arXiv cs.AI· Zerui Kang, Yishen Lim, Zhouyou Gu, Seungnyun Kim, Seung-Woo Ko, Tony Q. S. Quek, Jihong Park·· 10 天前AI 评分18
VLM 引导的电磁数字孪生在线校准演示：基于 Unitree G1 与 NVIDIA Sionna
Demo: Vision-Language Model-Guided Online Calibration of an Electromagnetic Digital Twin
AI 导读
一个由视觉语言模型（VLM）引导的电磁数字孪生在线校准框架，在 Unitree G1 机器人和 NVIDIA Sionna 上演示，通过两次 VLM 调用完成材质分类与路径点规划。在真实室内场景中，该框架在 20 米行程内实现归一化平均绝对电导率误差 1.74×10⁻⁴，随机初始化无法收敛，随机路径点则需两倍以上行程。
正文 · 原文
Abstract:An electromagnetic (EM) digital twin gives mobile robots wireless situational awareness but depends on material conductivities that change with the environment. Online calibration faces initialization sensitivity and measurement travel costs. We demonstrate a vision-language model (VLM)-guided framework using a Unitree G1 robot and NVIDIA Sionna, with two VLM calls: material classification maps visible materials through ITU-R P.2040 to conductivity priors for Sionna's gradient descent on accumulated received signal strength (RSS) measurements; waypoint planning selects the next measurement location online using residual RSS calibration error and image coverage. In a real indoor scenario, the framework achieves a normalized mean absolute conductivity error of $1.74\times10^{-4}$ within 20 m of travel; random initialization never converges, while random waypoints require over twice the travel.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.07081 [cs.RO] |
| (or arXiv:2610.07081v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07081 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1145/3842721.3850098
DOI(s) linking to related resources |
Submission history
From: Zerui Kang [view email]
[v1]
Mon, 5 Oct 2026 11:15:49 UTC (1,326 KB)
[v2]
Wed, 7 Oct 2026 05:08:16 UTC (1,326 KB)
来源：arXiv cs.AI · arxiv.org