Optimal control of motorsport differentials

Modern motorsport limited slip differentials (LSD) have evolved to become highly adjustable, allowing the torque bias that they generate to be tuned in the corner entry, apex and corner exit phases of typical on-track manoeuvres. The task of finding the optimal torque bias profile under such varied vehicle conditions is complex. This paper presents a nonlinear optimal control method which is used to find the minimum time optimal torque bias profile through a lane change manoeuvre. The results are compared to traditional open and fully locked differential strategies, in addition to considering related vehicle stability and agility metrics. An investigation into how the optimal torque bias profile changes with reduced track-tyre friction is also included in the analysis. The optimal LSD profile was shown to give a performance gain over its locked differential counterpart in key areas of the manoeuvre where a quick direction change is required. The methodology proposed can be used to find both optimal passive LSD characteristics and as the basis of a semi-active LSD control algorithm.     

高速公路相机自动标定及道路坐标系构建

为解决高速公路场景下利用视频监控系统正确描述车辆相对于道路的空间位置问题，通过引入Frenet坐标系概念，提出一种基于相机自动标定的道路坐标系模型。在相机自动标定阶段，利用线分段拟合方法从曲线车辆轨迹中提取平行于直线路段的轨迹点，并通过级联霍夫变换精确估计道路方向的消失点。然后,根据多车辆三维模型约束，对相机参数进行迭代优化。基于标定结果，将车辆轨迹映射到世界坐标系平面上，并用3次样条插值进行拟合。根据大量运动车辆在道路平面内形成的轨迹域分布特征，综合边界约束估计道路中心点。最后，结合道路中心线在各点处的法线向量与车道宽度信息确定平移量，并利用点平移运动拟合车道线，实现道路坐标系的自动建立。使用真实高速公路视频数据，在多种道路条件下进行试验。研究结果表明:在标定阶段，构建方法对不同高速公路场景的最大标定误差不超过11.55%;与最新的方法相比，直线道路平均标定误差分别降低6.68%和3.58%，弯曲道路平均标定误差分别降低7.43%和2.61%;在道路坐标系构建阶段，构建方法的平均投影距离为0.077 m，接近最新方法的0.069 5 m；而其平均精度为0.916，显著优于最新方法的0.663；所提道路坐标系能够自适应道路形态的变化，有效解决了从监控视频中描述车辆与道路之间相对位置关系的问题。     

识别驾驶人意图的车道偏离防避有界控制

为了防止车辆偏离车道导致交通事故的发生和避免车道偏离防避系统（Lane Departure Avoidance Systems,LDAS）对驾驶人行为不必要的干预,提出基于中心区操纵特性阈值法和基于D-S（Dempster-Shafer）证据理论的车辆偏离车道驾驶人意图识别准则,并运用CarSim/Simulink联合仿真对比2种识别准则的有效性。建立转向盘角速度为输入的车路模型,设计LDAS滑模转向控制器,基于预瞄点的侧向偏移量和横摆角速度设计LDAS的期望横摆角速度观测器,并与基于道路曲率和预瞄点侧向偏移量的期望横摆角速度的LDAS进行性能对比。运用相平面法确定保证LDAS车辆稳定性的前轮转向角最大值,并基于CarSim/LabVIEW RT硬件在环试验平台验证基于BP神经网络训练获得D-S证据理论的初始概率赋值的驾驶人意图决策算法的有效性。结果表明：所提出的识别准则能够及时识别车辆偏离车道时的驾驶人意图,为LDAS控制器介入赢得了宝贵的时间,所设计的期望横摆角速度观测器具有很好的稳定性,所提出的方法能够有效避免车辆偏离车道。     

Vision-based fusion of robust lane tracking and forward vehicle detection in a real driving environment

With the goal of developing an accurate and fast lane tracking system for the purpose of driver assistance, this paper proposes a vision-based fusion technique for lane tracking and forward vehicle detection to handle challenging conditions, i.e., lane occlusion by a forward vehicle, lane change, varying illumination, road traffic signs, and pitch motion, all of which often occur in real driving environments. First, our algorithm uses random sample consensus (RANSAC) and Kalman filtering to calculate the lane equation from the lane candidates found by template matching. Simple template matching and a combination of RANSAC and Kalman filtering makes calculating the lane equation as a hyperbola pair very quick and robust against varying illumination and discontinuities in the lane. Second, our algorithm uses a state transfer technique to maintain lane tracking continuously in spite of the lane changing situation. This reduces the computational time when dealing with the lane change because lane detection, which takes much more time than lane tracking, is not necessary with this algorithm. Third, false lane candidates from occlusions by frontal vehicles are eliminated using accurate regions of the forward vehicles from our improved forward vehicle detector. Fourth, our proposed method achieved robustness against road traffic signs and pitch motion using the adaptive region of interest and a constraint on the position of the vanishing point. Our algorithm was tested with image sequences from a real driving situation and demonstrated its robustness.     

