Saved in:
Bibliographic Details
Main Authors: Sakib, Shahriar Akbar, Pan, Shaowu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.06607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912547626549248
author Sakib, Shahriar Akbar
Pan, Shaowu
author_facet Sakib, Shahriar Akbar
Pan, Shaowu
contents We propose a noise-robust learning framework for the Koopman operator of nonlinear dynamical systems, with guaranteed long-term stability and improved model performance for better model-based predictive control tasks. Unlike some existing approaches that rely on ad hoc observables or black-box neural networks in extended dynamic mode decomposition (EDMD), our framework leverages observables generated by the system dynamics, when the system dynamics is known, through a Hankel matrix, which shares similarities with discrete Polyflow. When system dynamics is unknown, we approximate them with a neural network while maintaining structural similarities to discrete Polyflow. To enhance noise robustness and ensure long-term stability, we developed a stable parameterization of the Koopman operator, along with a progressive learning strategy for rollout loss. To further improve the performance of the model in the phase space, a simple iterative data augmentation strategy was developed. Numerical experiments of prediction and control of classic nonlinear systems with ablation study showed the effectiveness of the proposed techniques over several state-of-the-art practices.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06607
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Noise-Robust Stable Koopman Operator for Control with Hankel DMD
Sakib, Shahriar Akbar
Pan, Shaowu
Dynamical Systems
Machine Learning
37N35, 93B45
J.2
We propose a noise-robust learning framework for the Koopman operator of nonlinear dynamical systems, with guaranteed long-term stability and improved model performance for better model-based predictive control tasks. Unlike some existing approaches that rely on ad hoc observables or black-box neural networks in extended dynamic mode decomposition (EDMD), our framework leverages observables generated by the system dynamics, when the system dynamics is known, through a Hankel matrix, which shares similarities with discrete Polyflow. When system dynamics is unknown, we approximate them with a neural network while maintaining structural similarities to discrete Polyflow. To enhance noise robustness and ensure long-term stability, we developed a stable parameterization of the Koopman operator, along with a progressive learning strategy for rollout loss. To further improve the performance of the model in the phase space, a simple iterative data augmentation strategy was developed. Numerical experiments of prediction and control of classic nonlinear systems with ablation study showed the effectiveness of the proposed techniques over several state-of-the-art practices.
title Learning Noise-Robust Stable Koopman Operator for Control with Hankel DMD
topic Dynamical Systems
Machine Learning
37N35, 93B45
J.2
url https://arxiv.org/abs/2408.06607