Speaker
Description
Reliable models of dynamical systems are essential for tasks such as state estimation, prediction, and the implementation of safe control strategies. However, developing first-principles models for nonlinear systems is often time-consuming and requires significant expert knowledge. While machine learning offers an alternative, learned models frequently lack trustworthiness, generalizability, and physical consistency, making them ill-suited for safety-critical applications.
In this talk, I will present our recent work on data-driven port-Hamiltonian systems (PHS) for compositional and physically consistent modeling of complex dynamics, including ODE and PDE systems. We leverage machine learning methods with built-in uncertainty quantification to learn unknown Hamiltonian functions directly from data. Unlike many physics-informed learning approaches that enforce physical constraints through penalty terms, our models are physically consistent by design. This structure naturally supports composability: physical consistency is preserved under interconnection. Finally, I will discuss how data-driven port-Hamiltonian systems enable robust and safe learning-based control, making them a promising foundation for trustworthy and scalable modeling of physical systems.