CPS: Medium: Collaborative Research: Transforming Connected and Automated Transportation with Smart Networking, Cooperative Sensing, and Edge Computing

这笔NSF网络物理系统(CPS)拨款将通过在网络、传感和计算三个关键领域以及它们之间的协同作用方面的创新，推动互联和自动化车辆(CAV)系统的最先进水平。这项工作利用了几个预计将改变地面交通系统的新兴技术趋势：更高速度的无线连接、改进的车载和基于基础设施的传感能力，以及机器学习算法的进步。到目前为止，大多数相关的研究和开发都集中在个别技术上，导致效益有限。该项目将开发一个综合平台，通过解决与CAV运营条件相关的关键挑战，共同处理网络、传感和计算：例如，安全关键、高移动性、稀缺的车载计算资源、波动的网络条件、有限的传感器能力。研究团队将研究如何使用集成平台来实现现实世界的CAV应用，例如增强公共服务人员的安全、缓解瓶颈地区的拥堵以及保护脆弱的道路使用者(VRU)。鉴于其跨学科性质，该项目将在包括交通工程、移动/边缘计算和机器学习在内的多个研究社区产生广泛影响。这项研究的结果将使CAV生态系统中的多个利益相关者受益：司机、行人、CAV制造商、交通政府机构、移动网络运营商等，最终提高国家交通系统的安全性和机动性。该项目还将提供开展各种教育和外联活动的平台。这项研究的智力核心包括对地面交通CPS领域的几个基础性贡献。首先，它通过战略性地聚合4G/5G/WiFi/DSRC技术来创新车辆到一切(V2X)通信，以增强网络性能。其次，提出了一种协同感知和感知框架，在该框架中，附近的车辆可以与边缘节点共享原始传感器数据，以创建全局视图，从而提供扩展的感知范围和遮挡对象的检测。关键的技术贡献是确保良好的可扩展性-允许许多移动车辆在有限的、波动的网络资源的情况下高效地共享数据。第三，它支持在车辆和基础设施之间划分计算，以满足CAV应用的实时要求。第四，集成上述网络、传感和计算的构建块，研究团队将开发一个优化框架，该框架将对需要在哪种质量下执行什么计算做出适应性、资源感知的决策，以最大限度地提高CAV应用程序的服务质量。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This NSF Cyber-Physical Systems (CPS) grant will advance the state-of-the-art of Connected and Automated Vehicle (CAV) systems by innovating in the three key areas of networking, sensing, and computation, as well as the synergy among them. This work leverages several emerging technology trends that are expected to transform the ground transportation system: much higher-speed wireless connectivity, improved on-vehicle and infrastructure based sensing capabilities, and advances in machine learning algorithms. So far, most related research and development focused on individual technologies, leading to limited benefits. This project will develop an integrated platform that jointly handles networking, sensing, and computation, by addressing key challenges associated with the operating conditions of the CAVs: e.g., safety-critical, high mobility, scarce on-board computing resources, fluctuating network conditions, limited sensor capabilities. The research team will study how to use the integrated platform to enable real-world CAV applications, such as enhancement of public service personnel's safety, alleviation of congestion at bottleneck areas, and protection of vulnerable road users (VRUs). Given its interdisciplinary nature, this project will yield a broad impact in multiple research communities including transportation engineering, mobile/edge computing, and machine learning. The outcome of this research will benefit multiple stakeholders in the CAV ecosystem: drivers, pedestrians, CAV manufacturers, transportation government agencies, mobile network carriers, etc., ultimately improving the safety and mobility of the nation's transportation system. This project will also provide a platform to conduct various education and outreach activities. The intellectual core of this research consists of several foundational contributions to the ground transportation CPS domain. First, it innovates vehicle-to-everything (V2X) communications through strategically aggregating 4G/5G/WiFi/DSRC technologies to enhance network performance. Second, it develops a cooperative sensing and perception framework where nearby vehicles can share raw sensor data with an edge node to create a global view, which can provide extended perceptual range and detection of occluded objects. The key technical contribution is to ensure good scalability - allowing many moving vehicles to efficiently share their data despite limited, fluctuating network resources. Third, it enables partitioning computation across vehicles and the infrastructure to meet the real-time requirements of CAV applications. Fourth, integrating the above building blocks of networking, sensing, and computation, the research team will develop an optimization framework that makes adaptive, resource-aware decisions on what computation needs to be performed where at which quality, to maximize the service quality of CAV applications.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.