This project addresses the challenges in coordinating distributed and modular systems within evolving industrial landscapes. Our research explores the shift from monolithic to spatially distributed factories, aligning with environmental goals. The project's innovative approach involves developing collaborative self-learning agents for effective communication within human-machine and machine-machine interactions. By focusing on behavioral model inference and distributed optimization methods, we aim to contribute to the development of conscious agents capable of adapting to ever-changing common goals in industrial settings. We also address human-machine collaboration and integrate an IT-equipped human into the system as an agent that is capable of interacting with the system through dynamically generated user interfaces tuned for individual learning rates and current system goals.

2024

2028