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: 2134567
• 负责人: Marco Levorato
• 金额: $ 20.5万
• 依托单位: University of California-Irvine
• 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=2134567&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.

自动驾驶汽车和无人机等移动的自主系统（MAS）在城市交通、精准农业和远程监控等关键应用中发挥着关键作用。为了实现其任务，MAS越来越依赖于计算机视觉任务的高吞吐量低延迟流传输（例如，对象检测）到边缘服务器。然而，短暂的环境因素，如阻塞，拥塞和衰落可能会不规律地中断到边缘服务器的任务流。现有的工作已经解决了计算和通信问题的任务卸载MAS分别，这必然导致次优的解决方案。事实上，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有关，而多媒体数据的质量又取决于所采用的无线策略。然而，使用的无线参数取决于发送的数据质量（压缩越多，延迟就越高），这最终会影响所需的任务准确性。因此，要实现应用程序，是“服从设计”，而不损害任务的准确性，多媒体数据的语义必须从整体上和根本上交织在一起的实时优化的无线传输。该项目的核心进展是在资源有限的无线系统的背景下，基于硬件的语义驱动的多媒体压缩策略和MU-MIMO传输的联合优化的根本性新技术的设计和实验评估。PI将利用该项目的支持，让少数民族和代表性不足的学生参与研究和推广活动。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交叉点上发展独特的专业知识，该项目的关键技术工作将集中在基于深度强化学习（DRL）的新型策略的设计上，该策略将控制获取的数据流如何通过MU-MIMO压缩并无线传输到边缘服务器。PI将利用基于拆分计算的技术来避免由于压缩和MU-MIMO信道状态信息（CSI）反馈而增加的计算开销，同时保持任务精度接近原始。作为该项目的一部分，将开发基于FPGA实时处理和边缘计算的定制软件定义无线电（SDR）接口的成熟无人机原型。大规模的数据收集活动将使用东北大学的64天线SDR测试平台、加州大学欧文分校的无人机实验平台和AERPAW PAWR平台进行，以（i）收集必要的无线/多媒体数据来训练我们的算法;（二）执行广泛的测试和性能评估。该奖项反映了NSF的法定使命，并已被认为是值得通过评估使用基金会的知识优点和更广泛的影响审查标准。

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

State-Recovery Protocol for URLLC Applications in 5G Systems

5G 系统中 URLLC 应用的状态恢复协议

• DOI: 10.1109/wisnet56959.2023.10046219
• 发表时间: 2023
• 期刊: IEEE Topical Conference on Wireless Sensors and Sensor Networks (IEEE WiSNet
• 作者: Alsoliman, Anas;Abkenar, Forough Shirin;Levorato, Marco
• 通讯作者: Levorato, Marco

SmartDet: Context-Aware Dynamic Control of Edge Task Offloading for Mobile Object Detection

• DOI: 10.1109/wowmom54355.2022.00034
• 发表时间: 2022-01
• 期刊: 2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)
• 作者: Davide Callegaro;Francesco Restuccia;M. Levorato

Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks

• DOI: 10.1109/dyspan53946.2021.9677132
• 发表时间: 2021-12
• 期刊: 2021 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN)
• 作者: Peyman Tehrani;Francesco Restuccia;M. Levorato

SplitBeam: Effective and Efficient Beamforming in Wi-Fi Networks Through Split Computing

• DOI: 10.1109/icdcs57875.2023.00081
• 发表时间: 2023-07
• 期刊: 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS)
• 作者: Niloofar Bahadori;Yoshitomo Matsubara;Marco Levorato;Francesco Restuccia