论文标题
deeppicarmicro：将Tinyml应用于自动网络物理系统
DeepPicarMicro: Applying TinyML to Autonomous Cyber Physical Systems
论文作者
论文摘要
在微型微控制器单元（MCUS）上运行深层神经网络（DNN），由于其计算，内存和存储容量的局限性。幸运的是，MCU硬件和机器学习软件框架的最新进展使得在现代MCUS上运行相当复杂的神经网络成为可能，从而导致了一个新的研究领域，被广泛称为Tinyml。但是，很少有研究表明在网络物理系统（CPS）中使用替符的可能性。在本文中，我们提出了一种小型的自动驾驶RC汽车测试床Deeppicarmicro，它在Raspberry Pi Pico MCU上运行卷积神经网络（CNN）。我们应用最先进的DNN优化，以成功地适合著名的Pilotnet CNN体系结构，该体系结构用于在MCU上驱动Nvidia的真正自动驾驶汽车。我们应用最先进的网络体系结构搜索（NAS）方法来查找可以实时以端到端方式实时控制汽车的进一步优化网络。从一项广泛的系统实验评估研究中，我们观察到系统的准确性，延迟和控制性能之间的有趣关系。由此，我们提出了一种联合优化策略，该策略在启用AI的CPS网络体系结构搜索过程中同时遵循模型的准确性和延迟。
Running deep neural networks (DNNs) on tiny Micro-controller Units (MCUs) is challenging due to their limitations in computing, memory, and storage capacity. Fortunately, recent advances in both MCU hardware and machine learning software frameworks make it possible to run fairly complex neural networks on modern MCUs, resulting in a new field of study widely known as TinyML. However, there have been few studies to show the potential for TinyML applications in cyber physical systems (CPS). In this paper, we present DeepPicarMicro, a small self-driving RC car testbed, which runs a convolutional neural network (CNN) on a Raspberry Pi Pico MCU. We apply a state-of-the-art DNN optimization to successfully fit the well-known PilotNet CNN architecture, which was used to drive NVIDIA's real self-driving car, on the MCU. We apply a state-of-art network architecture search (NAS) approach to find further optimized networks that can effectively control the car in real-time in an end-to-end manner. From an extensive systematic experimental evaluation study, we observe an interesting relationship between the accuracy, latency, and control performance of a system. From this, we propose a joint optimization strategy that takes both accuracy and latency of a model in the network architecture search process for AI enabled CPS.
