用可微物理引擎模拟软体物体，实现高效精准的动态建模。
EMPM: Embodied MPM for Modeling and Simulation of Deformable Objects
- 基于可微材料点法（MPM）构建物理仿真框架，融合多视角视觉数据
- 通过最小化预测与观测视觉差异优化物理参数，实现在线自适应
- 适用于机器人抓取复杂软体物体，比弹簧质量模型更准确
在3D视觉、图形学和机器人操作中，如何以物理合理、通用且数据高效的方式建模连续体材料仍具挑战。现有方法常简化物体动力学或依赖大量训练数据，限制泛化能力。本文提出基于可微材料点法（MPM）的具身MPM（EMPM）框架，从多视角RGB-D视频重建几何与外观，并利用MPM物理引擎通过最小化预测与观测视觉数据的差异来模拟物体行为。进一步结合感官反馈在线优化MPM参数，实现自适应、鲁棒且物理感知的物体表征，为复杂软体物体的机器人操作开辟新可能。实验表明，EMPM优于弹簧-质量基线模型。
原文摘要 · Abstract (English)
Modeling deformable objects - especially continuum materials - in a way that is physically plausible, generalizable, and data-efficient remains challenging across 3D vision, graphics, and robotic manipulation. Many existing methods oversimplify the rich dynamics of deformable objects or require large training sets, which often limits generalization. We introduce embodied MPM (EMPM), a deformable object modeling and simulation framework built on a differentiable Material Point Method (MPM) simulator that captures the dynamics of challenging materials. From multi-view RGB-D videos, our approach reconstructs geometry and appearance, then uses an MPM physics engine to simulate object behavior by minimizing the mismatch between predicted and observed visual data. We further optimize MPM parameters online using sensory feedback, enabling adaptive, robust, and physics-aware object representations that open new possibilities for robotic manipulation of complex deformables. Experiments show that EMPM outperforms spring-mass baseline models. Project website: https://embodied-mpm.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。