Saved in:
Bibliographic Details
Main Authors: Chakrabarti, Ananda, Nayak, Indranil, Goswami, Debdipta
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.19085
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908283334295552
author Chakrabarti, Ananda
Nayak, Indranil
Goswami, Debdipta
author_facet Chakrabarti, Ananda
Nayak, Indranil
Goswami, Debdipta
contents This paper introduces the temporally-consistent bilinearly recurrent autoencoder (tcBLRAN), a Koopman operator based neural network architecture for modeling a control-affine nonlinear control system. The proposed method extends traditional Koopman autoencoders (KAE) by incorporating bilinear recurrent dynamics that are consistent across predictions, enabling accurate long-term forecasting for control-affine systems. This overcomes the roadblock that KAEs face when encountered with limited and noisy training datasets, resulting in a lack of generalizability due to inconsistency in training data. Through a blend of deep learning and dynamical systems theory, tcBLRAN demonstrates superior performance in capturing complex behaviors and control systems dynamics, providing a superior data-driven modeling technique for control systems and outperforming the state-of-the-art Koopman bilinear form (KBF) learned by autoencoder networks.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19085
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Temporally-Consistent Bilinearly Recurrent Autoencoders for Control Systems
Chakrabarti, Ananda
Nayak, Indranil
Goswami, Debdipta
Systems and Control
This paper introduces the temporally-consistent bilinearly recurrent autoencoder (tcBLRAN), a Koopman operator based neural network architecture for modeling a control-affine nonlinear control system. The proposed method extends traditional Koopman autoencoders (KAE) by incorporating bilinear recurrent dynamics that are consistent across predictions, enabling accurate long-term forecasting for control-affine systems. This overcomes the roadblock that KAEs face when encountered with limited and noisy training datasets, resulting in a lack of generalizability due to inconsistency in training data. Through a blend of deep learning and dynamical systems theory, tcBLRAN demonstrates superior performance in capturing complex behaviors and control systems dynamics, providing a superior data-driven modeling technique for control systems and outperforming the state-of-the-art Koopman bilinear form (KBF) learned by autoencoder networks.
title Temporally-Consistent Bilinearly Recurrent Autoencoders for Control Systems
topic Systems and Control
url https://arxiv.org/abs/2503.19085