English
Related papers

Related papers: Negative Imaginary Neural ODEs: Learning to Contro…

200 papers

This letter devises Neural Dynamic Equivalence (NeuDyE), which explores physics-aware machine learning and neural-ordinary-differential-equations (ODE-Net) to discover a dynamic equivalence of external power grids while preserving its…

Systems and Control · Electrical Eng. & Systems 2023-10-02 Qing Shen , Yifan Zhou , Qiang Zhang , Slava Maslennikov , Xiaochuan Luo , Peng Zhang

Negative imaginary (NI) systems theory is a well-established system theoretic framework for analysis and design of linear-time-invariant (LTI) control systems. In this paper, we aim to generalize negative imaginary systems theory to a class…

Dynamical Systems · Mathematics 2022-01-04 Ahmed G. Ghallab , Ian R. Petersen

In this paper, we investigate the necessary and sufficient conditions under which a class of nonlinear systems are state feedback equivalent to nonlinear negative imaginary (NI) systems with positive definite storage functions. The…

Systems and Control · Electrical Eng. & Systems 2022-06-08 Kanghong Shi , Ian R. Petersen , Igor G. Vladimirov

This paper studies the design of neural network (NN)-based controllers for unknown nonlinear systems, using contraction analysis. A Neural Ordinary Differential Equation (NODE) system is constructed by approximating the unknown draft…

Systems and Control · Electrical Eng. & Systems 2025-05-23 Hao Yin , Claudio De Persis , Bayu Jayawardhana , Santiago Sanchez Escalonilla Plaza

In the transition to achieving net zero emissions, it has been suggested that a substantial expansion of electric power grids will be necessary to support emerging renewable energy zones. In this paper, we propose employing battery-based…

Systems and Control · Electrical Eng. & Systems 2024-07-12 Yijun Chen , Kanghong Shi , Ian R. Petersen , Elizabeth L. Ratnam

A large class of inverse problems for PDEs are only well-defined as mappings from operators to functions. Existing operator learning frameworks map functions to functions and need to be modified to learn inverse maps from data. We propose a…

Machine Learning · Computer Science 2023-06-06 Roberto Molinaro , Yunan Yang , Björn Engquist , Siddhartha Mishra

The deployment of learning-based models in safety-critical control systems demands mathematical guarantees that standard regression architectures cannot provide. This paper presents an integrated framework that bridges Neural Ordinary…

Systems and Control · Electrical Eng. & Systems 2026-05-26 Lin Feng , Xin He

Deep learning methods have demonstrated significant potential for addressing complex nonlinear control problems. For real-world safety-critical tasks, however, it is crucial to provide formal stability guarantees for the designed…

Systems and Control · Electrical Eng. & Systems 2025-06-10 Han Wang , Keyan Miao , Diego Madeira , Antonis Papachristodoulou

Stability guarantees are crucial when ensuring a fully autonomous robot does not take undesirable or potentially harmful actions. Unfortunately, global stability guarantees are hard to provide in dynamical systems learned from data,…

This paper presents a velocity-free position control strategy for quadrotor unmanned aerial vehicles based on nonlinear negative imaginary (NNI) systems theory. Unlike conventional position control schemes that require velocity measurements…

Systems and Control · Electrical Eng. & Systems 2026-03-31 Ahmed G. Ghallab , Ian R. Petersen

Identifying accurate dynamic models is required for the simulation and control of various technical systems. In many important real-world applications, however, the two main modeling approaches often fail to meet requirements: first…

Machine Learning · Computer Science 2021-04-19 Manuel A. Roehrl , Thomas A. Runkler , Veronika Brandtstetter , Michel Tokic , Stefan Obermayer

In this paper, we address the adversarial training of neural ODEs from a robust control perspective. This is an alternative to the classical training via empirical risk minimization, and it is widely used to enforce reliable outcomes for…

Optimization and Control · Mathematics 2024-04-02 Cristina Cipriani , Alessandro Scagliotti , Tobias Wöhrer

Neural CDEs provide a natural way to process the temporal evolution of irregular time series. The number of function evaluations (NFE) is these systems' natural analog of depth (the number of layers in traditional neural networks). It is…

Machine Learning · Computer Science 2026-01-27 Ilya Kuleshov , Evgenia Romanenkova , Vladislav Zhuzhel , Galina Boeva , Evgeni Vorsin , Alexey Zaytsev

A robust output feedback consensus problem for networked identical nonlinear negative-imaginary (NI) systems is investigated in this paper. Output consensus is achieved by applying identical linear output strictly negative-imaginary (OSNI)…

Systems and Control · Electrical Eng. & Systems 2021-04-09 Kanghong Shi , Igor G. Vladimirov , Ian R. Petersen

In this paper, we propose an iterative training algorithm for Neural ODEs that provides models resilient to control (parameter) disturbances. The method builds on our earlier work Tuning without Forgetting-and similarly introduces training…

Machine Learning · Computer Science 2025-09-23 Erkan Bayram , Mohamed-Ali Belabbas , Tamer Başar

Many successful methods to learn dynamical systems from data have recently been introduced. However, ensuring that the inferred dynamics preserve known constraints, such as conservation laws or restrictions on the allowed system states,…

Machine Learning · Computer Science 2024-02-16 Alistair White , Niki Kilbertus , Maximilian Gelbrecht , Niklas Boers

In this paper, we study the internal stabilizability and internal stabilization problems for multidimensional (nD) systems. Within the fractional representation approach, a multidimen-sional system can be studied by means of matrices with…

Numerical Analysis · Mathematics 2018-06-22 Yacine Bouzidi , Thomas Cluzeau , Guillaume Moroz , Alban Quadrat

This paper develops a neural network based control framework that ensures system safety and input-to-state stability (ISS) for general nonlinear switched systems with unknown dynamics. Leveraging the concept of dwell time, we derive…

Systems and Control · Electrical Eng. & Systems 2026-01-22 Bhabani Shankar Dey , Ahan Basu , Pushpak Jagtap

This paper presents a cascaded control architecture, based on nonlinear dynamic inversion (NDI), for rigid body attitude control. The proposed controller works directly with the rotation matrix parameterization, that is, with elements of…

Systems and Control · Electrical Eng. & Systems 2024-09-06 Hafiz Zeeshan Iqbal Khan , Farooq Aslam , Muhammad Farooq Haydar , Jamshed Riaz

Neural Ordinary Differential Equations (ODEs) represent a significant advancement at the intersection of machine learning and dynamical systems, offering a continuous-time analog to discrete neural networks. Despite their promise, deploying…

Numerical Analysis · Mathematics 2025-06-18 Matteo Caldana , Jan S. Hesthaven