# Machine Learning-Powered Vision for Robotic Inspection in Manufacturing: A Review

## TL;DR

This review explores how machine learning-powered vision systems are being used in manufacturing for robotic inspection, showing high accuracy but limited real-world deployment.

## Contribution

The paper provides a comprehensive review of ML-powered vision systems in manufacturing, highlighting technical viability and deployment challenges.

## Key findings

- ML-powered vision systems achieve over 95% accuracy in defect detection and classification.
- Most implementations are at the prototype or pilot stage due to deployment barriers.
- Common models used include CNNs, YOLO variants, and traditional ML vision models.

## Abstract

Machine learning (ML)-powered vision for robotic inspection has accelerated with smart manufacturing, enabling automated defect detection and classification and real-time process optimization. This review provides insight into the current landscape and state-of-the-art practices in smart manufacturing quality control (QC). More than 50 studies spanning across automotive, aerospace, assembly, and general manufacturing sectors demonstrate that ML-powered vision is technically viable for robotic inspection in manufacturing. The accuracy of defect detection and classification frequently exceeds 95%, with some vision systems achieving 98–100% accuracy in controlled environments. The vision systems use predominantly self-designed convolutional neural network (CNN) architectures, YOLO variants, or traditional ML vision models. However, 77% of implementations remain at the prototype or pilot scale, revealing systematic deployment barriers. A discussion is provided to address the specifics of the vision systems and the challenges that these technologies continue to face. Finally, recommendations for future directions in ML-powered vision for robotic inspection in manufacturing are provided.