Abstract: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.
| Subjects: | Systems and Control (eess.SY); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Optimization and Control (math.OC); Machine Learning (stat.ML) |
| Cite as: | arXiv:2604.26172 [eess.SY] |
| (or arXiv:2604.26172v1 [eess.SY] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26172 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ankur Kamboj [view email]
[v1]
Tue, 28 Apr 2026 23:27:10 UTC (10,991 KB)
