MPC and System Identification with Differentiable Physics: Fluid System and Particle Beam Control

TL;DR

This paper introduces a real-time control and parameter estimation framework using differentiable physics simulators, demonstrated on fluid flow and particle accelerator applications.

Contribution

It presents a novel joint optimization approach for control and system identification using differentiable simulation, unlike traditional explicit model-based MPC.

Findings

Successfully applied to fluid flow control.

Effective in particle accelerator parameter estimation.

Enables real-time joint control and system identification.

Abstract

We consider the problem of simultaneous control and parameter estimation when the model is available only as a differentiable physics simulator. We propose a receding-horizon control framework in which a model predictive control (MPC) objective is optimized using gradients obtained by differentiating through the simulator, while physical parameters are updated online using measurement data. Unlike classical MPC, which relies on explicit algebraic models, our approach treats the dynamics as a computational object and performs simulation-based optimization using automatic differentiation. A shared differentiable model enables joint, real-time optimization of control inputs and physical parameters. We present two preliminary examples to demonstrate the proposed framework on two challenging applications: a fluid flow problem and a particle accelerator.