PulseAugur
EN
LIVE 12:46:52

New method uses Koopman operator regression for nonlinear system control

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a method for controlling nonlinear systems using Koopman operator regression within a reproducing kernel Hilbert space. This approach estimates unknown dynamics from finite samples, resulting in a linear switching predictive model where control variables dictate the switches. The learned dynamics are then applied to an infinite-horizon optimal control problem solved via model predictive control. The work includes theoretical analysis of learning rates and sub-optimality, supported by numerical simulations on the Duffing oscillator. AI

IMPACT This research could advance control theory applications in robotics and autonomous systems by enabling more precise management of complex nonlinear dynamics.

RANK_REASON The cluster contains an academic paper detailing a new method for controlling nonlinear systems.

Read on arXiv stat.ML →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New method uses Koopman operator regression for nonlinear system control

COVERAGE [2]

  1. arXiv stat.ML TIER_1 English(EN) · Edoardo Caldarelli, Oleksii Kachaiev, Cesare Molinari, Lorenzo Rosasco ·

    Learning to control switching nonlinear systems with Koopman operator regression

    arXiv:2607.11344v1 Announce Type: cross Abstract: In this work, we consider the identification and control of nonlinear systems with finite action spaces. The unknown dynamics are estimated from finite samples with Koopman operator regression in a reproducing kernel Hilbert space…

  2. arXiv stat.ML TIER_1 English(EN) · Lorenzo Rosasco ·

    Learning to control switching nonlinear systems with Koopman operator regression

    In this work, we consider the identification and control of nonlinear systems with finite action spaces. The unknown dynamics are estimated from finite samples with Koopman operator regression in a reproducing kernel Hilbert space, yielding a linear switching predictive model, th…

RELATED ENTITIES

RELATED TOPICS