ERI: Driving Risk-Initiated Vehicle-to-Everything Communications (DRIVEcomm)

互联和自动驾驶汽车不再是科幻小说中的未来梦想，但它们已经成为我们日常生活中的现实。在互联和自动驾驶汽车短暂而丰富的发展历史中，一个突出的范例是实现车辆之间的有效数据交换，这使得车辆到一切（V2X）通信成为家喻户晓的名字。尽管V2X通信发展迅速，但由于车辆系统的高移动性和动态性，成功交换安全消息仍然是一项艰巨的任务。更大的问题是，随着越来越多的车辆被连接和自动驾驶，交换的消息数量将爆炸式增长，这可能会降低成功传递消息的机会。为了解决这个问题，我们建议仔细定义传输信息的优先级，并相应地优先考虑车辆之间的信道访问。基于其重要性，该项目将朝着实现互联和自动驾驶汽车在现实条件下持续可靠运行的总体愿景迈出重要一步。拟议的研究活动将与教育和外联活动齐头并进，以培养下一代工程师的多学科思维。具体而言，该项目的成果（即，该项目将作为研究团队的主要资源，用于课程的现代化、促进少数族裔的招募、社区外展、本科生研究，以及与当地/国家利益相关者进一步合作，解决部署互联和自动驾驶汽车的实际问题。该项目的主要智力贡献在于以下创新方面：1）量化捕获多个风险确定特征的整体影响的“度量”; 2）将度量计算机制公式化为具有时间约束的“组合优化”问题; 3）提出“解决”所提出的组合优化问题的实用方法; 4）开发一个“测试平台”，在当前V2X用例中定义的安全消息类型中实现所提出的基于风险的优先级排序。我们将利用这些技术来证明拟议的V2X通信框架的理论性能界限，并了解其实际性能限制。因此，该项目的数学技术和经验观察将为未来关于联网和自动驾驶汽车以及智能交通系统的广泛问题的研究提供信息和支持。该奖项反映了NSF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。

Connected and autonomous vehicles are no longer a futuristic dream from science fiction, but they are already emerging as a reality in our everyday life. Throughout the short yet rich history of evolution of connected and autonomous vehicles, a salient paradigm is to accomplish the efficient data exchange among vehicles, which has made vehicle-to-everything (V2X) communications a household name. Despite the rapid evolution of V2X communications, successful exchange of safety messages still remains an ambitious task mainly due to the high mobility and dynamicity of vehicular systems. The bigger problem is that as more vehicles are connected and autonomously driven, the number of exchanged messages will explode, which will likely deteriorate the chance of successful message delivery. As an effort to address this problem, we propose to carefully define the priority of the transmitted information and prioritize channel access among vehicles accordingly. Predicated on the significance, this project will form a significant step towards the overarching vision of persistent and reliable operations of connected and autonomous vehicles in real-world conditions. The proposed research activities will go hand-in-hand with educational and outreach activities to train the next generation of engineers in multidisciplinary thinking. Specifically, the outcomes of this project (i.e., a testbed and further academic findings) will act as the research team's main resource in modernization of the courses, promotion of underrepresented minorities recruitment, community outreach, undergraduate research, and further collaboration with local/national stakeholders on resolving practical issues in deployment of connected and autonomous vehicles.The key intellectual contributions of this project lie in the following innovative aspects: 1) Quantification of a "metric" capturing the holistic impacts of multiple risk-determining features in concert; 2) Formulation of the metric computation mechanism as a "combinatorial optimization" problem with a time constraint; 3) Proposition of a practical methodology of "solving" the proposed combinatorial optimization problem; 4) Development of a "testbed" implementing the proposed risk-based prioritization among safety message types defined in current V2X use cases. We will draw from these techniques to prove theoretical performance bounds for the proposed V2X communications framework and understand its practical performance limits. Consequently, the mathematical techniques and empirical observations made by this project will inform and enable future research in a broad class of problems on connected and autonomous vehicles and intelligent transportation systems.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.