CPS Medium: Cooperative Driving in Heterogeneous Traffic of Manned and Unmanned Vehicles

这一网络物理系统(CPS)项目将开发一个理论框架，以促进在人类操作和自动操作的车辆的不同交通中的安全协作驾驶，并通过模拟和物理实验来证明其可行性。该项目将有助于提高目前正在由具有日益增长的自动驾驶功能的车辆改造的交通系统的安全性。通过将附加设备或副驾驶引入传统的人类驾驶车辆，该项目将提供一种智能驾驶助手，它可以感知驾驶员的行为，并在车辆处于危险中时向驾驶员发出警报。在进行合作驾驶时，副驾驶会提供建议，以减少与附近车辆相撞的机会。通过促进新兴自动驾驶汽车和传统人类驾驶汽车的合作驾驶，该项目将培养公众对自动驾驶的积极态度，从而加快自动驾驶汽车进入交通系统的步伐。教育和推广活动将提高年轻一代对自动驾驶、人工智能(AI)和机器人技术的更多认识，并刺激潜在学生在科学和工程领域攻读学位和职业。这项研究探索了由人工操作的车辆和自主操作的车辆组成的网络-物理-人类系统的协作控制的挑战性问题。首先，通过利用机器学习技术，本研究将开发一种集成的数据驱动、基于模型的方法来模拟不同级别的人和机器控制的车辆驾驶行为。该模型融合了外部风险和驾驶员行为，通过一种新的车辆反应模型来推断车辆的预期动作。其次，这项研究将为合作驾驶开发一个统一的决策框架，利用人和机器在感知、分析和控制方面的差异，为自动驾驶车辆和司机提供实时建议，以增强安全性。这样的框架可以扩展到其他类别的联网网络-物理-人类系统，其中向人类操作员提供的智能建议可以促进协作并增强系统级的性能和安全。第三，本研究将开发模拟和物理试验台，用于对理论框架进行实验评估。最后，这项研究将把现有的合作自动化研究移动应用平台扩展到自动驾驶汽车和传统汽车，这将允许研究人员研究未来智能交通系统中涉及人和机器的新问题。这一奖项反映了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 Cyber Physical Systems (CPS) project will develop a theoretical framework that facilitates safe cooperative driving in heterogeneous traffic of human-operated and autonomously-operated vehicles and demonstrate its feasibility through both simulation and physical experiments. This project will help improve the safety of a transportation system currently being transformed by vehicles with growing autonomous features. By introducing an add-on device, or copilot, into legacy human-driven vehicles, this project will offer a smart driving assistant that is aware of the driver's behaviors and can alert the driver when the vehicle is at risk. When engaged in cooperative driving, the copilot will provide advice that reduces the chance of collision with nearby vehicles. By facilitating cooperative driving for both emerging autonomous vehicles and legacy human-driven vehicles, this project will foster a positive attitude of the public toward autonomous driving, therefore accelerating the adoption of autonomous vehicles into the transportation system. The education and outreach activities will raise more awareness of autonomous driving, Artificial Intelligence (AI) and robotics to the younger generation, and stimulate prospective students to pursue degrees and careers in science and engineering. This research explores the challenging problem of cooperative control of a cyber-physical-human system consisting of both human-operated and autonomously-operated vehicles. First, by leveraging machine learning technologies, this research will develop an integrated data-driven, model-based approach to modeling vehicle driving behaviors with various levels of human and machine control. New machine learning models of human driving behaviors in the presence and absence of copilot's advice will be built, which fuse both external risks and driver's behavior to infer vehicle's intended maneuvers through a novel vehicle reaction model. Second, this research will develop a unified decision framework for cooperative driving that leverages the differences between humans and machines in sensing, analytics, and control to produce real-time advice to autonomous vehicles and drivers for enhanced safety. Such a framework can be extended to other classes of networked cyber-physical-human systems, where intelligent advice to human operators can facilitate collaboration and enhance system level performance and safety. Third, this research will develop both simulated and physical testbeds for experimental evaluation of the theoretical framework. Finally, this research will expand the existing Cooperative Automation Research Mobility Applications platform to both autonomous vehicles and legacy vehicles, which will allow researchers to study new problems in future intelligent transportation systems that involve both humans and machines.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.