Camera calibration and vehicle tracking: Highway traffic video analytics

We describe a real-time highway surveillance system (RHSS), which operates autonomously to collect statistics (speed and volume) and generates incident alerts (e.g., stopped vehicles). The system is designed to optimize long-term real-time performance accuracy. It also provides convenient integration to an existing surveillance infrastructure with different levels of service. Innovations include a novel 3-D Hungarian algorithm which is utilized for object tracking and a practical, hands-off mechanism for camera calibration. Speed is estimated based on trajectories after mapping/alignment with respect to dominant paths learned based on an evolutionary dynamics model. The system, RHSS, is intensively evaluated under different scenarios such as rain, low-contrast and high-contrast lightings. Performance is presented in comparison to a current commercial product. The contribution is innovation of new technologies that enable hands-off calibration (i.e., automatic detection of vanishing points) and improved accuracy (i.e., illumination balancing, tracking via a new 3-D Hungarian algorithm, and re-initialization of background detection on-the-fly). Results indicate the capability and applicability of the proposed system in real-time and real-world settings.     

交通流特征深度认知的车队运行参数优化方法

为提升车队对周围交通流环境的认知能力，获取车队周围多车的运行模式，同时通过改变车队运行参数实现车队群体对周围多车群体运行模式的诱导变化，为提升车队及交通流整体运行效率提供优化策略，提出了基于狄利克雷混和高斯过程的车队周围多车运行模式获取算法，将车队周围多车车辆的复杂运行模式视为混和高斯过程，利用狄利克雷分布作为高斯混和权重的先验分布，建立车队周围多车运行模式速度场，从而获取车队周围多车运行模式并分类；通过比较不同多车运行模式下车队的运行效率，提升车队对所处运行环境的认知能力。研究结果表明：利用非参数贝叶斯算法将复杂的多车运行状态进行分类，获取的车队周围多车运行模式可表现为对车队运行效率产生不同影响的速度场；通过将车队周围的多车运行仿真数据分成多个运行模式，可获取不同多车运行模式下车队及交通流整体运行特性；通过更改车队运行参数，观察不同多车运行模式的占比变化，可获取车队运行参数对所处运行环境改变的影响趋势；车队周围多车运行模式的获取，不仅可以提升车队对周围运行环境的认知能力，使得车队能够选取有利路径行驶，同时能够为车队运行策略的优化提供有效的信息。     

用于智能驾驶系统评价的乘员损伤模型

只有较少的交通事故数据资源被用于建立基于碰撞速度信息的乘员损伤模型，致使所得到的模型精度差。为此，提出了基于车辆变形深度的乘员损伤模型。对美国不同制造年代和车辆级别的事故数据进行聚类分析，论证出车辆变形深度与乘员损伤风险具有相关性。以车辆变形深度为自变量，通过回归分析得到乘员损伤模型。不同种类车辆的乘员损伤模型拟合精度R²约为0.9，证明了该模型的正确性。为进一步验证，以此模型为基础，评价智能驾驶系统的有效性。以自动紧急制动系统为例，对比基于变形深度和速度变化量信息2种方法的有效性计算结果。结果表明：2组结果的平均误差不超过1%，验证了基于变形深度的乘员损伤模型的准确性。该模型仅需要事故数据库中准确的变形深度信息，能够获得更多的事故数据支持，从而可以更好地适应于不同类别智能驾驶系统的评价需求。     

Roads in transition: Integrated modeling of a manufacturer-traveler-infrastructure system in a mixed autonomous/human driving environment

This paper develops an integrated model to characterize the market penetration of autonomous vehicles (AVs) in urban transportation networks. The model explicitly accounts for the interplay among the AV manufacturer, travelers with heterogeneous values of travel time (VOTT), and road infrastructure capacity. By making in-vehicle time use more leisurely or productive, AVs reduce travelers’ VOTT. In addition, AVs can move closer together than human-driven vehicles because of shorter safe reaction time, which leads to increased road capacity. On the other hand, the use of AV technologies means added manufacturing cost and higher price. Thus, traveler adoption of AVs will trade VOTT savings with additional out-of-pocket cost. The model is structured as a leader (AV manufacturer)-follower (traveler) game. Given the cost of producing AVs, the AV manufacturer sets AV price to maximize profit while anticipating AV market penetration. Given an AV price, the vehicle and routing choice of heterogeneous travelers are modeled by combining a multinomial logit model with multi-modal multi-class user equilibrium (UE). The overall problem is formulated as a mathematical program with complementarity constraints (MPCC), which is challenging to solve. We propose a solution approach based on piecewise linearization of the MPCC as a mixed-integer linear program (MILP) and solving the MILP to global optimality. Non-uniform distribution of breakpoints that delimit piecewise intervals and feasibility-based domain reduction are further employed to reduce the approximation error brought by linearization. The model is implemented in a simplified Singapore network with extensive sensitivity analyses and the Sioux Falls network. Computational results demonstrate the effectiveness and efficiency of the solution approach and yield valuable insights about transportation system performance in a mixed autonomous/human driving environment.     

