DeepAI AI Chat
Log In Sign Up

Koopman NMPC: Koopman-based Learning and Nonlinear Model Predictive Control of Control-affine Systems

by   Carl Folkestad, et al.

Koopman-based learning methods can potentially be practical and powerful tools for dynamical robotic systems. However, common methods to construct Koopman representations seek to learn lifted linear models that cannot capture nonlinear actuation effects inherent in many robotic systems. This paper presents a learning and control methodology that is a first step towards overcoming this limitation. Using the Koopman canonical transform, control-affine dynamics can be expressed by a lifted bilinear model. The learned model is used for nonlinear model predictive control (NMPC) design where the bilinear structure can be exploited to improve computational efficiency. The benefits for control-affine dynamics compared to existing Koopman-based methods are highlighted through an example of a simulated planar quadrotor. Prediction error is greatly reduced and closed loop performance similar to NMPC with full model knowledge is achieved.


page 1

page 2

page 3

page 4


Advantages of Bilinear Koopman Realizations for the Modeling and Control of Systems with Unknown Dynamics

Nonlinear dynamical systems can be made easier to control by lifting the...

Neural Koopman Lyapunov Control

Learning and synthesizing stabilizing controllers for unknown nonlinear ...

Learning Koopman Operators with Control Using Bi-level Optimization

The accurate modeling and control of nonlinear dynamical effects are cru...

Learning Bilinear Models of Actuated Koopman Generators from Partially-Observed Trajectories

Data-driven models for nonlinear dynamical systems based on approximatin...

Koopman Linearization for Data-Driven Batch State Estimation of Control-Affine Systems

We present the Koopman State Estimator (KoopSE), a framework for model-f...