Building Hybrid B-Spline And Neural Network Operators

DOI

10.1109/CDC56724.2024.10886426

Authors

Raffaele Romagnoli, Duquesne University
Jasmine Ratchford, Carnegie Mellon University
Mark H. Klein, Carnegie Mellon University

Document Type

Conference Paper

Publication Date

1-1-2024

Publication Title

Proceedings of the IEEE Conference on Decision and Control

First Page

3611

Last Page

3617

ISSN

7431546

Abstract

Control systems are critical in ensuring the safety of cyber-physical systems (CPS) across domains like airplanes and missiles. Safeguarding CPS necessitates runtime methodologies that continuously monitor safety-critical conditions and respond in a verifiably safe manner. Many real-time safety approaches require predicting the future behavior of systems. However, achieving this requires accurate models that can operate in real time. Inspired by DeepONets, we propose a novel approach that combines B-splines' inductive bias with data-driven neural networks (NNs). Our hybrid B-spline neural operator serves as a universal approximator, validated on a 6DOF quadrotor.

Open Access

Green Accepted

Preprint

Link to Free Full Text

Repository Citation

Romagnoli, R., Ratchford, J., & Klein, M. (2024). Building Hybrid B-Spline And Neural Network Operators. Proceedings of the IEEE Conference on Decision and Control, 3611-3617. https://doi.org/10.1109/CDC56724.2024.10886426