Co-Learning Port-Hamiltonian Systems and Optimal Energy-Shaping Control
For control engineers, this provides a data-driven method to learn stable, interpretable controllers for port-Hamiltonian systems without requiring a known model.
The paper develops a physics-informed learning framework that co-learns a port-Hamiltonian system model and an optimal energy-shaping controller from trajectory data, achieving provably stable and passive control. Validation on pendulum tasks shows effective state regulation and swing-up.
We develop a physics-informed learning framework for energy-shaping control of port-Hamiltonian (pH) systems from trajectory data. The proposed approach {co-learns} a pH system model and an optimal energy-balancing passivity-based controller (EB-PBC) through alternating optimization with policy-aware data collection. At each iteration, the system model is refined using trajectory data collected under the current control policy, and the controller is re-optimized on the updated model. Both components are parameterized by neural networks that embed the pH {dynamics} and EB-PBC structure, ensuring interpretability in terms of energy {interactions}. The learned controller renders the closed-loop system inherently passive and provably stable, and exploits passive plant dynamics without canceling the natural potential. A dissipation regularization enforces strict energy decay during training, thereby enhancing robustness to sim-to-real gaps. The proposed framework is validated on state-regulation and swing-up tasks for planar and torsional pendulum systems.