Data-driven Bayesian Control of Port-Hamiltonian Systems
Port-Hamiltonian theory is an established way to describe nonlinear physical systems widely used in various fields such as robotics, energy management, and mechanical engineering. This has led to considerable research interest in the control of Port-Hamiltonian systems, resulting in numerous model-based control techniques. However, the performance and stability of the closed-loop typically depend on the quality of the PH model, which is often difficult to obtain using first principles. We propose a Gaussian Processes (GP) based control approach for Port-Hamiltonian systems (GPC-PHS) by leveraging gathered data. The Bayesian characteristics of GPs enable the creation of a distribution encompassing all potential Hamiltonians instead of providing a singular point estimate. Using this uncertainty quantification, the proposed approach takes advantage of passivity-based robust control with interconnection and damping assignment to establish probabilistic stability guarantees.
Code (0)
등록된 구현이 없습니다.
Tasks
energy managementGaussian ProcessesManagementUncertainty QuantificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Gaussian Process Port-Hamiltonian Systems: Bayesian Learning with Physics Prior
Data-driven approaches achieve remarkable results for the modeling of complex dynamics based on collected data. However, these models often neglect basic physical principles which determine the behavior of any real-world…
Uncertainty QuantificationPhysics-informed Learning for Passivity-based Tracking Control
Passivity-based control ensures system stability by leveraging dissipative properties and is widely applied in electrical and mechanical systems. Port-Hamiltonian systems (PHS), in particular, are well-suited for interco…
Bayesian Safety Guarantees for Port-Hamiltonian Systems with Learned Energy Functions
Control barrier functions for port-Hamiltonian systems inherit model uncertainty when the Hamiltonian is learned from data. We show how to propagate this uncertainty into a safety filter with independently tunable credib…
Controlled oscillation modeling using port-Hamiltonian neural networks
Learning dynamical systems through purely data-driven methods is challenging as they do not learn the underlying conservation laws that enable them to correctly generalize. Existing port-Hamiltonian neural network method…
SymQNet: Amortized Acquisition for Low-Latency Adaptive Hamiltonian Learning
Adaptive Hamiltonian learning is central to calibrating and characterizing quantum devices. In an adaptive controller, choosing the next experiment is itself a computation. Bayesian design rules are recomputed after ever…
Active Learning