In the literature, actor-critic model predictive control (AC-MPC) integrates MPC with reinforcement learning to enable high-performance control of complex dynamical systems. However, its differentiable MPC layer requires repeatedly solving an optimization problem in both the forward and backward passes, leading to substantial training and inference latency. This paper tackles this bottleneck introducing a CUDA-accelerated variant that significantly reduces end-to-end execution time while preserving the control performance of the baseline formulation. Simulation results on an agile drone racing task show that our approach achieves state-of-the-art lap times and near-limit dynamic behaviour with markedly reduced training and inference time.
@article{arxiv.2605.29155,
title = {CA-AC-MPC: CUDA-Accelerated Actor-Critic Model Predictive Control},
author = {Antoonio Buo and Vittorio Cammarota and Michele Avagnale and Pierluigi Arpenti and Vincenzo Lippiello and Fabio Ruggiero},
journal= {arXiv preprint arXiv:2605.29155},
year = {2026}
}
Comments
Accepted for presentation at the 2026 International Conference on Unmanned Aircraft Systems, ICUAS 2026