Neural ODEs as Feedback Policies for Nonlinear Optimal Control

TL;DR

This paper introduces a neural ODE-based control policy framework for solving constrained nonlinear optimal control problems by leveraging system models, demonstrated on Van der Pol and bioreactor systems.

Contribution

It proposes a novel neural ODE approach for designing feedback control policies that satisfy constraints in nonlinear control tasks.

Findings

Effective control on Van der Pol system

Successful application to bioreactor control

Practical approximation to complex control solutions

Abstract

Neural ordinary differential equations (Neural ODEs) define continuous time dynamical systems with neural networks. The interest in their application for modelling has sparked recently, spanning hybrid system identification problems and time series analysis. In this work we propose the use of a neural control policy capable of satisfying state and control constraints to solve nonlinear optimal control problems. The control policy optimization is posed as a Neural ODE problem to efficiently exploit the availability of a dynamical system model. We showcase the efficacy of this type of deterministic neural policies in two constrained systems: the controlled Van der Pol system and a bioreactor control problem. This approach represents a practical approximation to the intractable closed-loop solution of nonlinear control problems.