Latent-space Dynamics for Reduced Deformable Simulation

Fulton, Lawson; Modi, Vismay; Duvenaud, David; Levin, David I. W.; Jacobson, Alec

Latent-space Dynamics for Reduced Deformable Simulation

Files

v38i2pp379-391.pdf (20.77 MB)

main_final-handbrake.mp4 (18.61 MB)

Date

2019

Authors

Fulton, Lawson
Modi, Vismay
Duvenaud, David
Levin, David I. W.
Jacobson, Alec

Publisher

The Eurographics Association and John Wiley & Sons Ltd.

Abstract

We propose the first reduced model simulation framework for deformable solid dynamics using autoencoder neural networks. We provide a data-driven approach to generating nonlinear reduced spaces for deformation dynamics. In contrast to previous methods using machine learning which accelerate simulation by approximating the time-stepping function, we solve the true equations of motion in the latent-space using a variational formulation of implicit integration. Our approach produces drastically smaller reduced spaces than conventional linear model reduction, improving performance and robustness. Furthermore, our method works well with existing force-approximation cubature methods.

        @article{10.1111:cgf.13645
,
journal = {Computer Graphics Forum},
title = {{Latent-space Dynamics for Reduced Deformable Simulation
}},
author = {Fulton, Lawson and 
Modi, Vismay and 
Duvenaud, David and 
Levin, David I. W. and 
Jacobson, Alec
},
year = {2019
},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.13645
}
}