ReLU-QP: A GPU-Accelerated Quadratic Programming Solver for Model-Predictive Control

We present ReLU-QP, a GPU-accelerated solver for quadratic programs (QPs) that is capable of solving high-dimensional control problems at real-time rates. ReLU-QP is derived by exactly reformulating the Alternating Direction Method of Multipliers (ADMM) algorithm for solving QPs as a deep, weight-ti...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE International Conference on Robotics and Automation (ICRA) pp. 13285 - 13292
Main Authors Bishop, Arun L., Zhang, John Z., Gurumurthy, Swaminathan, Tracy, Kevin, Manchester, Zachary
Format Conference Proceeding
LanguageEnglish
Published IEEE 13.05.2024
Subjects
Benchmark testing
Machine learning
Manipulators
Neural networks
Quadratic programming
Quadrupedal robots
Real-time systems
Online AccessGet full text

Cover

More Information
Summary:We present ReLU-QP, a GPU-accelerated solver for quadratic programs (QPs) that is capable of solving high-dimensional control problems at real-time rates. ReLU-QP is derived by exactly reformulating the Alternating Direction Method of Multipliers (ADMM) algorithm for solving QPs as a deep, weight-tied neural network with rectified linear unit (ReLU) activations. This reformulation enables the deployment of ReLU-QP on GPUs using standard machine-learning toolboxes. We evaluate the performance of ReLU-QP across three model-predictive control (MPC) benchmarks: stabilizing random linear dynamical systems with control limits, balancing an Atlas humanoid robot on a single foot, and performing a whole-body pick-up motion on a quadruped equipped with a six-degree-of-freedom arm. These benchmarks indicate that ReLU-QP is competitive with state-of-the-art CPU-based solvers for small-to-medium-scale problems and offers order-of-magnitude speed improvements for larger-scale problems.
DOI:10.1109/ICRA57147.2024.10611249