Antares and Oròbix unveil AI-Go visual control tool for pharma and manufacturing

Track & Trace provider Antares Vision Group has partnered with AI specialist Oròbix to develop the AI-Go platform, which delivers visual inspection quality control for the pharmaceutical and manufacturing packaging sectors.

AI-Go’s analytical capabilities enable companies to detect complex anomalies in packaging, such as chromatic impurities, glass fragments, cosmetic defects, or foreign bodies, leading to a “drastic reduction” in false scrap and a “measurable improvement” in production quality.

Antares says the AI solution addresses the growing demand in the pharmaceutical and manufacturing industries for “faster, more accurate, and more adaptable processes to enhance quality, efficiency, and competitiveness.”

Gianluca Mazzantini, CEO at Antares Vision Group, comments: “AI has become a fundamental strategic lever for industrial competitiveness: integrated in a secure, transparent, and validatable way, it enables us to offer our customers better-performing inspection machines, able to improve product quality, reduce scrap, and increase production efficiency.”

Pietro Rota, CEO at Oròbix, adds: “AI applied to visual inspection represents a turning point for the manufacturing industry. With solutions like AI-Go, we are bringing intelligence to production processes able to understand real data and dynamically adapt itself to the variability frequently seen in production.”

“At Oròbix, we are working to make AI a real ally of quality and of industrial production.”

AI visual inspection

AI-Go is said to create classification, segmentation, and optical character recognition models in a short timeframe, using a limited number of examples and requiring no specialist skills.

The platform incorporates deep learning technologies that allow models to be dynamically adapted to different formats and products, helping to reduce set-up time while enhancing flexibility and operational efficiency on production lines.

AI-Go has two integrated components: the AI-Go Studio cloud environment, which collects images and trains the models, and the AI-Go Runtime edge module, which autonomously executes the models directly on production lines, even offline.

According to Antares, the platform enhances operational robustness and deployment, even in complex industrial settings.

Vision Language Models

Packaging industry experts have highlighted AI as key to advancements in automation and connected packaging.

Antares adds that AI-Go is also looking ahead toward the integration of Vision Language Models (VLM), “which represent the next game-changer in industrial visual inspection.”

Luca Antiga, chief technology officer at Oròbix, says: “VLMs are innovative models that combine the understanding of images and language, enabling complex tasks to be performed through simple instructions in natural language.”

“We are working on rendering AI-Go increasingly intuitive and powerful: the native integration of VLMs will enable quality controls to be set up faster and in a more accessible way, even without technical skills.”