Problem
Research questions and friction points this paper is trying to address.
Electromagnetic Digital Twin
Online Calibration
Material Conductivity
Initialization Sensitivity
Measurement Travel Cost
Demo: Vision-Language Model-Guided Online Calibration of an Electromagnetic Digital Twin
🤖 AI Summary
This study addresses the challenges of initialization sensitivity and high measurement path costs in online calibration for electromagnetic digital twins by proposing a vision-language model (VLM)-driven robotic autonomous calibration framework. The proposed method leverages VLMs to perform material prior mapping, thereby overcoming the limitations of random initialization, and designs a residual-based intelligent waypoint selection strategy to optimize signal acquisition paths. These components are integrated with gradient descent algorithms to efficiently invert conductivity parameters. Experimental evaluations conducted on a Unitree G1 robot and the NVIDIA Sionna platform demonstrate that the proposed approach achieves an extremely low normalized mean absolute error within a 20-meter travel distance, exhibiting significantly superior convergence efficiency compared to conventional random strategies.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Vision-Language Model
Electromagnetic Digital Twin
Online Calibration
Waypoint Planning
Material Conductivity
🔎 Similar Papers
No similar papers found.
