arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.12467cs.LGcs.AIcs.CE
收藏

使用分层接触网格Transformer学习柔性体碰撞动力学

Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer

Yonsei University(延世大学);Arizona State University(亚利桑那州立大学);LG Display Co., Ltd.(LG显示公司);KAIST(韩国科学技术院)

Youn-Yeol Yu, Jeongwhan Choi, Woojin Cho, Kookjin Lee, Nayong Kim, Kiseok Chang, Chang-Seung Woo, Ilho Kim, Seok-Woo Lee, Joon-Young Yang, Sooyoung Yoon, Noseong Park

AI总结:

提出分层接触网格Transformer(HCMT),通过分层网格结构学习柔性体瞬时碰撞中的长距离依赖,快速传播碰撞效果,在柔性体动力学数据集上显著优于现有方法。

摘要:

最近,许多基于网格的图神经网络(GNN)模型被提出用于建模复杂的高维物理系统。与传统数值求解器相比,在显著减少求解时间方面取得了显著成就。这些方法通常旨在i)降低求解物理动力学的计算成本,和/或ii)提出技术以提高流体和刚体动力学中的求解精度。然而,它们在解决柔性体动力学挑战方面的有效性仍然探索不足,其中瞬时碰撞在非常短的时间范围内发生。在本文中,我们提出了分层接触网格Transformer(HCMT),它使用分层网格结构,并且能够学习物体空间相距较远位置之间(由碰撞产生的)长距离依赖关系——较高层网格中两个相近的位置对应于较低层网格中两个较远的位置。HCMT实现了长距离交互,并且分层网格结构将碰撞效果快速传播到远处位置。为此,它由接触网格Transformer和分层网格Transformer(分别为CMT和HMT)组成。最后,我们提出了一个柔性体动力学数据集,包含反映显示行业产品设计中经常使用的实验设置的轨迹。我们还使用众所周知的基准数据集比较了几种基线的性能。我们的结果表明,HCMT相对于现有方法提供了显著的性能改进。我们的代码可在 https://github.com/yuyudeep/hcmt 获取。

英文摘要:

Recently, many mesh-based graph neural network (GNN) models have been proposed for modeling complex high-dimensional physical systems. Remarkable achievements have been made in significantly reducing the solving time compared to traditional numerical solvers. These methods are typically designed to i) reduce the computational cost in solving physical dynamics and/or ii) propose techniques to enhance the solution accuracy in fluid and rigid body dynamics. However, it remains under-explored whether they are effective in addressing the challenges of flexible body dynamics, where instantaneous collisions occur within a very short timeframe. In this paper, we present Hierarchical Contact Mesh Transformer (HCMT), which uses hierarchical mesh structures and can learn long-range dependencies (occurred by collisions) among spatially distant positions of a body -- two close positions in a higher-level mesh correspond to two distant positions in a lower-level mesh. HCMT enables long-range interactions, and the hierarchical mesh structure quickly propagates collision effects to faraway positions. To this end, it consists of a contact mesh Transformer and a hierarchical mesh Transformer (CMT and HMT, respectively). Lastly, we propose a flexible body dynamics dataset, consisting of trajectories that reflect experimental settings frequently used in the display industry for product designs. We also compare the performance of several baselines using well-known benchmark datasets. Our results show that HCMT provides significant performance improvements over existing methods. Our code is available at https://github.com/yuyudeep/hcmt.

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。

↑