Metraipolis › archive › dc_c26fbfb46fa7
Micro Neural Policies for Safe Real-Time Robotic Control — arXiv:2610.08541
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08541
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:21:54.255Z
- SHA-256 of the archived text
7cfc67d798955809677ae9810c05ee6990bc59c07130a8420a446904c17ee091- Stable URL of this page
https://metraipolis.com/documento/dc_c26fbfb46fa7
How to cite
Micro Neural Policies for Safe Real-Time Robotic Control — arXiv:2610.08541 — arXiv (en), https://arxiv.org/abs/2610.08541 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c26fbfb46fa7 (Metraipolis archive dc_c26fbfb46fa7, sha256 7cfc67d798955809677ae9810c05ee6990bc59c07130a8420a446904c17ee091)
BibTeX
@misc{dcc26fbfb46fa7,
title = {Micro Neural Policies for Safe Real-Time Robotic Control — arXiv:2610.08541},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08541},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c26fbfb46fa7; sha256 7cfc67d798955809677ae9810c05ee6990bc59c07130a8420a446904c17ee091},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08541. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this paper, we investigate the synthesis of Micro Neural Policies (MNP) to enable safe and robust real-time robotic control on computationally constrained embedded devices. We demonstrate that integrating Evolution Strategy (ES) and Statistical Model Checking (SMC)-based verification for policy search can drastically reduce neural network size without compromising safety and robustness. We conduct a large-scale training and evaluation of MNP on Cartpole and Quadrotor control tasks, varying control frequencies and network architectures. After validating these policies in simulation, we evaluate their deployability through zero-shot transfer to physical systems. Our experiments show that MNP can successfully achieve safe sim-to-real transfer without sacrificing control performance. We then show that the policies' memory footprint, ranging from 0.5 to 7.5 kB, allows deployment on microcontrollers, where they achieve real-time inference latency with under 25 ns of jitter while leaving the chip idle for over 97% of the time for additional workloads. This makes them a highly practical solution for severely resource-constrained robotic systems. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.08541 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.840Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).