Building Hybrid B-Spline And Neural Network Operators

SEI Report
This paper proposes a B-spline neural operator for real-time CPS safety, combining neural networks with inductive bias to predict system behavior on a quadrotor.
Publisher

IEEE

DOI (Digital Object Identifier)
10.1109/CDC56724.2024.10886426

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.

Part of a Collection

AI Division Publications

Cite This SEI Report

Romagnoli, R., Ratchford, J., & Klein, M. (2024, December 16). Building Hybrid B-Spline And Neural Network Operators. Retrieved August 8, 2026, from https://doi.org/10.1109/CDC56724.2024.10886426.

@techreport{romagnoli_2024,
author={Romagnoli, Raffaele and Ratchford, Jasmine and Klein, Mark},
title={Building Hybrid B-Spline And Neural Network Operators},
month={Dec},
year={2024},
institution={Software Engineering Institute, Carnegie Mellon University},
doi={10.1109/CDC56724.2024.10886426},
url={https://doi.org/10.1109/CDC56724.2024.10886426},
note={Accessed: 2026-Aug-8}
}

Romagnoli, Raffaele, Jasmine Ratchford, and Mark Klein. "Building Hybrid B-Spline And Neural Network Operators." Software Engineering Institute, Carnegie Mellon University. IEEE, December 16, 2024. https://doi.org/10.1109/CDC56724.2024.10886426.

R. Romagnoli, J. Ratchford, and M. Klein, "Building Hybrid B-Spline And Neural Network Operators," Software Engineering Institute, Carnegie Mellon University. IEEE, 16-Dec-2024 [Online]. Available: https://doi.org/10.1109/CDC56724.2024.10886426. [Accessed: 8-Aug-2026].

Romagnoli, Raffaele, Jasmine Ratchford, and Mark Klein. "Building Hybrid B-Spline And Neural Network Operators." Software Engineering Institute, Carnegie Mellon University, IEEE, 16 Dec. 2024. https://doi.org/10.1109/CDC56724.2024.10886426. Accessed 8 Aug. 2026.

Romagnoli, Raffaele; Ratchford, Jasmine; & Klein, Mark. Building Hybrid B-Spline And Neural Network Operators. IEEE. 2024. DOI: 10.1109/CDC56724.2024.10886426. https://doi.org/10.1109/CDC56724.2024.10886426

This content was created for a conference series or symposium and does not necessarily reflect the positions and views of the Software Engineering Institute.