Safe Large Scale Robust Nonlinear Mpc

---
name: safe-large-scale-robust-nonlinear-mpc
description: "We present GPU-SLS, a GPU-parallelized framework for safe, robust nonlinear model predictive control (MPC) that scales to high-dimensional uncertain robotic systems and long planni... Activation: safe, large, scale, robust, nonlinear"
---

# Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU

## Overview
We present GPU-SLS, a GPU-parallelized framework for safe, robust nonlinear model predictive control (MPC) that scales to high-dimensional uncertain robotic systems and long planning horizons. Our method jointly optimizes an inequality-constrained, dynamically-feasible nominal trajectory, a tracking controller, and a closed-loop reachable set under disturbance, all in real-time. To efficiently compute nominal trajectories, we develop a sequential

## Source Paper
- **Title:** Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU
- **Authors:** Jeffrey Fang, Glen Chou
- **arXiv:** 2604.07644v1
- **Published:** 2026-04-08
- **Categories:** cs.RO, cs.AI, eess.SY, math.OC

## Core Concepts

### Key Contributions
1. We present GPU-SLS, a GPU-parallelized framework for safe, robust nonlinear model predictive control (MPC) that scales t...
2. Our method jointly optimizes an inequality-constrained, dynamically-feasible nominal trajectory, a tracking controller, ...
3. To efficiently compute nominal trajectories, we develop a sequential quadratic programming procedure with a novel GPU-ac...

## Practical Applications

- Control system design and optimization
- Distributed system coordination
- Multi-agent system orchestration

## References

- Jeffrey Fang et al. (2026). "Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU." arXiv:2604.07644v1.

## Activation Keywords
- safe, large, scale, robust, nonlinear, milliseconds, reachability, constrained

---
*Generated: 2026-04-13*