Generalized Dynamics Generation towards Scannable Physical World Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yichen, Li, Zhiyi, Feng, Brandon, Zhang, Dinghuai, Torralba, Antonio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911216263233536
author Li, Yichen
Li, Zhiyi
Feng, Brandon
Zhang, Dinghuai
Torralba, Antonio
author_facet Li, Yichen
Li, Zhiyi
Feng, Brandon
Zhang, Dinghuai
Torralba, Antonio
contents Digital twin worlds with realistic interactive dynamics presents a new opportunity to develop generalist embodied agents in scannable environments with complex physical behaviors. To this end, we present GDGen (Generalized Representation for Generalized Dynamics Generation), a framework that takes a potential energy perspective to seamlessly integrate rigid body, articulated body, and soft body dynamics into a unified, geometry-agnostic system. GDGen operates from the governing principle that the potential energy for any stable physical system should be low. This fresh perspective allows us to treat the world as one holistic entity and infer underlying physical properties from simple motion observations. We extend classic elastodynamics by introducing directional stiffness to capture a broad spectrum of physical behaviors, covering soft elastic, articulated, and rigid body systems. We propose a specialized network to model the extended material property and employ a neural field to represent deformation in a geometry-agnostic manner. Extensive experiments demonstrate that GDGen robustly unifies diverse simulation paradigms, offering a versatile foundation for creating interactive virtual environments and training robotic agents in complex, dynamically rich scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15041
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalized Dynamics Generation towards Scannable Physical World Model
Li, Yichen
Li, Zhiyi
Feng, Brandon
Zhang, Dinghuai
Torralba, Antonio
Computer Vision and Pattern Recognition
Digital twin worlds with realistic interactive dynamics presents a new opportunity to develop generalist embodied agents in scannable environments with complex physical behaviors. To this end, we present GDGen (Generalized Representation for Generalized Dynamics Generation), a framework that takes a potential energy perspective to seamlessly integrate rigid body, articulated body, and soft body dynamics into a unified, geometry-agnostic system. GDGen operates from the governing principle that the potential energy for any stable physical system should be low. This fresh perspective allows us to treat the world as one holistic entity and infer underlying physical properties from simple motion observations. We extend classic elastodynamics by introducing directional stiffness to capture a broad spectrum of physical behaviors, covering soft elastic, articulated, and rigid body systems. We propose a specialized network to model the extended material property and employ a neural field to represent deformation in a geometry-agnostic manner. Extensive experiments demonstrate that GDGen robustly unifies diverse simulation paradigms, offering a versatile foundation for creating interactive virtual environments and training robotic agents in complex, dynamically rich scenarios.
title Generalized Dynamics Generation towards Scannable Physical World Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.15041