DeepPicarMicro: Applying TinyML to Autonomous Cyber Physical Systems

IF 0.5 Q4 COMPUTER SCIENCE, SOFTWARE ENGINEERING
M. Bechtel, QiTao Weng, H. Yun
{"title":"DeepPicarMicro: Applying TinyML to Autonomous Cyber Physical Systems","authors":"M. Bechtel, QiTao Weng, H. Yun","doi":"10.1109/RTCSA55878.2022.00019","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":38446,"journal":{"name":"International Journal of Embedded and Real-Time Communication Systems (IJERTCS)","volume":"46 1","pages":"120-127"},"PeriodicalIF":0.5000,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Embedded and Real-Time Communication Systems (IJERTCS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/RTCSA55878.2022.00019","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 1

Abstract

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.
deepppicarmicro:将TinyML应用于自主网络物理系统
由于微型微控制器(mcu)在计算、内存和存储容量方面的限制,在微型微控制器(mcu)上运行深度神经网络(dnn)具有挑战性。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MCU上运行相当复杂的神经网络成为可能,从而产生了一个被广泛称为TinyML的新研究领域。然而,很少有研究表明TinyML在网络物理系统(CPS)中的应用潜力。在本文中,我们介绍了DeepPicarMicro,这是一个小型自动驾驶RC汽车测试平台,它在树莓派Pico MCU上运行卷积神经网络(CNN)。我们采用了最先进的深度神经网络优化,成功地拟合了著名的PilotNet CNN架构,该架构用于在MCU上驱动NVIDIA的真正自动驾驶汽车。我们采用最先进的网络架构搜索(NAS)方法来寻找进一步优化的网络,这些网络可以以端到端方式实时有效地控制汽车。从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。基于此,我们提出了一种联合优化策略,在人工智能支持的CPS网络架构搜索过程中同时考虑模型的准确性和延迟。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
1.70
自引率
14.30%
发文量
17
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信