Anomaly Detection on Small Industrial Components via Vision-Based Tactile Sensing
2026-08-31 • Robotics
Robotics
AI summaryⓘ
The authors studied how to use tactile sensors, which take detailed pictures of small objects by touch, to find defects in tiny industrial parts. They tested different methods to spot anomalies without needing examples of defects, using a robot with a special sensor called GelSight Mini. Their experiments checked how many good contacts are needed for reliable detection, how well the methods work when sensing different spots, and the effect of sensor resolution on accuracy. The authors provide useful advice for using touch-based sensing in factory quality control.
Vision-based tactile sensingAnomaly detectionGelSight sensorDeep learningFeature embeddingIndustrial inspectionUnsupervised learningSurface geometryCollaborative robotSensor resolution
Authors
G. F. Preziosa, M. Casiglia, M. Faroni, A. M. Zanchettin, P. Rocco
Abstract
Automated inspection of small industrial components, including sub-centimetre-scale parts where defects are geometry-driven and poorly resolved by standard optical cameras, calls for sensing modalities that can directly capture fine surface geometry. Vision-based tactile sensors address this need by converting contact imprints into high-resolution image-like data compatible with existing deep-learning pipelines, yet their effective use for industrial anomaly detection (AD) remains largely unexplored. This work systematically evaluates unsupervised AD methods on a real tactile dataset covering five genuine industrial components acquired with a GelSight Mini sensor mounted on a collaborative robot. Four feature-embedding methods, SPADE, PaDiM, FAPM, and InReaCh, are compared under three validations explicitly motivated by the deployment constraints of contact-based sensing: a Good Fraction analysis establishing the minimum number of nominal contacts for stable performance, directly bounded by gel wear since every acquisition degrades the soft interface; a cross-position evaluation assessing generalization across different contact locations observing the same recurring surface pattern; and a low- versus high-resolution comparison evaluating the cost-benefit of higher-resolution tactile acquisition. Overall, this systematic benchmarking study provides practical guidance for researchers and practitioners adopting vision-based tactile sensing for industrial AD and shows how this modality can serve as a viable alternative for industrial quality-control tasks.