In this thesis we deal with the problem of using deep reinforcement learning to generate robust policies for real robots. We identify three key issues that need to be tackled in order to make progress along these lines. How to perform exploration in robotic tasks, with discontinuities in the environment and sparse rewards. How to ensure policies trained in simulation transfer well to real systems. How to build policies that are robust to environment variability we encounter in the real world. We aim to tackle these issues through three papers that are part of this thesis. In the first one, we present an approach for learning an exploration process based on data from previously solved tasks to aid in solving new ones. In the second, we show how learning variable gain policies can produce better performing solutions on contact sensitive tasks, as well as propose a way to regularize these policies to enable direct transfer to real systems and improve their interpretability. In the final work, we propose a two-stage approach that goes from simple demonstrations to robust adaptive behaviors that can be directly deployed on real systems.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Learning robust control policies for real robots


    Beteiligte:
    Bogdanovic, Miroslav (Autor:in) / Eberhard Karls Universität Tübingen (Grad-verleihende Institution)

    Erscheinungsdatum :

    2021


    Format / Umfang :

    1 Online-Ressource (unterschiedliche Seitenzählungen)


    Anmerkungen:

    Illustrationen



    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    DDC:    629.892




    Robust Software Architecture for Robots

    Aghazanian, Hrand / Baumgartner, Eric / Garrett, Michael | NTRS | 2009


    Sensor based real-time control of robots

    Andersen, Thomas Timm | BASE | 2015

    Freier Zugriff

    ARC: Adversarially Robust Control Policies for Autonomous Vehicles

    Kuutti, Sampo / Fallah, Saber / Bowden, Richard | IEEE | 2021


    Robust Tracking Control of Aerial Robots Via a Simple Learning Strategy-Based Feedback Linearization

    Mehndiratta, Mohit / Kayacan, Erkan / Reyhanoglu, Mahmut et al. | BASE | 2020

    Freier Zugriff