This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. ; Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 ; Cataloged from student-submitted PDF version of thesis. ; Includes bibliographical references (pages 47-49). ; Physical simulators have been widely used in robot planning and control. Among them, differentiable simulators are particularly favored, as they can be incorporated into gradient-based optimization algorithms that are efficient in solving inverse problems such as optimal control and motion planning. Simulating deformable objects is, however, more challenging compared to rigid body dynamics. The underlying physical laws of deformable objects are more complex, and the resulting systems have orders of magnitude more degrees of freedom and therefore they are significantly more computationally expensive to simulate. Computing gradients with respect to physical design or controller parameters is typically even more computationally challenging. In this paper, we propose a real-time, differentiable hybrid Lagrangian-Eulerian physical simulator for deformable objects, ChainQueen, based on the Moving Least Squares Material Point Method (MLS-MPM). MLS-MPM can simulate deformable objects including contact and can be seamlessly incorporated into inference, control and co-design systems. We demonstrate that our simulator achieves high precision in both forward simulation and backward gradient computation. We have successfully employed it in a diverse set of control tasks for soft robots, including problems with nearly 3, 000 decision variables. ; by Yuanming Hu. ; S.M. ; S.M. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    The ChainQueen differentiable physics engine



    Erscheinungsdatum :

    2019-01-01


    Anmerkungen:

    1102050240


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629




    A differentiable physics engine for deep learning in robotics

    Degrave, Jonas / Hermans, Michiel / Dambre, Joni et al. | BASE | 2019

    Freier Zugriff

    Differentiable Game Mechanics

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

    Freier Zugriff

    Stable Opponent Shaping in Differentiable Games

    Letcher, A / Foerster, J / Balduzzi, D et al. | BASE | 2019

    Freier Zugriff

    Interpretable Image Classification with Differentiable Prototypes Assignment

    Rymarczyk, Dawid / Struski, Łukasz / Górszczak, Michał et al. | British Library Conference Proceedings | 2022


    The Mechanics of n-Player Differentiable Games

    Balduzzi, D / Racaniere, S / Martens, J et al. | BASE | 2018

    Freier Zugriff