Deep Learning of Koopman Representation for Control

by   Yiqiang Han, et al.

We develop a data-driven, model-free approach for the optimal control of the dynamical system. The proposed approach relies on the Deep Neural Network (DNN) based learning of Koopman operator for the purpose of control. In particular, DNN is employed for the data-driven identification of basis function used in the linear lifting of nonlinear control system dynamics. The controller synthesis is purely data-driven and does not rely on a priori domain knowledge. The OpenAI Gym environment, employed for Reinforcement Learning-based control design, is used for data generation and learning of Koopman operator in control setting. The method is applied to two classic dynamical systems on OpenAI Gym environment to demonstrate the capability.


Data Driven Control with Learned Dynamics: Model-Based versus Model-Free Approach

This paper compares two different types of data-driven control methods, ...

Data-driven End-to-end Learning of Pole Placement Control for Nonlinear Dynamics via Koopman Invariant Subspaces

We propose a data-driven method for controlling the frequency and conver...

Learning to Reach, Swim, Walk and Fly in One Trial: Data-Driven Control with Scarce Data and Side Information

We develop a learning-based control algorithm for unknown dynamical syst...

Data-driven simulation for general purpose multibody dynamics using deep neural networks

In this paper, a machine learning-based simulation framework of general-...

Universal Model-free Information Extraction

Bayesian approaches have been used extensively in scientific and enginee...

The self-learning AI controller for adaptive power beaming with fiber-array laser transmitter system

In this study we consider adaptive power beaming with fiber-array laser ...

Please sign up or login with your details

Forgot password? Click here to reset