An important field in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent. When gradient-based methods are used, models are kept small or rely on finite difference approximations for the Jacobian. This method quickly grows expensive with increasing numbers of parameters, such as found in deep learning. We propose an implementation of a modern physics engine, which can differentiate control parameters. This engine is implemented for both CPU and GPU. Firstly, this paper shows how such an engine speeds up the optimization process, even for small problems. Furthermore, it explains why this is an alternative approach to deep Q-learning, for using deep learning in robotics. Finally, we argue that this is a big step for deep learning in robotics, as it opens up new possibilities to optimize robots, both in hardware and software.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    A differentiable physics engine for deep learning in robotics


    Beteiligte:

    Erscheinungsdatum :

    2019-01-01


    Anmerkungen:

    FRONTIERS IN NEUROROBOTICS ; ISSN: 1662-5218



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    The ChainQueen differentiable physics engine

    Hu, Yuanming,S. M.Massachusetts Institute of Technology. | BASE | 2019

    Freier Zugriff

    Arduino: From Physics to Robotics

    Marzoli, Irene / Rizza, Nico / Saltarelli, Alessandro et al. | Springer Verlag | 2021

    Freier Zugriff

    Teaching Physics Concepts Using Educational Robotics

    Guastella, Domenico / D'Amico, Antonella | TIBKAT | 2020


    Differentiable Game Mechanics

    Letcher, A / Balduzzi, D / Racaniere, S et al. | BASE | 2019

    Freier Zugriff

    FPGA architecture for deep learning and its application to planetary robotics

    Gankidi, Pranay Reddy / Thangavelautham, Jekan | IEEE | 2017