An unsupervised PINN is used to learn nonlinear observer gains by enforcing the contraction matrix inequality, with an exponential ISS bound claimed for the resulting observer.
Non-asymptotic neural network-based state and disturbance estimation for a class of nonlinear systems using modulating functions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Unsupervised Physics-Informed Neural Network-based Nonlinear Observer design for autonomous systems using contraction analysis
An unsupervised PINN is used to learn nonlinear observer gains by enforcing the contraction matrix inequality, with an exponential ISS bound claimed for the resulting observer.