Deep Koopman Operator With Control for Nonlinear Systems

  title={Deep Koopman Operator With Control for Nonlinear Systems},
  author={Hao-bin Shi and Max Qinghu Meng},
  journal={IEEE Robotics and Automation Letters},
  • Hao-bin ShiM. Meng
  • Published 16 February 2022
  • Computer Science
  • IEEE Robotics and Automation Letters
Recently Koopman operator has become a promising data-driven tool to facilitate real-time control for unknown nonlinear systems. It maps nonlinear systems into equivalent linear systems in embedding space, ready for real-time linear control methods. However, designing an appropriate Koopman embedding function remains a challenging task. Furthermore, most Koopman-based algorithms only consider nonlinear systems with linear control input, resulting in lousy prediction and control performance when… 

Figures and Tables from this paper

Data-Driven Linear Koopman Embedding for Networked Systems: Model-Predictive Grid Control

A data-learned linear Koopman embedding of nonlinear networked dynamics and uses it to enable real-time model predictive emergency voltage control in a power network.

Data-Driven Linear Koopman Embedding for Model-Predictive Power System Control

This paper presents a linear Koopman embedding for model predictive emergency voltage regulation in power systems, by way of a data-driven lifting of the system dynamics into a higher dimensional

Deep Koopman with Control: Spectral Analysis of Soft Robot Dynamics

By globally linearising dynamics, the Koopman operator is analyzed using spectral decomposition to characterises important physics-based interpretations, such as functional growths and oscillations, in the context of spectral analysis.

A Novel Koopman-Inspired Method for the Secondary Control of Microgrids with Grid-Forming and Grid-Following Sources

This paper proposes an online data-driven Koopman-inspired identification and control method for microgrid secondary voltage and frequency control. Unlike typical data-driven methods, the proposed

Data-driven Predictive Tracking Control based on Koopman Operators

—We seek to combine the nonlinear modeling capabil- ities of a wide class of neural networks with the safety guarantees of model predictive control (MPC) in a rigorous and online computationally



Learning Compositional Koopman Operators for Model-Based Control

This paper proposes to learn compositional Koopman operators, using graph neural networks to encode the state into object-centric embeddings and using a block-wise linear transition matrix to regularize the shared structure across objects.

Deep Learning of Koopman Representation for Control

A data-driven, model-free approach for the optimal control of the dynamical system that relies on the Deep Neural Network based learning of Koopman operator for the purpose of control.

Deep learning for universal linear embeddings of nonlinear dynamics

It is often advantageous to transform a strongly nonlinear system into a linear one in order to simplify its analysis for prediction and control, so the authors combine dynamical systems with deep learning to identify these hard-to-find transformations.

Derivative-Based Koopman Operators for Real-Time Control of Robotic Systems

Experimental results show that the proposed data-driven control approach outperforms a tuned proportional–integral–derivative controller and that updating the data- driven model online significantly improves performance in the presence of unmodeled fluid disturbance.

Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control

This work presents an optimization method that ensures stability at every step and iteratively improves the reconstruction error using gradient directions derived, and achieves an orders-of-magnitude improvement in reconstruction error and superior results in terms of control performance.

Forecasting Sequential Data using Consistent Koopman Autoencoders

This work proposes a novel Consistent Koopman Autoencoder model which leverages the forward and backward dynamics, and achieves accurate estimates for significant prediction horizons, while also being robust to noise.

A Data–Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition

This approach is an extension of dynamic mode decomposition (DMD), which has been used to approximate the Koopman eigenvalues and modes, and if the data provided to the method are generated by a Markov process instead of a deterministic dynamical system, the algorithm approximates the eigenfunctions of the Kolmogorov backward equation.

Modern Koopman Theory for Dynamical Systems

An overview of modern Koopman operator theory is provided, describing recent theoretical and algorithmic developments and highlighting these methods with a diverse range of applications, making it ideal for leveraging big-data and machine learning techniques.