Differentiable Model Predictive Control on the GPU

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Adabag, Emre, Greiff, Marcus, Subosits, John, Lew, Thomas
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912633624461312
author Adabag, Emre
Greiff, Marcus
Subosits, John
Lew, Thomas
author_facet Adabag, Emre
Greiff, Marcus
Subosits, John
Lew, Thomas
contents Differentiable model predictive control (MPC) offers a powerful framework for combining learning and control. However, its adoption has been limited by the inherently sequential nature of traditional optimization algorithms, which are challenging to parallelize on modern computing hardware like GPUs. In this work, we tackle this bottleneck by introducing a GPU-accelerated differentiable optimization tool for MPC. This solver leverages sequential quadratic programming and a custom preconditioned conjugate gradient (PCG) routine with tridiagonal preconditioning to exploit the problem's structure and enable efficient parallelization. We demonstrate substantial speedups over CPU- and GPU-based baselines, significantly improving upon state-of-the-art training times on benchmark reinforcement learning and imitation learning tasks. Finally, we showcase the method on the challenging task of reinforcement learning for driving at the limits of handling, where it enables robust drifting of a Toyota Supra through water puddles.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Differentiable Model Predictive Control on the GPU
Adabag, Emre
Greiff, Marcus
Subosits, John
Lew, Thomas
Optimization and Control
Machine Learning
Systems and Control
Differentiable model predictive control (MPC) offers a powerful framework for combining learning and control. However, its adoption has been limited by the inherently sequential nature of traditional optimization algorithms, which are challenging to parallelize on modern computing hardware like GPUs. In this work, we tackle this bottleneck by introducing a GPU-accelerated differentiable optimization tool for MPC. This solver leverages sequential quadratic programming and a custom preconditioned conjugate gradient (PCG) routine with tridiagonal preconditioning to exploit the problem's structure and enable efficient parallelization. We demonstrate substantial speedups over CPU- and GPU-based baselines, significantly improving upon state-of-the-art training times on benchmark reinforcement learning and imitation learning tasks. Finally, we showcase the method on the challenging task of reinforcement learning for driving at the limits of handling, where it enables robust drifting of a Toyota Supra through water puddles.
title Differentiable Model Predictive Control on the GPU
topic Optimization and Control
Machine Learning
Systems and Control
url https://arxiv.org/abs/2510.06179