考虑拥堵空间排队与溢出的道路网静态交通流分配

为刻画拥堵空间排队与溢出现象对交通流分配的影响，提出考虑拥堵空间排队与溢出的道路网静态交通流分配问题，并构建相关的求解算法，用于描述交通需求在起讫点移动过程中路网整体的宏观运行状态。首先，丰富和完善考虑拥堵空间排队与溢出的静态交通流分配的相关假设，提出次生瓶颈、拥堵干扰与渗透和分段化路段阻抗等基本概念和理论，来刻画拥堵交通瓶颈、拥堵空间排队等交通现象；其次，建立网络瓶颈识别算法和空间排队回溯算法，基于此构建考虑拥堵空间排队和溢出的增量分配算法，用于求解交通流分配的结果；最后，通过使用一个具有说明型的算例进行对比分析。研究结果表明：建立的瓶颈识别、排队回溯和增量分配算法可以识别路网中的瓶颈位置及其拥堵排队区域，并可计算得到各路段上的分段分配流量；与点排队只影响瓶颈路段的运行状况和均一的路段分配结果相比，可有效描述路网整体的宏观运行状态以及由于拥堵空间排队所导致的拥堵干扰与渗透现象；不同于“时间片”的伪动态交通流分配模型，新建算法的分配结果是“全时段”与“整体性”的路网宏观运行状态，包含了拥堵瓶颈的具体位置和空间排队的干扰与渗透情况；一般拥堵点排队模型和基于“时间片”的拥堵空间排队模型难以刻画拥堵干扰与渗透现象以及路网整体的宏观运行状态，故所建立的分配方法是对传统拥堵交通流分配的丰富和发展。     

Robust traffic assignment model: Formulation,solution algorithms and empirical application

ABSTRACT

The deterministic traffic assignment problem based on Wardrop's first criterion of traffic network utilization has been widely studied in the literature. However, the assumption of deterministic travel times in these models is restrictive, given the large degree of uncertainty prevalent in urban transportation networks. In this context, this paper proposes a robust traffic assignment model that generalizes Wardrop's principle of traffic network equilibrium to networks with stochastic and correlated link travel times and incorporates the aversion of commuters to unreliable routes.

The user response to travel time uncertainty is modeled using the robust cost (RC) measure (defined as a weighted combination of the mean and standard deviation of path travel time) and the corresponding robust user equilibrium (UE) conditions are defined. The robust traffic assignment problem (RTAP) is subsequently formulated as a Variational Inequality problem. To solve the RTAP, a Gradient Projection algorithm is proposed, which involves solving a series of minimum RC path sub-problems that are theoretically and practically harder than deterministic shortest path problems. In addition, an origin-based heuristic is proposed to enhance computational performance on large networks. Numerical experiments examine the computational performance and convergence characteristics of the exact algorithm and establish the accuracy and efficiency of the origin-based heuristic on various real-world networks. Finally, the proposed RTA model is applied to the Chennai road network using empirical data, and its benefits as a normative benchmark are quantified through comparisons against the standard UE and System Optimum (SO) models.     

