CAREER: Conflicting Traffic Streams with Mixed Traffic: Modeling and Control

该学院早期职业发展（CAREER）资助支持理解混合自主和人为控制交通流中的交通流模式的基础研究。 新兴的互联自动驾驶汽车（CAV）技术在减少交通系统拥堵、提高安全性和提高能源效率方面具有巨大潜力。 虽然当道路上的所有车辆都是CAV时，预期效益最大，但短期内将包括混合连接车辆（CV）连接自动驾驶车辆和非连接（人类驾驶或HV）车辆。 该项目将研究混合交通流，量化其对拥堵和交通流量的影响，并制定旨在提高系统整体性能和安全性的稳健策略，从而更好地了解不同车辆类型如何在交通中相互作用。 研究结果将指导未来交通系统的道路设计、政策和长期规划的发展。 研究活动将与一系列教育和外展活动紧密结合，以有效促进智能和可持续交通。 这些活动包括：（一）开发一套工具，与研究和实践界共享（例如，（i）加强现有的工程课程;（ii）扩大妇女对STEM的参与;（iii）向广泛的受众提供外展服务，包括K-12学生和教师以及跨部门研究社区。该项目的研究目标是：（i）描述在冲突交通流中HV和CAV的驾驶行为，（ii）混合交通对交通流的集体影响，以及（iii）研究CAV的鲁棒战术级控制策略，以提高系统在吞吐量、交通流稳定性和安全性方面的性能。 该研究涉及使用驾驶模拟器和现场测试的数据收集，建立不同车型的行为模型（即，CAV、CV和HV），并使用基于规则和基于人工智能（AI）的控制方法设计和评估战术级控制策略。本研究将揭示在冲突交通流的背景下，CAV的合作行为以及HV和CV在合作下的行为。 该研究有望为混合业务的CTS提供有效的控制策略。该推广计划将为高中学生和教师提供接触大学虚拟驾驶实验室以及新兴交通系统研究挑战的机会。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

This Faculty Early Career Development (CAREER) grant supports fundamental research in understanding of traffic flow patterns in mixed autonomous and human-controlled traffic streams. Emerging connected automated vehicle (CAV) technologies hold enormous potential to reduce transportation system congestion, improve safety, and facilitate higher energy efficiency. While anticipated benefits are greatest when all vehicles on the roads are CAVs, the near-term future will consist of mixed connected vehicles (CVs) connected automated vehicles and non-connected (human-driven, or HV) vehicles. This project will study mixed traffic streams, quantifying their impact on congestion and traffic flow, and develop robust strategies intended to improve performance and safety of the system as a whole, thereby enabling better understanding of how different vehicle types interact in traffic. The results will guide the development of roadway design, policies, and long-term planning for future transportation systems. The research activities will be closely integrated with a set of education and outreach activities to effectively promote smart and sustainable transportation. These activities include (i) developing a set of tools that will be shared with the research and practice communities (e.g., portable driving simulators, and an open-sourced micro-simulation platform), (ii) enhancing existing engineering curricula, (iii) broadening participation of women in STEM, and (iv) providing outreach to a broad audience, including K-12 students and teachers as well as cross-sector research communities. The research objectives of this project are to (i) characterize the driving behaviors of HVs and CAVs in conflicting traffic streams, (ii) the collective impact of mixed traffic on the traffic flow, and (iii) investigate robust tactical-level control strategies for CAVs to improve system performance with respect to throughput, traffic flow stability, and safety. The research involves data collection on using driving simulators and field tests, establishment of behavior models for different vehicle types (i.e., CAVs, CVs, and HVs) based on the collected data, and design and evaluation of tactical level control strategies using rule-based and Artificial Intelligent (AI)-based control approaches. This research will uncover the cooperative behavior of CAVs and the behavior of HVs and CVs under cooperation in the context of conflicting traffic streams. The research is expected to produce effective control strategies for CTS with mixed traffic. The outreach plan will provide high school students and teachers with exposure to the university's virtual driving lab as well as to research challenges in emerging 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.