Collaborative Research: NeTS: Small: Reliable Task Offloading in Mobile Autonomous Systems Through Semantic MU-MIMO Control

合作研究：NeTS：小型：通过语义 MU-MIMO 控制实现移动自治系统中的可靠任务卸载

• 批准号: 2134973
• 负责人: Francesco Restuccia
• 金额: $ 21万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2134973&HistoricalAwards=false
• 关键词: Collaborative; Research; NeTS; Small; Reliable

Mobile autonomous systems (MASs) such as self-driving vehicles and drones have a pivotal role in critical applications such as urban mobility, precision agriculture and remote surveillance. To achieve their tasks, MASs increasingly rely on high-throughput low-latency streaming of computer vision tasks (e.g., object detection) to edge servers. However, ephemeral environmental factors such as blockages, congestion and fading may erratically interrupt the flow of tasks to the edge servers. Existing work has addressed computation and communication issues of task offloading by MASs separately, which necessarily leads to suboptimal solutions. Task accuracy, indeed, is inevitably tied to the quality of the multimedia data being sent to the edge, which in turns depends on the adopted wireless strategy. However, the wireless parameters being used depend on the quality of data being sent (the more compression, the higher the latency), which ultimately impacts the desired task accuracy. Thus, to achieve applications that are “resilient-by-design" without compromising task accuracy, the semantics of the multimedia data must be holistically and fundamentally intertwined with real-time optimization of wireless transmissions. The core advance of this project is the design and experimental evaluation of fundamentally novel techniques for hardware-based semantic-driven joint optimization of multimedia compression strategies and MU-MIMO transmissions in the context of resource-limited wireless systems. The PIs will leverage the support of this project to involve minority and underrepresented students in research and outreach activities. As part of the project, graduate students will develop unique expertise at the crossroads of machine learning, embedded systems and wireless networks.The key technical efforts of this project will focus on the design of novel deep reinforcement learning (DRL)-based strategies that will control how the acquired data stream is compressed and wirelessly transmitted to the edge servers through MU-MIMO. The PIs will utilize techniques based on split computing to avoid increasing computational overhead due to the compression and MU-MIMO channel state information (CSI) feedback, while keeping the task accuracy close to the original. A full-fledged drone-based prototype based on customized software-defined radio (SDR) interfaces based on FPGA real-time processing and edge computing will be developed as part of the project. Large-scale data collection campaigns will be performed with a 64-antenna SDR testbed at Northeastern, a drone experimental testbed at UC Irvine, and the AERPAW PAWR platform to (i) collect the necessary wireless/multimedia data to train our algorithms; (ii) perform extensive testing and performance evaluation.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

移动自主系统（质量），例如自动驾驶车辆和无人机在关键应用中具有关键作用，例如城市移动性，精确额定商标和远程监视。为了实现其任务，质量越来越依赖于计算机视觉任务（例如对象检测）的高通量低延迟流来边缘服务器。但是，诸如阻塞，拥塞和褪色之类的短暂环境因素可能会错误地中断任务流向边缘服务器的流动。现有工作已经解决了质量分别卸载任务的计算和通信问题，这必然导致次优的解决方案。实际上，任务准确性不可避免地与发送到边缘的多媒体数据的质量相关，这反过来取决于所采用的无线策略。但是，所使用的无线参数取决于发送的数据质量（压缩越多，延迟越高），这最终会影响所需的任务准确性。为了实现在没有妥协任务准确性的情况下“逐个设计”的应用程序，多媒体数据的语义必须从整体和根本上与无线传输的实时优化相结合。该项目的核心进步是对基于硬件的语义驱动连接优化多媒体压缩策略和MU-MIMO传输的根本新技术的设计和实验评估。 PI将利用该项目的支持，涉及少数群体和代表性不足的学生从事研究和外展活动。作为该项目的一部分，研究生将在机器学习，嵌入式系统和无线网络的十字路口发展独特的专业知识。该项目的关键技术工作将集中在新型深层增强学习（DRL）基于基于的基于的深入增强策略上，这些策略将如何控制所获得的数据流如何压缩和无线传输到通过MU-Mimo通过MU-MIMO传输到Edge Server。 PIS将基于拆分计算利用技术，以避免由于压缩和MU-MIMO通道状态信息（CSI）的反馈而增加计算开销，同时使任务准确性接近原始。基于FPGA实时处理和Edge Computing基于定制软件定义的无线电（SDR）接口的全面无人机原型将作为项目的一部分开发。大规模的数据收集活动将使用在东北地区测试的64-Antenna SDR，在UC Irvine进行的无人机实验测试，以及（i）收集必要的无线/多媒体数据以训练我们的算法； （ii）进行广泛的测试和绩效评估。该奖项反映了NSF的法定任务，并使用基金会的知识分子优点和更广泛的影响审查标准，被视为值得通过评估来支持。

项目成果

Matching DNN Compression and Cooperative Training with Resources and Data Availability

• DOI: 10.1109/infocom53939.2023.10229076
• 发表时间: 2022-12
• 期刊: IEEE INFOCOM 2023 - IEEE Conference on Computer Communications
• 作者: F. Malandrino;G. Giacomo;Armin Karamzade;M. Levorato;C. Chiasserini

Edge-V : Enabling Vehicular Edge Intelligence in Unlicensed Spectrum Bands

• DOI: 10.1109/vtc2023-spring57618.2023.10199660
• 发表时间: 2023-06
• 期刊: 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring)
• 作者: F. Raviglione;C. Casetti;Francesco Restuccia

Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges

• DOI: 10.1145/3527155
• 发表时间: 2021-03
• 期刊: ACM Computing Surveys
• 影响因子: 16.6
• 作者: Yoshitomo Matsubara;M. Levorato;Francesco Restuccia

Toward Integrated Sensing and Communications in IEEE 802.11bf Wi-Fi Networks

迈向 IEEE 802.11bf Wi-Fi 网络中的集成传感和通信

• DOI: 10.1109/mcom.001.2200806
• 发表时间: 2023
• 期刊: IEEE Communications Magazine
• 影响因子: 11.2
• 作者: Meneghello, Francesca;Chen, Cheng;Cordeiro, Carlos;Restuccia, Francesco
• 通讯作者: Restuccia, Francesco

Hercules: An Emulation-Based Framework for Transport Layer Measurements over 5G Wireless Networks

Hercules：基于仿真的 5G 无线网络传输层测量框架

• DOI: 10.1145/3615453.3616516
• 发表时间: 2023
• 期刊: ACM
• 作者: Pinto, Andrea;Ashdown, Andrew;Bin Hassan, Tanzil;Cheng, Hai;Esposito, Flavio;Bonati, Leonardo;D'Oro, Salvatore;Melodia, Tommaso;Restuccia, Francesco
• 通讯作者: Restuccia, Francesco