Neural Observer with Lyapunov Stability Guarantee for Uncertain Nonlinear Systems
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose a novel nonlinear observer based on neural networks, called neural observer, for observation tasks of linear time-invariant (LTI) systems and uncertain nonlinear systems. In particular, the neural observer designed for uncertain systems is inspired by the active disturbance rejection control, which can measure the uncertainty in real-time. The stability analysis (e.g., exponential convergence rate) of LTI and uncertain nonlinear systems (involving neural observers) are presented and guaranteed, where it is shown that the observation problems can be solved only using the linear matrix inequalities (LMIs). Also, it is revealed that the observability and controllability of the system matrices are required to demonstrate the existence of solutions of LMIs. Finally, the effectiveness of neural observers is verified on three simulation cases, including the X-29A aircraft model, the nonlinear pendulum, and the four-wheel steering vehicle.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 50 references that are in the map. First posted on arXiv 27 Aug 2022.
Builds on
21 of 50 references.
References · 21
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
- 2017Solving high-dimensional partial differential equations using deep learningcited by 556
- 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
- 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 293
- 2019Implicit Deep Learningcited by 124
- 2020Learning Stable Deep Dynamics Modelscited by 111
- 2014Analysis and Design of Optimization Algorithms via Integral Quadratic Constraintscited by 105
- 2019Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programmingcited by 101
- 2017Maximum Principle Based Algorithms for Deep Learningcited by 78
- 2021Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overviewcited by 45
- 2020Stability Analysis using Quadratic Constraints for Systems with Neural Network Controllerscited by 44
9 more
- 2021Implicit energy regularization of neural ordinary-differential-equation controlcited by 29
- 2021Towards Robust Neural Networks via Close-loop Controlcited by 23
- 2020Offset-free setpoint tracking using neural network controllerscited by 10
- 2020The Impact of Data on the Stability of Learning-Based Control- Extended Versioncited by 6
- 2019A Control-Theoretic Perspective on Optimal High-Order Optimizationcited by 5
- 2020How Training Data Impacts Performance in Learning-based Controlcited by 5
- 2020Safe Learning-based Observers for Unknown Nonlinear Systems using Bayesian Optimizationcited by 3
- 2022Solving Optimal Control Problems of Rigid-Body Dynamics with Collisions Using the Hybrid Minimum Principlecited by 3
- 2020Neural Network Based Nonlinear Observerscited by 1
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.
2 papers.