Neural ODEs as Feedback Policies for Nonlinear Optimal Control
This work addresses constrained nonlinear control problems for applications like hybrid systems and bioreactors, representing an incremental improvement by applying Neural ODEs as feedback policies.
The authors tackled nonlinear optimal control problems by proposing a neural control policy based on Neural ODEs that satisfies state and control constraints, demonstrating efficacy on the controlled Van der Pol system and a bioreactor control problem as a practical approximation to intractable closed-loop solutions.
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.