arXiv：cs.AI· Kuixiang Shao, Chuansen Nie, Yinuo Bai, Jiayuan Gu, Jingyi Yu·· 13 小时前
FACT：面向铰接数字孪生的保真度感知构建框架
FACT: Fidelity-Aware Construction of Articulated Twins
AI 导读
FACT 是一个智能体框架，通过证据—诊断—修正循环在共享可编辑表示上逐步构建铰接数字孪生，以提升几何、接触与动力学保真度。它从图像重建可编辑铰接几何，经任务感知局部重划分修复碰撞代理后再做保真度约束压缩，并利用仿真残差从被动响应视频构建响应模型。实验显示其几何重建优于基线，能用更简单的碰撞代理实现更可靠交互，且比直接参数推断更好地复现留出的物理响应。
正文
Abstract:Visually plausible articulated assets may still fail during contact interactions or exhibit inaccurate motion. We present FACT (Fidelity-Aware Construction of Articulated Twins), an agentic framework that progressively constructs articulated twins to improve geometry, contact, and dynamic fidelity. The agent drives an evidence--diagnosis--revision loop on a shared editable representation, selecting measurements and model edits using quantitative feedback, while numerical tools execute and validate the updates. It reconstructs editable articulated geometry from images through feature planning, targeted measurements, and diagnostic refinement. On this reference, it repairs collision proxies through task-aware local repartitioning before fidelity-constrained compression. Finally, it constructs response models from passive-response videos, using simulation residuals to guide model revision and constrained physical parameter fitting. Experiments show that FACT improves geometric reconstruction over baselines, enables more reliable interaction with simpler collision proxies, and better reproduces held-out physical responses than direct parameter inference.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.37067 [cs.RO] |
| (or arXiv:2609.37067v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2609.37067 arXiv-issued DOI via DataCite |
Submission history
From: Kuixiang Shao [view email]
[v1]
Tue, 29 Sep 2026 09:04:34 UTC (3,042 KB)
[v2]
Fri, 9 Oct 2026 12:58:36 UTC (3,042 KB)
来源：arXiv：cs.AI · arxiv.org