Learned Lifted Linearization Applied to Unstable Dynamic Systems Enabled by Koopman Direct Encoding
This addresses a fundamental difficulty in modeling unstable dynamic systems for applications in control and prediction, though it appears incremental as it builds on existing Koopman and learning techniques.
The paper tackles the problem of constructing Koopman models for nonlinear dynamical systems with both stable and unstable regions, which existing data-driven methods struggle with, by proposing a method that learns observables via neural networks on separated trajectory data and uses Direct Encoding to create a linear state transition matrix, resulting in dramatic improvement over existing methods.
This paper presents a Koopman lifting linearization method that is applicable to nonlinear dynamical systems having both stable and unstable regions. It is known that DMD and other standard data-driven methods face a fundamental difficulty in constructing a Koopman model when applied to unstable systems. Here we solve the problem by incorporating knowledge about a nonlinear state equation with a learning method for finding an effective set of observables. In a lifted space, stable and unstable regions are separated into independent subspaces. Based on this property, we propose to find effective observables through neural net training where training data are separated into stable and unstable trajectories. The resultant learned observables are used for constructing a linear state transition matrix using method known as Direct Encoding, which transforms the nonlinear state equation to a state transition matrix through inner product computations with the observables. The proposed method shows a dramatic improvement over existing DMD and data-driven methods.