CA-AC-MPC: CUDA-Accelerated Actor-Critic Model Predictive Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914611889963008 |
|---|---|
| author | Buo, Antoonio Cammarota, Vittorio Avagnale, Michele Arpenti, Pierluigi Lippiello, Vincenzo Ruggiero, Fabio |
| author_facet | Buo, Antoonio Cammarota, Vittorio Avagnale, Michele Arpenti, Pierluigi Lippiello, Vincenzo Ruggiero, Fabio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29155 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CA-AC-MPC: CUDA-Accelerated Actor-Critic Model Predictive Control Buo, Antoonio Cammarota, Vittorio Avagnale, Michele Arpenti, Pierluigi Lippiello, Vincenzo Ruggiero, Fabio Robotics Artificial Intelligence Distributed, Parallel, and Cluster Computing 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. |
| title | CA-AC-MPC: CUDA-Accelerated Actor-Critic Model Predictive Control |
| topic | Robotics Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2605.29155 |