Zero-Shot Function Encoder-Based Differentiable Predictive Control
This addresses the need for fast, adaptive control in nonlinear systems, offering a general-purpose tool that is incremental by building on existing neural ODE and predictive control methods.
The paper tackles the problem of adaptive control for nonlinear dynamical systems by introducing a differentiable framework that integrates a function encoder-based neural ODE with differentiable predictive control, enabling zero-shot adaptation to new systems without retraining and eliminating costly online optimization, with demonstrated efficiency and accuracy across various parametric scenarios.
We introduce a differentiable framework for zero-shot adaptive control over parametric families of nonlinear dynamical systems. Our approach integrates a function encoder-based neural ODE (FE-NODE) for modeling system dynamics with a differentiable predictive control (DPC) for offline self-supervised learning of explicit control policies. The FE-NODE captures nonlinear behaviors in state transitions and enables zero-shot adaptation to new systems without retraining, while the DPC efficiently learns control policies across system parameterizations, thus eliminating costly online optimization common in classical model predictive control. We demonstrate the efficiency, accuracy, and online adaptability of the proposed method across a range of nonlinear systems with varying parametric scenarios, highlighting its potential as a general-purpose tool for fast zero-shot adaptive control.