Saved in:
Bibliographic Details
Main Authors: Fu, Tairan, Santos-Martín, Francisco Javier, Conde, Javier, Reviriego, Pedro, Merino-Gómez, Elena
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22829
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917434195181568
author Fu, Tairan
Santos-Martín, Francisco Javier
Conde, Javier
Reviriego, Pedro
Merino-Gómez, Elena
author_facet Fu, Tairan
Santos-Martín, Francisco Javier
Conde, Javier
Reviriego, Pedro
Merino-Gómez, Elena
contents The digital transformation of industrial manufacturing increasingly relies on the ability of autonomous robots to interact with legacy infrastructure, particularly analog gauges. While Vision-Language Models (VLMs) have demonstrated potential in zero-shot instrument recognition, their deployment in measurement systems remains constrained by an inherent inability to accurately analyze high-frequency temporal events and needle vibrations. This paper evaluates state-of-the-art models, including GPT-5 and Gemini 3, against the strict requirements of metrology and uncertainty quantification. To facilitate this evaluation, we introduce a novel dataset comprising video sequences of various gauge types: circular, linear, and Vernier, under diverse motion speed profiles. Our findings indicate that current VLMs exhibit limited ability in interpreting needle trajectories and scale semantics, failing to provide the traceability and reliability needed for safety-critical monitoring. The results demonstrate that these models have not yet achieved the performance necessary to be classified as trustworthy synthetic instruments under existing IEEE and ISO standards.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22829
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Lost in the Vibrations: Vision Language Models Fail the Dynamic Gauges Test
Fu, Tairan
Santos-Martín, Francisco Javier
Conde, Javier
Reviriego, Pedro
Merino-Gómez, Elena
Computer Vision and Pattern Recognition
The digital transformation of industrial manufacturing increasingly relies on the ability of autonomous robots to interact with legacy infrastructure, particularly analog gauges. While Vision-Language Models (VLMs) have demonstrated potential in zero-shot instrument recognition, their deployment in measurement systems remains constrained by an inherent inability to accurately analyze high-frequency temporal events and needle vibrations. This paper evaluates state-of-the-art models, including GPT-5 and Gemini 3, against the strict requirements of metrology and uncertainty quantification. To facilitate this evaluation, we introduce a novel dataset comprising video sequences of various gauge types: circular, linear, and Vernier, under diverse motion speed profiles. Our findings indicate that current VLMs exhibit limited ability in interpreting needle trajectories and scale semantics, failing to provide the traceability and reliability needed for safety-critical monitoring. The results demonstrate that these models have not yet achieved the performance necessary to be classified as trustworthy synthetic instruments under existing IEEE and ISO standards.
title Lost in the Vibrations: Vision Language Models Fail the Dynamic Gauges Test
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.22829