• Model: physics-based models of machines: multibody dynamics, flexible bodies, contacts, clearances, friction and hydraulics.
• Simulate: real-time simulation, hardware-in-the-loop testing and real-time fatigue assessment.
• Understand: physics-informed AI: virtual sensors, state estimation and remaining useful life. A model that runs in real time and is updated with measurements is a digital twin.
• Act: simulation-driven robotics: motion planning, control, reinforcement learning and sim-to-real transfer.

Safer, more autonomous, and more sustainable machinery.