Neural Observer with Lyapunov Stability Guarantee for Uncertain Nonlinear Systems

• URL: http://arxiv.org/abs/2208.13006v1
• Date: Sat, 27 Aug 2022 13:16:43 GMT
• Title: Neural Observer with Lyapunov Stability Guarantee for Uncertain Nonlinear Systems
• Authors: Song Chen, Tehuan Chen, Chao Xu, and Jian Chu
• Abstract summary: We propose a novel nonlinear observer, called the neural observer, for observation tasks of linear time-invariant (LTI) systems and uncertain nonlinear systems. We derive stability analyses (e.g., exponential convergence rate) of LTI and uncertain nonlinear systems that pave the way to solve observation problems using linear matrix inequalities (LMIs) only. We verify the availability of neural observers on three simulation cases, including the X-29A aircraft model, the nonlinear pendulum, and the four-wheel steering vehicle.
• Score: 6.479565605473741
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a novel nonlinear observer, called the neural observer, for observation tasks of linear time-invariant (LTI) systems and uncertain nonlinear systems by introducing the neural network (NN) into the design of observers. By exploring the method of NN representation to the NN mapping vector, we derive stability analyses (e.g., exponential convergence rate) of LTI and uncertain nonlinear systems that pave the way to solve observation problems using linear matrix inequalities (LMIs) only. Remarkably, the neural observer designed for uncertain systems is based on the ideology of the active disturbance rejection control (ADRC), which can measure the uncertainty in real-time. The LMI results are also significant since we reveal that the observability and controllability of system matrices are required for the existence of solutions of LMIs. Finally, we verify the availability of neural observers on three simulation cases, including the X-29A aircraft model, the nonlinear pendulum, and the four-wheel steering vehicle.

Related papers

• Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation [67.63756749551924]
  Learning-based neural network (NN) control policies have shown impressive empirical performance in a wide range of tasks in robotics and control. Lyapunov stability guarantees over the region-of-attraction (ROA) for NN controllers with nonlinear dynamical systems are challenging to obtain. We demonstrate a new framework for learning NN controllers together with Lyapunov certificates using fast empirical falsification and strategic regularizations.
  arXiv  Detail & Related papers  (2024-04-11T17:49:15Z)
• Nonlinear Discrete-Time Observers with Physics-Informed Neural Networks [0.0]
  We use Physics-Informed Neural Networks (PINNs) to solve the discrete-time nonlinear observer state estimation problem. The proposed PINN approach aims at learning a nonlinear state transformation map by solving a system of inhomogeneous functional equations.
  arXiv  Detail & Related papers  (2024-02-19T18:47:56Z)
• Learning Robust State Observers using Neural ODEs (longer version) [1.0094821910320064]
  We present a methodology for the design of state observers for nonlinear systems based on Neural ODEs, learning Luenberger-like observers and their nonlinear extension. For tuneable KKL observers, the relationship between the design of the observer and its trade-off between convergence speed and robustness is analysed and used as a basis for improving the robustness of the learning-based observer in training.
  arXiv  Detail & Related papers  (2022-12-01T20:58:39Z)
• Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations [114.17826109037048]
  Ordinary Differential Equations (ODEs) have recently gained a lot of attention in machine learning. theoretical aspects, e.g., identifiability and properties of statistical estimation are still obscure. This paper derives a sufficient condition for the identifiability of homogeneous linear ODE systems from a sequence of equally-spaced error-free observations sampled from a single trajectory.
  arXiv  Detail & Related papers  (2022-10-12T06:46:38Z)
• Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems [59.57462129637796]
  This paper presents a backward reachability approach for safety verification of closed-loop systems with neural networks (NNs) The presence of NNs in the feedback loop presents a unique set of problems due to the nonlinearities in their activation functions and because NN models are generally not invertible. We present frameworks for calculating BP over-approximations for both linear and nonlinear systems with control policies represented by feedforward NNs.
  arXiv  Detail & Related papers  (2022-09-28T13:17:28Z)
• Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guarantees [4.786698731084036]
  We propose a learning framework to stabilize an unknown nonlinear system with a neural controller and learn a neural Lyapunov function. We provide theoretical guarantees of the proposed learning framework in terms of the closed-loop stability for the unknown nonlinear system.
  arXiv  Detail & Related papers  (2022-06-04T05:57:31Z)
• A Theoretical Overview of Neural Contraction Metrics for Learning-based Control with Guaranteed Stability [7.963506386866862]
  This paper presents a neural network model of an optimal contraction metric and corresponding differential Lyapunov function. Its innovation lies in providing formal robustness guarantees for learning-based control frameworks.
  arXiv  Detail & Related papers  (2021-10-02T00:28:49Z)
• Learning Nonlinear Waves in Plasmon-induced Transparency [0.0]
  We consider a recurrent neural network (RNN) approach to predict the complex propagation of nonlinear solitons in plasmon-induced transparency metamaterial systems. We prove the prominent agreement of results in simulation and prediction by long short-term memory (LSTM) artificial neural networks.
  arXiv  Detail & Related papers  (2021-07-31T21:21:44Z)
• Controlling nonlinear dynamical systems into arbitrary states using machine learning [77.34726150561087]
  We propose a novel and fully data driven control scheme which relies on machine learning (ML) Exploiting recently developed ML-based prediction capabilities of complex systems, we demonstrate that nonlinear systems can be forced to stay in arbitrary dynamical target states coming from any initial state. Having this highly flexible control scheme with little demands on the amount of required data on hand, we briefly discuss possible applications that range from engineering to medicine.
  arXiv  Detail & Related papers  (2021-02-23T16:58:26Z)
• Neural Dynamic Mode Decomposition for End-to-End Modeling of Nonlinear Dynamics [49.41640137945938]
  We propose a neural dynamic mode decomposition for estimating a lift function based on neural networks. With our proposed method, the forecast error is backpropagated through the neural networks and the spectral decomposition. Our experiments demonstrate the effectiveness of our proposed method in terms of eigenvalue estimation and forecast performance.
  arXiv  Detail & Related papers  (2020-12-11T08:34:26Z)
• Lipschitz Recurrent Neural Networks [100.72827570987992]
  We show that our Lipschitz recurrent unit is more robust with respect to input and parameter perturbations as compared to other continuous-time RNNs. Our experiments demonstrate that the Lipschitz RNN can outperform existing recurrent units on a range of benchmark tasks.
  arXiv  Detail & Related papers  (2020-06-22T08:44:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.