Influence of connected and autonomous vehicles on traffic flow stability and throughput

The introduction of connected and autonomous vehicles will bring changes to the highway driving environment. Connected vehicle technology provides real-time information about the surrounding traffic condition and the traffic management center’s decisions. Such information is expected to improve drivers’ efficiency, response, and comfort while enhancing safety and mobility. Connected vehicle technology can also further increase efficiency and reliability of autonomous vehicles, though these vehicles could be operated solely with their on-board sensors, without communication. While several studies have examined the possible effects of connected and autonomous vehicles on the driving environment, most of the modeling approaches in the literature do not distinguish between connectivity and automation, leaving many questions unanswered regarding the implications of different contemplated deployment scenarios. There is need for a comprehensive acceleration framework that distinguishes between these two technologies while modeling the new connected environment. This study presents a framework that utilizes different models with technology-appropriate assumptions to simulate different vehicle types with distinct communication capabilities. The stability analysis of the resulting traffic stream behavior using this framework is presented for different market penetration rates of connected and autonomous vehicles. The analysis reveals that connected and autonomous vehicles can improve string stability. Moreover, automation is found to be more effective in preventing shockwave formation and propagation under the model’s assumptions. In addition to stability, the effects of these technologies on throughput are explored, suggesting substantial potential throughput increases under certain penetration scenarios.     

基于多维信息特征分析的驾驶人认知负荷研究

准确评估驾驶人认知负荷水平，对于深入研究驾驶人行为特性，改善驾驶安全性具有重要意义。现有的驾驶人认知负荷分类方法，大多基于心电、脑电等生理信息和车辆信息，由于特征选择上的单一性，导致驾驶人认知负荷分类模型的分类精度不高。设计基于跟驰场景的不同认知负荷N-back次任务试验，通过采集受试者的生理信号和车辆信号，结合NASA_TLX主观评分和机器学习算法，提出了基于多维信息特征融合的驾驶人认知负荷分类方法。研究表明：基于生理信息和车辆信息的多维信息特征认知负荷分类方法，其精度显著高于传统的基于生理信息的认知负荷分类方法，以多维信息特征为输入，随机森林法以其稳定性好、抗过拟合能力强的特点，表现出优异的分类效果，相比神经网络和支持向量机，具有最高的平均分类精度。     

铁道车辆轴箱弹簧断裂故障对动力学性能的影响

车辆运行过程中,当轴箱弹簧突发断裂故障,会造成动力学状态和性能突变,一系悬挂刚度突然减小,暂时失去承载能力,会威胁车辆行车安全。结合整车的动力学仿真,建立了轴箱弹簧断裂过程的力学模型,对整个断裂过程进行仿真,模拟了轴箱弹簧突然断裂工况下车辆动力学性能变化,分析了轴箱弹簧断裂条件下车辆直线行车安全性以及曲线通过安全性。计算分析结果表明:轴箱弹簧突然断裂导致一系悬挂刚度剧变,引起轮轨垂向力先减小后增大,轮重减载率、脱轨系数等参数增大直至超限,但对轮轨横向力影响不大。     

Scheduling of Intelligent and Autonomous Vehicles under pairing/unpairing collaboration strategy in container terminals

A new class of Intelligent and Autonomous Vehicles (IAVs) has been designed in the framework of Intelligent Transportation for Dynamic Environment (InTraDE) project funded by European Union. This type of vehicles is technologically superior to the existing Automated Guided Vehicles (AGVs), in many respects. They offer more flexibility and intelligence in maneuvering within confined spaces where the logistic operations take place. This includes the ability of pairing/unpairing enabling a pair of 1-TEU (20-foot Equivalent Unit) IAVs dynamically to join, transport containers of any size between 1-TEU and 1-FFE (40-foot Equivalent) and disjoin again. Deploying IAVs helps port operators to remain efficient in coping with the ever increasing volume of container traffic at ports and eliminate the need for deploying more 40-ft transporters in the very confined area of ports. In order to accommodate this new feature of IAVs, we review and extend one of the existing mixed integer programming models of AGV scheduling in order to minimize the makespan of operations for transporting a set of containers of different sizes between quay cranes and yard cranes. In particular, we study the case of Dublin Ferryport Terminal. In order to deal with the complexity of the scheduling model, we develop a Lagrangian relaxation-based decomposition approach equipped with a variable fixing procedure and a primal heuristics to obtain high-quality solution of instances of the problem.     

螺旋匝道和螺旋桥的小客车行驶速度特征

为明确螺旋匝道和螺旋桥处的驾驶行为模式和汽车运行特征，在涪陵长江一桥、乌江二桥、重庆融侨大道和涪陵金凯环形高架4处地点开展螺旋匝道实车试验，用车载仪器采集自然驾驶状态下的汽车连续行驶轨迹、速度以及周围行驶环境等信息。基于自然驾驶数据，研究螺旋匝道范围内的速度变化模式、幅值特性以及影响因素。研究结果表明：单车道螺旋匝道的速度变化模式多样化，双车道螺旋匝道的行驶速度在整体上维持稳定，匝道范围内的连续升坡和降坡并未导致速度出现趋势性衰减和趋势性升高；螺旋匝道并入主线时，驾驶人在合流鼻之前有明显的、共性的减速行为，这与现行设计标准中的设计假定相反；除涪陵长江一桥之外，其余3处都是下行速度低于上行速度；螺旋匝道设计速度越低，实测速度与设计速度之间的偏离越严重，并且速度幅值离散化，因此不建议使用20 km·h^-1的匝道设计速度；螺旋匝道运行速度与匝道半径成正相关。     

77G毫米波雷达ADAS应用及方案分析

深入挖掘国际期刊和知名研究机构的文献,向广大读者介绍最新的汽车毫米波雷达技术和原理,收集了较为全面的77G毫米波雷达在高级辅助驾驶和自动驾驶中的应用功能。梳理出雷达性能和应用功能之间的对用关系,同时对比了毫米波雷达和其他最新车载空间传感器之差异和优势。并将上述信息结合最新的三家主力半导体公司的汽车毫米波雷达硬件方案加以分析,提出在选择方案时如何在性能、技术特点和功能应用方面考虑。主要结论:毫米波雷达将是未来自动驾驶汽车空间传感器的基础和重要发展方向。