A Versatile Framework for Data-Driven Control of Nonlinear Systems
Nima Monshizadeh, Claudio De Persis, Pietro Tesi

TL;DR
This paper introduces a comprehensive, unifying framework for data-driven control of nonlinear systems, enabling systematic design and synthesis of controllers with broad applicability and new insights.
Contribution
It presents a high-level, systematic approach to formulate and solve nonlinear control problems using data-driven methods, unifying existing techniques and enabling new results.
Findings
Framework successfully synthesizes control algorithms meeting design specifications
Demonstrates versatility through various practical examples
Enables derivation of novel control insights and results
Abstract
This note aims to provide a systematic investigation of direct data-driven control, enriching the existing literature not by adding another isolated result, but rather by offering a unifying, versatile, and broad framework that enables the generation of novel results in this domain. We formulate the nonlinear design problem from a high-level perspective as a set of desired controlled systems and propose systematic procedures to synthesize data-driven control algorithms that meet the specified design requirements. Various examples are presented to demonstrate the applicability of the proposed approach and its ability to derive new insights and results, illustrating the novel contributions enabled by the framework.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsControl Systems and Identification · Advanced Control Systems Optimization · Fault Detection and Control Systems
MethodsSparse Evolutionary Training
