arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.12077cs.LGcs.SYeess.SYphysics.comp-phstat.ML
收藏

Symplectic ODE-Net:学习带控制的哈密顿动力学

Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control

Princeton University(普林斯顿大学);Siemens Corporation, Corporate Technology(西门子公司企业技术部)

Yaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty

AI总结:

提出 SymODEN 深度学习框架,将带控制的哈密顿动力学作为物理归纳偏置,从状态轨迹学习可解释、物理一致的系统模型,以提升少样本泛化并支持基于模型的控制。

摘要:

在本文中,我们介绍了 Symplectic ODE-Net(SymODEN),这是一个深度学习框架,能够从观测到的状态轨迹中推断由常微分方程(ODE)给出的物理系统动力学。为了用更少的训练样本实现更好的泛化,SymODEN 通过以物理信息驱动的方式设计相关计算图,融入了适当的归纳偏置。具体而言,我们强制模型学习带控制的哈密顿动力学,以透明的方式学习底层动力学,随后可利用这些动力学获得对系统相关物理方面的洞见,例如质量和势能。此外,我们提出了一种参数化方法,即使广义坐标数据嵌入在高维空间中,或者我们只能获得速度数据而无法获得广义动量,该方法也能够强制满足这种哈密顿形式体系。该框架通过为物理系统提供可解释且物理一致的模型,为综合基于模型的控制策略开辟了新的可能性。

英文摘要:

In this paper, we introduce Symplectic ODE-Net (SymODEN), a deep learning framework which can infer the dynamics of a physical system, given by an ordinary differential equation (ODE), from observed state trajectories. To achieve better generalization with fewer training samples, SymODEN incorporates appropriate inductive bias by designing the associated computation graph in a physics-informed manner. In particular, we enforce Hamiltonian dynamics with control to learn the underlying dynamics in a transparent way, which can then be leveraged to draw insight about relevant physical aspects of the system, such as mass and potential energy. In addition, we propose a parametrization which can enforce this Hamiltonian formalism even when the generalized coordinate data is embedded in a high-dimensional space or we can only access velocity data instead of generalized momentum. This framework, by offering interpretable, physically-consistent models for physical systems, opens up new possibilities for synthesizing model-based control strategies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