arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.15083cs.LGcs.CE
收藏

神经模块物理学用于弹性模拟

Neural Modular Physics for Elastic Simulation

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);Shanghai University(上海大学);Meta Reality Labs(Meta现实实验室)

Yifei Li, Haixu Wu, Zeyi Xu, Tuur Stuyck, Wojciech Matusik

AI总结:

本文提出神经模块物理学用于弹性模拟,结合神经网络的近似能力与传统模拟器的物理可靠性,实现更优的物理一致性和通用性。

摘要:

基于学习的方法在物理模拟中取得了显著进展,通常通过端到端优化的神经网络近似动力学。尽管这些模型提供了一种有效的模拟方法,但可能在传统数值模拟器中失去本质特征,如物理可解释性和可靠性。受经典模拟器模块化操作的启发,本文提出了用于弹性模拟的神经模块物理学(NMP),将神经网络的近似能力与传统模拟器的物理可靠性相结合。在以往的单体学习范式之外,NMP通过将弹性动力学分解为具有物理意义的神经模块,并通过中间物理量连接这些模块,实现了对中间量和物理约束的直接监督。通过专门的架构和训练策略,我们的方法将数值计算流程转化为模块化的神经模拟器,实现了改进的物理一致性和通用性。实验表明,NMP在未见的初始条件和分辨率下表现出更优的泛化能力,具有稳定的长周期模拟性能,比其他神经模拟器更好地保持物理特性,并在未知底层动力学的场景中比传统模拟器更具可行性。

英文摘要:

Learning-based methods have made significant progress in physics simulation, typically approximating dynamics with a monolithic end-to-end optimized neural network. Although these models offer an effective way to simulation, they may lose essential features compared to traditional numerical simulators, such as physical interpretability and reliability. Drawing inspiration from classical simulators that operate in a modular fashion, this paper presents Neural Modular Physics (NMP) for elastic simulation, which combines the approximation capacity of neural networks with the physical reliability of traditional simulators. Beyond the previous monolithic learning paradigm, NMP enables direct supervision of intermediate quantities and physical constraints by decomposing elastic dynamics into physically meaningful neural modules connected through intermediate physical quantities. With a specialized architecture and training strategy, our method transforms the numerical computation flow into a modular neural simulator, achieving improved physical consistency and generalizability. Experimentally, NMP demonstrates superior generalization to unseen initial conditions and resolutions, stable long-horizon simulation, better preservation of physical properties compared to other neural simulators, and greater feasibility in scenarios with unknown underlying dynamics than traditional simulators.

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。

↑