AB  - In this paper, we present a new data-driven method for learning stable models of nonlinear systems. Our model lifts the original state space to a higher-dimensional linear manifold using Koopman embeddings. Interestingly, we prove that every discrete-time nonlinear contracting model can be learnt in our framework. Another significant merit of the proposed approach is that it allows for unconstrained optimization over the Koopman embedding and operator jointly while enforcing stability of the model, via a direct parameterization of stable linear systems, greatly simplifying the computations involved. We validate our method on a simulated system and analyze the advantages of our parameterization compared to alternatives.
AU  - Fan, F
AU  - Yi, B
AU  - Rye, D
AU  - Shi, G
AU  - Manchester, IR
DA  - 2022/01/01
DO  - 10.23919/ACC53348.2022.9867865
EP  - 2747
JO  - 2022 American Control Conference (ACC)
PB  - Institute of Electrical and Electronics Engineers (IEEE)
PY  - 2022/01/01
SP  - 2742
TI  - Learning Stable Koopman Embeddings
VL  - 2022-June
Y1  - 2022/01/01
Y2  - 2026/05/11
ER  -