FAME-QP: A GPU-Accelerated Quadratic-Programming Solver for Real-Time Model Predictive Control
FAME-QP: A GPU-Accelerated Quadratic-Programming Solver for Real-Time Model Predictive Control
This paper introduces FAME-QP, a GPU-accelerated solver designed for dense quadratic programs in linear model predictive control. By combining constraint-dependent operator representations with fused single- and two-kernel iterations replayed through CUDA graphs, the system automatically selects execution configurations via device calibration and problem-specific timing. It utilizes a cached operator bank to select initial penalties and updates operators lazily when problem matrices change. Numerical benchmarks and simulated control experiments on humanoid and quadrotor systems demonstrate reduced latency compared to competing GPU solvers while maintaining solution accuracy and control performance.
The authors report reduced latency and maintained accuracy for simulated humanoid and quadrotor control tasks using a GPU-accelerated quadratic programming solver, with results benchmarked against competing solvers in a simulation environment.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
s a cached operator bank to select the initial penalty and updates operators lazily when problem matrices change. Numerical benchmarks and simulated humanoid and quadrotor control experiments demonstrate reduced latency relative to competing GPU solvers while maintaining solution accuracy and control performance.
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org