Plug-and-Play Physics-informed Learning using Uncertainty Quantified Port-Hamiltonian Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Tan, Kaiyuan, Li, Peilun, Wang, Jun, Beckers, Thomas
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913807435038720
author Tan, Kaiyuan
Li, Peilun
Wang, Jun
Beckers, Thomas
author_facet Tan, Kaiyuan
Li, Peilun
Wang, Jun
Beckers, Thomas
contents The ability to predict trajectories of surrounding agents and obstacles is a crucial component in many robotic applications. Data-driven approaches are commonly adopted for state prediction in scenarios where the underlying dynamics are unknown. However, the performance, reliability, and uncertainty of data-driven predictors become compromised when encountering out-of-distribution observations relative to the training data. In this paper, we introduce a Plug-and-Play Physics-Informed Machine Learning (PnP-PIML) framework to address this challenge. Our method employs conformal prediction to identify outlier dynamics and, in that case, switches from a nominal predictor to a physics-consistent model, namely distributed Port-Hamiltonian systems (dPHS). We leverage Gaussian processes to model the energy function of the dPHS, enabling not only the learning of system dynamics but also the quantification of predictive uncertainty through its Bayesian nature. In this way, the proposed framework produces reliable physics-informed predictions even for the out-of-distribution scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17966
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Plug-and-Play Physics-informed Learning using Uncertainty Quantified Port-Hamiltonian Models
Tan, Kaiyuan
Li, Peilun
Wang, Jun
Beckers, Thomas
Robotics
Machine Learning
The ability to predict trajectories of surrounding agents and obstacles is a crucial component in many robotic applications. Data-driven approaches are commonly adopted for state prediction in scenarios where the underlying dynamics are unknown. However, the performance, reliability, and uncertainty of data-driven predictors become compromised when encountering out-of-distribution observations relative to the training data. In this paper, we introduce a Plug-and-Play Physics-Informed Machine Learning (PnP-PIML) framework to address this challenge. Our method employs conformal prediction to identify outlier dynamics and, in that case, switches from a nominal predictor to a physics-consistent model, namely distributed Port-Hamiltonian systems (dPHS). We leverage Gaussian processes to model the energy function of the dPHS, enabling not only the learning of system dynamics but also the quantification of predictive uncertainty through its Bayesian nature. In this way, the proposed framework produces reliable physics-informed predictions even for the out-of-distribution scenarios.
title Plug-and-Play Physics-informed Learning using Uncertainty Quantified Port-Hamiltonian Models
topic Robotics
Machine Learning
url https://arxiv.org/abs/2504.17966