COALA – COgnitive Assisted agile manufacturing for a LAbor force supported by trustworthy Artificial Intelligence

Human beings are at the center of knowledge-intensive manufacturing processes. They must be qualified and flexible to meet the requirements of their working environment. Training new workers in these processes is time-consuming and costly for companies. Industries such as Italian textile sector are suffering from shortage of skilled workers caused, for example, by demographic change. A second challenge for the manufacturing sector is constant competition of high-quality products. COALA will address both challenges through innovative design and development of a voice-controlled digital intelligent assistant for manufacturing sector.

The COALA solution will be based on privacy-focused open assistant Mycroft. It integrates prescriptive quality analysis, an AI system to support on-the-job training of new employees, and a novel explanatory engine - the WHY engine. Key components for the implementation of solution are a new didactic concept to inform employees about opportunities, challenges and risks in collaboration between humans and AI, as well as a simultaneous change management process. Three use cases (textile, white goods, liquid packaging) will evaluate results in common manufacturing processes with significant economic relevance. COALA will contribute its results to the European AI community, e.g. via the AI4EU platform, and in addition it will engage Digital Innovation Hubs to replicate its demonstrators for Europe's first trusted digital assistant for manufacturing industry. It is estimated that manufacturing defect costs can be reduced by 30-60% through prescriptive quality analysis and workforce training. The expected impact of transition is a 15% to 30% reduction in time resources for process-related education and training.