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

• URL: http://arxiv.org/abs/2604.07644v1
• Date: Wed, 08 Apr 2026 23:08:15 GMT
• Title: Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU
• Abstract summary: We present GPU-SLS, a GPU-parallelized framework for safe, robust nonlinear model predictive control (MPC)<n>Our method jointly optimize an inequality-constrained, dynamically-feasible nominal trajectory, a tracking controller, and a closed-loop reachable set under disturbance.<n>We validate our approach on complex nonlinear systems, including whole-body quadrupeds (61D) and humanoids (75D)
• Score: 3.093890460224435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 quadratic programming procedure with a novel GPU-accelerated quadratic program (QP) solver that uses parallel associative scans and adaptive caching within an alternating direction method of multipliers (ADMM) framework. The same GPU QP backend is used to optimize robust tracking controllers and closed-loop reachable sets via system level synthesis (SLS), enabling reachability-constrained control in both fixed- and receding-horizon settings. We achieve substantial performance gains, reducing nominal trajectory solve times by 97.7% relative to state-of-the-art CPU solvers and 71.8% compared to GPU solvers, while accelerating SLS-based control and reachability by 237x. Despite large problem scales, our method achieves 100% empirical safety, unlike high-dimensional learning-based reachability baselines. We validate our approach on complex nonlinear systems, including whole-body quadrupeds (61D) and humanoids (75D), synthesizing robust control policies online on the GPU in 20 milliseconds on average and scaling to problems with 2 x 10^5 decision variables and 8 x 10^4 constraints. The implementation of our method is available at https://github.com/Jeff300fang/gpu_sls.

