论文标题
Lagnetvip：视频预测的拉格朗日神经网络
LagNetViP: A Lagrangian Neural Network for Video Prediction
论文作者
论文摘要
视频预测的主要范例依赖于不透明的过渡模型，在这些模型中，运动方程和系统的基本物理量都不容易推断。牛顿第二定律定义的运动方程描述了物理系统状态的时间演变，因此可以应用于确定未来系统状态的时间。在本文中，我们介绍了一个视频预测模型，其中运动方程是从基础物理数量的学习表示的明确构造的。为了实现这一目标，我们同时学习了低维状态的表示和系统拉格朗日。拉格朗日的动力学和势能项是明显建模的，并且使用Euler-Lagrange方程明确构建了低维运动方程。我们证明了这种方法对在经过修改的Openai Gym Pendulum-V0和Acrobot环境中呈现的图像序列上的视频预测的功效。
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.
