EMPM: Embodied MPM for Modeling and Simulation of Deformable Objects

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Yunuo, Hu, Yafei, Sun, Lingfeng, Kusnur, Tushar, Herlant, Laura, Jiang, Chenfanfu
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908785498390528
author Chen, Yunuo
Hu, Yafei
Sun, Lingfeng
Kusnur, Tushar
Herlant, Laura
Jiang, Chenfanfu
author_facet Chen, Yunuo
Hu, Yafei
Sun, Lingfeng
Kusnur, Tushar
Herlant, Laura
Jiang, Chenfanfu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17251
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EMPM: Embodied MPM for Modeling and Simulation of Deformable Objects
Chen, Yunuo
Hu, Yafei
Sun, Lingfeng
Kusnur, Tushar
Herlant, Laura
Jiang, Chenfanfu
Robotics
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.
title EMPM: Embodied MPM for Modeling and Simulation of Deformable Objects
topic Robotics
url https://arxiv.org/abs/2601.17251