aiqbench analysis
This research advances data-driven control theory by integrating neural Lie derivatives into feedback linearization, offering a fully learned approach to system stabilization without relying on explicit physical models. By establishing rigorous conditions where bounded identification errors guarantee bounded tracking errors, the work bridges the gap between theoretical robustness and practical implementation in dynamic systems like DC motors.
Learning Neural Feedback Linearization for Data-driven Systems via Augmented Lagrangian
arXiv:2609.25163v1 Announce Type: new Abstract: The paper proposes a novel data-driven framework for designing and training a feedback linearizing controller by explicitly incorporating relative degree based conditions into the learning process. This enables the conventional feedback controller components to be replaced by neural Lie derivatives, thereby facilitating a fully data-driven feedback linearization framework. Furthermore, practical closed-loop stability is established by deriving sufficient conditions under which bounded identification errors lead to bounded tracking errors. The derived theoretical results are validated through their application to an armature controlled DC motor.
Abstract:The paper proposes a novel data-driven framework for designing and training a feedback linearizing controller by explicitly incorporating relative degree based conditions into the learning process. This enables the conventional feedback controller components to be replaced by neural Lie derivatives, thereby facilitating a fully data-driven feedback linearization framework. Furthermore, practical closed-loop stability is established by deriving sufficient conditions under which bounded identification errors lead to bounded tracking errors. The derived theoretical results are validated through their application to an armature controlled DC motor.
Machine Learning (cs.LG)
arXiv:2609.25163 [cs.LG]
(or arXiv:2609.25163v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.25163 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 177 words
