# 面向安全实时机器人控制的 Micro Neural Policies

> 原文链接：https://robotics.hellobike.com/papers/2026-10-06-2610-08541
> 频道：papers | 更新日期：2026-10-06 | 标签：arxiv, cs.RO
> 核心摘要：针对受限嵌入式设备上的安全实时控制，结合ES与SMC验证搜索MNP，并在Cartpole、Quadrotor及物理系统上验证。

# 面向安全实时机器人控制的 Micro Neural Policies

::: v-pre
> 原文链接：[Micro Neural Policies for Safe Real-Time Robotic Control](https://arxiv.org/abs/2610.08541)（arXiv 2610.08541 · 发布日期：2026-10-06）

**Micro Neural Policies for Safe Real-Time Robotic Control**

针对受限嵌入式设备上的安全实时控制，结合ES与SMC验证搜索MNP，并在Cartpole、Quadrotor及物理系统上验证。

## 核心要点

- 目标是在计算受限嵌入式设备上实现安全、鲁棒的实时机器人控制。
- 将Evolution Strategy与SMC验证结合进行策略搜索，以显著缩小神经网络规模。
- 在Cartpole和Quadrotor任务上大规模训练评估，覆盖不同控制频率和网络结构。
- 仿真后零样本迁移到物理系统，并可在微控制器上实现实时推理与低抖动。

**验证范围与局限**：验证范围为Cartpole和Quadrotor控制任务，先在仿真中验证，再零样本迁移到物理系统。

## 英文摘要 (Abstract)

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.

作者：Hongpeng Cao, Riccardo Curcio, Daniele Ottaviano, Marco Caccamo
:::

## 原始参考来源 (Sources)

- [arXiv 2610.08541：Micro Neural Policies for Safe Real-Time Robotic Control](https://arxiv.org/abs/2610.08541)