MLWiNS: Ultra-Reliable Collaborative Computing for Autonomous Unmanned Aerial Vehicles

MLWiNS：用于自主无人机的超可靠协作计算

• 批准号: 2003237
• 负责人: Marco Levorato
• 金额: $ 30万
• 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: 2020
• 资助国家: 美国
• 起止时间: 2020-07-01 至 2023-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2003237&HistoricalAwards=false
• 关键词: MLWiNS; Ultra; Reliable; Collaborative; Computing

Unmanned Autonomous Vehicles (UAV) are expected to play a central role in many applications of great interest, including urban and infrastructure monitoring, precision agriculture and delivery services. However, making the operations of these airborne platforms autonomous requires the execution of algorithms for the real-time analysis of the surrounding environment and mission planning. The complexity of these algorithms clashes with the inherent constraints of UAVs, whose embedded systems have limited computing power and energy supply. The proposed research aims at the development of techniques to make distributed computing ultra reliable in the context of UAV systems. The project establishes a layer of intelligence that controls in real-time how information is propagated and processed across the layers of the systems to transform sensorial input into decisions, as well as a semantic form of neural compression to significantly reduce the amount of data transported over weak wireless links. This project will have a broad impact in terms of education, mentorship and outreach. The impact of this research effort will be broadened by providing unique outreach and educational opportunities to students at the collegiate and high school level.The proposed project approaches the problem from two complementary angles: (1) designing deep reinforcement learning (RL) agents that learn to optimally communicate data across noisy channels, and (2), building novel lossy compression algorithms based on probabilistic deep learning that are specifically designed for distributed machine learning without a human in the loop. For (1), one of the key challenges resides in the multi-scale nature of the stochastic processes driving the system dynamics that present important geographical and temporal trends at different scales. An innovative hierarchical learning approach will be used to make the RL agent effective as the system dynamics evolve across time and space. For (2), novel kinds of extreme neural lossy compression algorithms based on Variational AutoEncoders (VAE) with additional supervision will be designed. Instead of focusing on signal reconstruction, the resulting compressor will aim at preserving only relevant information needed for a specified supervised learning task, leading to the new paradigm of supervised (or semantic) compression.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.

无人驾驶汽车（UAV）有望在许多令人感兴趣的应用中发挥核心作用，包括城市和基础设施监控、精准农业和配送服务。然而，使这些机载平台的操作自主化需要执行算法来实时分析周围环境和任务规划。这些算法的复杂性与无人机的固有约束相冲突，无人机的嵌入式系统具有有限的计算能力和能量供应。提出的研究旨在发展技术，使分布式计算在无人机系统的背景下超可靠。该项目建立了一个智能层，可以实时控制信息在系统各层之间的传播和处理方式，从而将感官输入转化为决策，同时还建立了一种语义形式的神经压缩，以显著减少通过弱无线链路传输的数据量。这个项目将在教育、指导和推广方面产生广泛的影响。这项研究工作的影响将通过为大学和高中的学生提供独特的外展和教育机会而扩大。提出的项目从两个互补的角度来解决这个问题：(1)设计深度强化学习（RL）代理，学习如何在有噪声的信道上最佳地通信数据；(2)构建基于概率深度学习的新型有损压缩算法，该算法专门为分布式机器学习而设计，无需人工参与。对于(1)，关键挑战之一在于驱动系统动力学的随机过程的多尺度性质，这些过程在不同尺度上呈现重要的地理和时间趋势。一种创新的分层学习方法将用于使RL代理在系统动态跨时间和空间演变时有效。(2)设计了基于附加监督的变分自编码器（VAE）的新型极端神经有损压缩算法。而不是专注于信号重建，由此产生的压缩器将旨在仅保留指定监督学习任务所需的相关信息，从而导致监督（或语义）压缩的新范式。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Optimal Task Allocation for Time-Varying Edge Computing Systems with Split DNNs

具有分割 DNN 的时变边缘计算系统的最优任务分配

• DOI: 10.1109/globecom42002.2020.9322344
• 发表时间: 2020
• 期刊: IEEE Global Communications Conference (GLOBECOM
• 作者: Callegaro, Davide;Matsubara, Yoshitomo;Levorato, Marco
• 通讯作者: Levorato, Marco

Neural Transformation Learning for Deep Anomaly Detection Beyond Images

• 发表时间: 2021-03
• 期刊: ArXiv
• 作者: Chen Qiu;Timo Pfrommer;M. Kloft;S. Mandt;Maja R. Rudolph

Intrusion Detection Framework for Invasive FPV Drones Using Video Streaming Characteristics

• DOI: 10.1145/3579999
• 发表时间: 2023-01
• 期刊: ACM Transactions on Cyber-Physical Systems
• 影响因子: 2.3
• 作者: Anas Alsoliman;Giulio Rigoni;Davide Callegaro;M. Levorato;C. Pinotti;M. Conti

Towards Empirical Sandwich Bounds on the Rate-Distortion Function

• 发表时间: 2021-11
• 期刊: ArXiv
• 作者: Yibo Yang;S. Mandt

Split Computing for Complex Object Detectors: Challenges and Preliminary Results

复杂目标检测器的分割计算：挑战和初步结果

• DOI: 10.1145/3410338.3412338
• 发表时间: 2020
• 期刊: Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning
• 作者: Yoshitomo Matsubara;M. Levorato
• 通讯作者: M. Levorato