Related papers

• CR-Solver: GPU-Accelerated Kinematics Solver for Tendon-driven Continuum Robots [18.541022260976348]
  We present a two-stage, optimization-based solver for the motion generation of tendon-driven continuum robots.<n>Our method unifies inverse kinematics, path following, and trajectory planning within a single constrained nonlinear optimization framework.<n>We validate our approach on three tasks, demonstrating significant speedups over traditional CPU-based solvers while achieving a consistently high success rate above 95% and millimeter-level accuracy.
  arXiv  Detail & Related papers  (2026-07-13T10:02:36Z)
• GPU-Accelerated Polygonal Signed Distance Functions for Real-Time Collision Avoidance [2.1993185973565113]
  In dense environments, where feasible space is limited, the computational workload often dominates the control-cycle runtime.<n>The proposed Polygonal Signed Distance Function (PSDF) is a geometry-exact signed distance function between a convex polygonal robot footprint and obstacles represented by their boundary edges.<n>PSDF is embedded into model predictive control by locally linearizing the stage-wise safety constraints within a sequential quadratic programming-based real-time iteration scheme.<n>PSDF-MPC maintains real-time feasibility and robust collision avoidance in dense polygonal environments.
  arXiv  Detail & Related papers  (2026-07-05T13:46:59Z)
• GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear and Neural Network Dynamics [3.9198548406564595]
  This paper studies real-time robust optimal control for uncertain nonlinear systems, where linear time-varying (LTV) approximations make planning tractable but require sound linearization error bounds (LEBs) to guarantee robust constraint satisfaction.<n>We develop tight, differentiable, GPU-parallel LEBs for LTV approximations of nonlinear and neural network (NN) dynamics.<n>Our method can compute robust control policies on the GPU at rates up to 67 Hz, reducing solve times and conservativeness relative to baselines while preserving formal guarantees and real-time performance.
  arXiv  Detail & Related papers  (2026-07-01T17:42:37Z)
• Scaling Nonlinear Optimization: Many Problems One GPU [45.58567999526917]
  We introduce textttjaxipm, the first GPU-batched NLP solver, based on IPOPT.<n>We demonstrate up to a $32.85times$ increase in throughput over IPOPT.
  arXiv  Detail & Related papers  (2026-06-24T19:34:41Z)
• Parallel-in-Time Nonlinear Optimal Control via GPU-native Sequential Convex Programming [2.8852807790754618]
  We introduce a fully GPU-native trajectory optimization framework that combines sequential convex programming with a consensus-based alternating direction method of multipliers.<n>We validate the solver on a quadrotor agile flight task and a Mars powered descent problem using an on-board edge computing platform.<n> Benchmarks reveal a sustained 4x throughput speedup and a 51% reduction in energy consumption over a heavily optimized 12-core CPU baseline.
  arXiv  Detail & Related papers  (2026-03-11T12:39:14Z)
• Iterative Convex Optimization with Control Barrier Functions for Obstacle Avoidance among Polytopes [3.8436274588467696]
  Obstacle avoidance by polytopic robots is a challenging problem in optimization-based control and trajectory planning.<n>Existing methods rely on hyperiable distance approximations, such as ellipsoids, which distort geometric dynamics.<n>In this paper, we propose a novel iterative convexity- finite-horizon optimization framework for safety-critical navigation programs.
  arXiv  Detail & Related papers  (2026-03-06T05:10:44Z)
• cuNRTO: GPU-Accelerated Nonlinear Robust Trajectory Optimization [18.671476756500464]
  Trajectory optimization enables autonomous systems to operate safely under uncertainty.<n>These problems often lead to large Second Order Conic Programming (SOCP) constraints, which are computationally expensive.<n>We propose two dynamic optimization architectures that have direct application to robust decision-making and are implemented on splitting.
  arXiv  Detail & Related papers  (2026-03-03T06:17:08Z)
• Graph Neural Model Predictive Control for High-Dimensional Systems [16.33188337508456]
  This work presents a framework that integrates Graph Neural Network (GNN)-based dynamics models with structure-exploiting Model Predictive Control.<n>A tailored condensing algorithm eliminates state variables from the control problem, ensuring efficient computation.<n>Results show that our method scales to systems with up to 1,000 nodes at 100 Hz in closed-loop, and demonstrates real-time reference tracking on hardware with sub-centimeter accuracy.
  arXiv  Detail & Related papers  (2026-02-19T18:26:42Z)
• Efficiently Training Deep-Learning Parametric Policies using Lagrangian Duality [55.06411438416805]
  Constrained Markov Decision Processes (CMDPs) are critical in many high-stakes applications.<n>This paper introduces a novel approach, Two-Stage Deep Decision Rules (TS- DDR) to efficiently train parametric actor policies.<n>It is shown to enhance solution quality and to reduce computation times by several orders of magnitude when compared to current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-23T18:19:47Z)
• Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching [55.28394191394675]
  We develop an adaptive inexact Newton method for equality-constrained nonlinear, nonIBS optimization problems. We demonstrate the superior performance of our method on benchmark nonlinear problems, constrained logistic regression with data from LVM, and a PDE-constrained problem.
  arXiv  Detail & Related papers  (2023-05-28T06:33:37Z)
• Real-Time GPU-Accelerated Machine Learning Based Multiuser Detection for 5G and Beyond [70.81551587109833]
  nonlinear beamforming filters can significantly outperform linear approaches in stationary scenarios with massive connectivity. One of the main challenges comes from the real-time implementation of these algorithms. This paper explores the acceleration of APSM-based algorithms through massive parallelization.
  arXiv  Detail & Related papers  (2022-01-13T15:20:45Z)
• COSMIC: fast closed-form identification from large-scale data for LTV systems [4.10464681051471]
  We introduce a closed-form method for identification of discrete-time linear timevariant systems from data. We develop an algorithm with guarantees of optimality and with a complexity that increases linearly with the number of instants considered per trajectory. Our algorithm was applied to both a Low Fidelity and Functional Engineering Simulators for the Comet Interceptor mission.
  arXiv  Detail & Related papers  (2021-12-08T16:07:59Z)
• Finite-time System Identification and Adaptive Control in Autoregressive Exogenous Systems [79.67879934935661]
  We study the problem of system identification and adaptive control of unknown ARX systems. We provide finite-time learning guarantees for the ARX systems under both open-loop and closed-loop data collection.
  arXiv  Detail & Related papers  (2021-08-26T18:00:00Z)
• Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow [94.24763814458686]
  Security-constrained optimal power flow (SCOPF) is fundamental in power systems. Modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs. This paper proposes a novel approach that combines deep learning and robust optimization techniques.
  arXiv  Detail & Related papers  (2020-07-14T12:38:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.