Iterative solvers are widely used to accurately simulate physical systems. These solvers require initial guesses to generate a sequence of improving approximate solutions. In this contribution, we introduce a novel method to accelerate iterative solvers for rod dynamics with graph networks (GNs) by predicting the initial guesses to reduce the number of iterations. Unlike existing methods that aim to learn physical systems in an end-to-end manner, our approach guarantees long-term stability and therefore leads to more accurate solutions. Furthermore, our method improves the run time performance of traditional iterative solvers for rod dynamics. To explore our method we make use of position-based dynamics (PBD) as a common solver for physical systems and evaluate it by simulating the dynamics of elastic rods. Our approach is able to generalize across different initial conditions, discretizations, and realistic material properties. We demonstrate that it also performs well when taking discontinuous effects into account such as collisions between individual rods. Finally, to illustrate the scalability of our approach, we simulate complex 3D tree models composed of over a thousand individual branch segments swaying in wind fields.
|Original language||English (US)|
|Title of host publication||35th Conference on Neural Information Processing Systems, NeurIPS 2021|
|Publisher||Neural information processing systems foundation|
|Number of pages||14|
|State||Published - Jan 1 2021|
Bibliographical noteKAUST Repository Item: Exported on 2022-06-20
Acknowledgements: This work was supported and funded by KAUST through the baseline funding of the Computational Sciences Group and a Center Partnership Fund of the Visual Computing Center. The valuable comments of the anonymous reviewers that improved the manuscript are gratefully acknowledged.