Researchers have developed a new framework called Internal Controller Identification (ICI) for identifying nonlinear systems, even those that are potentially unstable. This method generalizes the classical Youla parameterization to the nonlinear setting, ensuring closed-loop stability by construction. Experiments demonstrate that ICI outperforms baseline methods in scenarios with unstable plants, weak excitation, and feedback-correlated noise, while also offering zero-shot generalization to new environments and providing a generalization bound with limited data. AI
IMPACT This research could lead to more robust and stable AI control systems, particularly in complex or potentially unstable environments.
RANK_REASON Academic paper detailing a new method for system identification. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- Influence Flower
- Internal Controller Identification
- PAC-bayesian learning
- ScienceCast
- Youla parameterization
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →