SYLGDec 1, 2022

Learning Robust State Observers using Neural ODEs (longer version)

arXiv:2212.00866v224 citationsh-index: 19
Originality Incremental advance
AI Analysis

This work addresses the problem of robust state estimation in control systems, offering a learning-based approach that is incremental in applying Neural ODEs to observer design.

The paper tackles the design of state observers for nonlinear systems with partially or fully unknown dynamics using Neural ODEs, achieving improved robustness by analyzing the trade-off between convergence speed and robustness in training.

Relying on recent research results on Neural ODEs, this paper presents a methodology for the design of state observers for nonlinear systems based on Neural ODEs, learning Luenberger-like observers and their nonlinear extension (Kazantzis-Kravaris-Luenberger (KKL) observers) for systems with partially-known nonlinear dynamics and fully unknown nonlinear dynamics, respectively. In particular, for tuneable KKL observers, the relationship between the design of the observer and its trade-off between convergence speed and robustness is analysed and used as a basis for improving the robustness of the learning-based observer in training. We illustrate the advantages of this approach in numerical simulations.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes