Session 4 – 22 June

The Asimov project: AI training using simulated instruments for machine optimization and verification

16:00 – 16:30

With the rise of high-tech cyber-physical systems (CPSs) in all areas of industry and society, the user-friendliness and uptimes of these systems become increasingly important. Especially keeping the control parameters of CPSs in their correct operating window is a big challenge, for example in electron microscopy, unmanned utility vehicles and pulp & paper process control. The Asimov project will increase the autonomy and self-optimization of CPSs by creating physically realistic digital twins of these systems and training innovative AI algorithms for CPS control using these digital twins. This talk introduces the project and the main use cases of the European consortium partners and discusses the challenges we are going to face and, hopefully, resolve regarding digital twin-based AI training.

Remco Schoenmakers holds a PhD in astrophysics from the University of Groningen. After a short stint at Philips Medical Systems, he has spent the last 20 years at FEI (now Thermo Fisher Scientific), developing software for 3D image analysis and big data & cloud computing solutions for electron microscopy. Currently, he’s Director Digital Science of the Advanced Technology (research) department, where he’s responsible for the long-term digital strategy, including artificial intelligence and machine learning, and chairman of the Center of Excellence on AI for Thermo Fisher Scientific worldwide.

Remco Schoenmakers

Director digital science technologies at Thermo Fisher Scientific