DeepAI AI Chat
Log In Sign Up

LagNetViP: A Lagrangian Neural Network for Video Prediction

by   Christine Allen-Blanchette, et al.
Princeton University

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.


page 4

page 5


Discovering interpretable Lagrangian of dynamical systems from data

A complete understanding of physical systems requires models that are ac...

Discrete Lagrangian Neural Networks with Automatic Symmetry Discovery

By one of the most fundamental principles in physics, a dynamical system...

Neural Physicist: Learning Physical Dynamics from Image Sequences

We present a novel architecture named Neural Physicist (NeurPhy) to lear...

A Characteristic Mapping Method for the three-dimensional incompressible Euler equations

We propose an efficient semi-Lagrangian Characteristic Mapping (CM) meth...

Learning Interpretable Dynamics from Images of a Freely Rotating 3D Rigid Body

In many real-world settings, image observations of freely rotating 3D ri...

Symbolic Pregression: Discovering Physical Laws from Raw Distorted Video

We present a method for unsupervised learning of equations of motion for...