← Back to all news
arXiv Machine Learning By E. Javier Olucha, Amritam Das, Roland T\'oth

Learning Surrogate LPV State-Space Models with Uncertainty Quantification

Read the original on arXiv Machine Learning →

The paper introduces a Bayesian method for jointly estimating Linear Parameter-Varying (LPV) state-space models and their scheduling maps from input-output data, while explicitly quantifying both aleatoric and epistemic uncertainties. This approach preserves the LPV structure necessary for controller synthesis and provides confidence bounds on predicted responses, enabling efficient simulation and uncertainty propagation. The method is illustrated on a surrogate model of a two-dimensional nonlinear mass‑spring‑damper system.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 6

A Systematic Review and Taxonomy of Reinforcement Learning-Model Predictive Control Integration for Linear Systems

arXiv:2604. 21030v2 Announce Type: replace-cross Abstract: The integration of Model Predictive Control (MPC) and Reinforcement Learning (RL) has emerged as a promising paradigm for constrained decision-making and adaptive control.

By Mohsen Jalaeian Farimani, Roya Khalili Amirabadi, Davoud Nikkhouy, Malihe Abdolbaghi, Mahshad Rastegarmoghaddam, Shima Samadzadeh, Mahdi Ghane
reinforcement-learning
More like this →
arXiv Machine Learning
Sep 10

A robust and adaptive MPC formulation for Gaussian process models

The paper introduces a robust and adaptive model predictive control framework for uncertain nonlinear systems with bounded disturbances and unmodeled nonlinearities, leveraging Gaussian Processes to learn dynamics from noisy measurements. It derives robust predictions for GP models using contraction metrics, integrating them into the MPC formulation to ensure recursive feasibility, robust constraint satisfaction, and convergence to a reference state with high probability. A numerical example involving a planar quadrotor experiencing challenging ground effects demonstrates significant performance gains from the robust prediction method and online learning.

By Mathieu Dubied, Amon Lahr, Melanie N. Zeilinger, Johannes K\"ohler
More like this →