Learning Provable Neural Network Observer for Uncertain Dynamical Systems
In many safety-critical applications, control of uncertain dynamical systems relies on observers that estimate states and external disturbances. Neural network observers can improve estimation accuracy, but certifying their Lyapunov stability via Linear Matrix Inequality (LMI) constraints leads to large-scale semidefin...
Zhang-Yi Wang, Jia-Xu Liu, Chen Song et al.
· 0 citations