LagNetViP: A Lagrangian Neural Network for Video Prediction

The dominant paradigms for video prediction rely on opaque transition models where neither the equations of motion nor the underlying physical quantities of the system are easily inferred. The equations of motion, as defined by Newton's second law, describe the time evolution of a physical syst...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-10
Main Authors: Allen-Blanchette, Christine, Veer, Sushant, Majumdar, Anirudha, Naomi Ehrich Leonard
Format: Article
Language:English
Subjects:
Equations of motion
Euler-Lagrange equation
Mathematical models
Neural networks
Pendulums
Potential energy
Prediction models
Representations
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The dominant paradigms for video prediction rely on opaque transition models where neither the equations of motion nor the underlying physical quantities of the system are easily inferred. The equations of motion, as defined by Newton's second law, describe the time evolution of a physical system state and can therefore be applied toward the determination of future system states. In this paper, we introduce a video prediction model where the equations of motion are explicitly constructed from learned representations of the underlying physical quantities. To achieve this, we simultaneously learn a low-dimensional state representation and system Lagrangian. The kinetic and potential energy terms of the Lagrangian are distinctly modelled and the low-dimensional equations of motion are explicitly constructed using the Euler-Lagrange equations. We demonstrate the efficacy of this approach for video prediction on image sequences rendered in modified OpenAI gym Pendulum-v0 and Acrobot environments.
ISSN:2331-8422