Volkswagen Group Automates Sign Inspection Workflow Using AWS

During vehicle production, Volkswagen Group brands must apply 25 different labels that contain country-specific safety, usability, and specification data—with over 2,000 variants. Any damaged, incorrect, or missing labels could pose regulatory issues. Furthermore, errors can occur during the inspection process, as employees are not always able to read the labels to confirm accuracy.

To automate this process, Volkswagen brand Porsche developed an intelligent Sign Inspection (iSI) solution on Amazon Web Services (AWS). This solution is powered by the Digital Production Platform (DPP), a cloud-based industrial platform built by the Volkswagen Group and AWS to enable the development of scalable use cases across the company and transform its manufacturing and logistics processes. The DPP will also serve as the foundation for the Industrial Cloud—an open platform, community, and marketplace of digital solutions available to the automotive manufacturing industry.

Volkswagen follows stringent quality control processes to ensure each vehicle label is correct and undamaged. However, plants produce vehicles sold globally, so workers must handle labels written in several languages. To reach its goal of zero label defects, Porsche developed an automated sign inspection solution. “iSI helps workers reduce control task complexity and helps Porsche further increase vehicle quality,” says Thomas Reichert, product owner of artificial intelligence–based computer vision at Porsche.

The iSI solution relies on Volkswagen’s DPP, which advances the use of Internet of Things (IoT) solutions to innovate supply chains. The DPP is powered by AWS IoT Core, which enables developers to connect IoT devices to the cloud without the need to provision or manage servers. “We benefit from the DPP Connect team, which provides standardized IoT solutions for our plant floor equipment,” explains Winfried Oberkersch, product owner of artificial intelligence–based computer vision at Porsche. For example, Volkswagen’s Industrial Computer Vision (ICV) Camera Service uses AWS IoT Core to connect cameras in the factory network to the cloud.

Porsche uses iSI to automatically inspect labels on the plant floor with IoT-enabled devices and to perform manual inspections using a mobile app. In the assembly line, automated cameras photograph labels and send them to the cloud for analysis. If an issue is detected, the system notifies an in-line worker, who takes the vehicle to a quality check station for manual inspection.

During manual inspection, workers photograph individual labels using the iSI app. Using Amazon Textract—a fully managed machine learning service that automatically extracts printed text, handwriting, and other data from scanned documents—the iSI app compares text on labels to data stored in Volkswagen’s ICV Inference Service to identify anomalies. The results are translated and displayed to the worker, who can take appropriate action to fix detected errors.

By using AWS services to build iSI, Volkswagen is closer to reaching its zero-defects goal. In the future, the Group wants to expand the solution to all its global plants. “Our iSI use case is only the first of many more to follow,” says Oberkersch. “With our modular approach and standardized services, we can bring the iSI solution to other Volkswagen Group brands and use ICV functionalities to implement more use cases for all production logistics.”