发表机构
Sapienza University of Rome; Technical University of Munich（罗马大学; 慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出微型神经策略，通过进化策略与统计模型检验集成，实现安全实时控制，并在微控制器上高效部署。
AI 中文摘要
本文研究了微型神经策略（MNP）的合成，以在计算受限的嵌入式设备上实现安全且鲁棒的实时机器人控制。我们证明了将进化策略（ES）和基于统计模型检验（SMC）的验证集成到策略搜索中，可以大幅减小神经网络规模，同时不牺牲安全性和鲁棒性。我们在Cartpole和Quadrotor控制任务上进行了大规模的训练和评估，并变化了控制频率和网络架构。在仿真中验证这些策略后，我们通过零样本迁移到物理系统来评估其可部署性。实验表明，MNP能够成功实现安全的仿真到现实迁移，而不牺牲控制性能。随后，我们展示了策略的内存占用范围在0.5至7.5 kB之间，允许部署在微控制器上，在那里它们实现了实时推理延迟，抖动低于25纳秒，同时芯片空闲时间超过97%，可用于额外工作负载。这使得它们成为严重资源受限机器人系统的高度实用解决方案。
英文摘要
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.
Comments9 pages
