning is usually performed by observing real robot executions. Physics-based simulators are a good alternative for providing highly valuable information while avoiding costly and potentially destructive robot executions. We present a novel approach for learning the probabilities of symbolic robot action outcomes. This is done leveraging different environments, such as physics-based simulators, in execution time. To this end, we propose MENID (Multiple Environment Noise Indeterministic Deictic) rules, a novel representation able to cope with the inherent uncertainties present in robotic tasks. MENID rules explicitly represent each possible outcomes of an action, keep memory of the source of the experience, and maintain the probability of success of each outcome. We also introduce an algorithm to distribute actions among environments, based on previous experiences and expected gain. Before using physics-based simulations, we propose a methodology for evaluating different simulation settings and determining the least time-consuming model that could be used while still producing coherent results. We demonstrate the validity of the approach in a dismantling use case, using a simulation with reduced quality as simulated system, and a simulation with full resolution where we add noise to the trajectories and some physical parameters as a representation of the real system.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Leveraging multiple environments for learning and decision making: a dismantling use case


    Beteiligte:

    Erscheinungsdatum :

    2020-01-01



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    DDC:    629




    DISMANTLING FACILITIES AND DISMANTLING METHOD

    YAMAMOTO KAZUHIDE / SUZUKI YUTO / MINAMIYAMA AKIO et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    DISMANTLING SYSTEM

    TANAKA KIYOKAZU / OKADA TOMOFUMI / TAKAMURA REONA | Europäisches Patentamt | 2020

    Freier Zugriff

    Dismantling system

    TANAKA KIYOKAZU / OKADA TOMOFUMI / TAKAMURA REONA | Europäisches Patentamt | 2022

    Freier Zugriff