Neural network based control of unknown nonlinear systems via contraction analysis
Hao Yin, Claudio De Persis, Bayu Jayawardhana, Santiago Sanchez Escalonilla Plaza

TL;DR
This paper presents a neural network control framework for unknown nonlinear systems using contraction analysis, ensuring convergence to equilibrium neighborhoods with convex conditions for efficiency.
Contribution
It introduces a contraction-based neural ODE approach with convex reformulation of conditions, enabling effective control of unknown nonlinear systems.
Findings
Contractive neural ODE systems guarantee convergence to equilibrium neighborhoods.
Convex LMI conditions improve computational efficiency.
Controller design ensures trajectories converge to the neighborhood of the unknown equilibrium.
Abstract
This paper studies the design of neural network (NN)-based controllers for unknown nonlinear systems, using contraction analysis. A Neural Ordinary Differential Equation (NODE) system is constructed by approximating the unknown draft dynamics with a feedforward NN. Incremental sector bounds and contraction theory are applied to the activation functions and the weights of the NN, respectively. It is demonstrated that if the incremental sector bounds and the weights satisfy some non-convex conditions, the NODE system is contractive. To improve computational efficiency, these non-convex conditions are reformulated as convex LMI conditions. Additionally, it is proven that when the NODE system is contractive, the trajectories of the original autonomous system converge to a neighborhood of the unknown equilibrium, with the size of this neighborhood determined by the approximation error. For a…
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 and Stability of Dynamical Systems · Adaptive Dynamic Programming Control · Adaptive Control of Nonlinear Systems
MethodsNeural Oblivious Decision Ensembles