高速路网不停车收费车道优化布设方法

合理设置高速公路收费站ETC (Electronic Toll Collection)车道数量，对高速公路通行效率至关重要。针对目前路网中ETC与MTC (Manual Toll Collection)车辆混行的情况，考虑ETC的普及率，结合多用户路网均衡模型和排队论方法，建立基于双层规划模型的高速路网ETC车道优化布设方法。上层模型以车辆总通行时间最小为目标，优化设置进出收费站的ETC车道数量；下层模型为多用户路网均衡模型，反映ETC和MTC车辆的路径和收费车道选择行为。下层模型通过设计收费站的等价拓扑结构，表征收费站的车道使用规则及车辆的收费车道选择行为，并采用排队论方法估计ETC和MTC车道的收费排队时间。根据模型的特点设计了基于主动集的启发式算法，利用参数二进制与拉格朗日函数法确定迭代下降方向，解决了下降方向与步长难以计算的问题；通过内嵌优化函数的方式，保证在主动集转化过程中上层约束均不会失效，且避免了迭代过程中的模型解退化问题。基于上海市绕城高速进行实证分析，结果表明：随着ETC普及率的提升，收费排队时长按照负指数趋势下降；与按比例布设ETC车道的方法相比，所提方法最高可降低57.4%的收费排队时间，且该方法可以避免ETC车道布设过多对于MTC车道通行能力挤压造成的负面效果。研究成果可以有效指导高速路网ETC车道的布设，提高路网通行效率。     

Vehicle dynamics and road curvature estimation for lane departure warning system using robust fuzzy observers: experimental validation

This paper describes a new approach to estimate vehicle dynamics and the road curvature in order to detect vehicle lane departures. This method has been evaluated through an experimental set-up using a real test vehicle equipped with the RT2500 inertial measurement unit. Based on a robust unknown input fuzzy observer, the road curvature is estimated and compared to the vehicle trajectory curvature. The difference between the two curvatures is used by the proposed lane departure detection algorithm as the first driving risk indicator. To reduce false alarms and take into account driver corrections, a second driving risk indicator based on the steering dynamics is considered. The vehicle nonlinear model is deduced from the vehicle lateral dynamics and road geometry and then represented by an uncertain Takagi–Sugeno fuzzy model. Taking into account the unmeasured variables, an unknown input fuzzy observer is proposed. Synthesis conditions of the proposed fuzzy observer are formulated in terms of linear matrix inequalities using the Lyapunov method.     

高速路段动态OD反推模型与算法研究

各进出口匝道间的实时交通量是高速公路管理系统重要的输入数据,也是难以获得的数据。本文回顾了动态OD反推理论的发展历程,提出了动态路径走行时间的完善和简化计算方法,在此基础上建立了基于高速路段的动态OD反推模型,设计了遗传算法对问题进行求解,并讨论了算法中的六个关键问题,提供了一种获得高速公路进出口间动态OD交通量的有效方法。实例研究表明,模型和算法具有较高的效率和准确性,能够应用于在线系统。     

基于双线公交专用道的公共交通效益研究

公交专用道是公交优先的重要环节。在我国,单线公交专用道并不能从实质上解决公交优先的问题。为能更好地发挥公交专用道作用,提出了在大城市或特大型城市设置双线公交专用道,以及双线公交专用道的设置条件,并对双线公交专用道和单线公交专用道的效益进行对比,运用模型计算后得出了优选方案。     

基于动态交通分配的应急路径规划

为了提高在应急救援与疏散工作中的应急交通效率,针对已有相关算法未考虑交通问题动态性的不足,提出了1个基于动态交通分配的应急路径规划算法。给出了问题的定义,设计了1个基于仿真的动态交通分配模型,给出了基于动态交通分配的算法求解步骤。通过北京市路网数据对算法进行验证,证明了算法的可行性与有效性。     

Automated Vehicle Merging Maneuver Implementation for AHS

Summary This paper presents a real-time implementation of a general merging algorithm for automated highway systems. A merging control problem is proposed first. A real-time algorithm is then presented, which is used to calculate a smooth reference speed trajectory for the merging vehicle based on the speed of the main lane vehicle. This algorithm can also be applied even when the main lane vehicles change speed. To make the algorithm adapt to different road layouts and to increase safety, a concept of virtual platooning is proposed. It effectively shifts the time of platoon formation forward prior to the start of real merging. Aspects closely related to real-time implementation are discussed, such as the controller adopted, the use of magnetometer based distance measurement and information passing by communication from main lane vehicles. Test results are presented and briefly analyzed.     

基于改进RepVGG网络的车道线检测算法

为提高自动驾驶系统中车道线检测的速度和精度,提出了基于可解耦训练状态与推理状态的车道线检测算法.在结构重参数化VGG(RepVGG)主干网络中引入注意力机制压缩-激励(SE)模块,增强对重要车道线信息的特征提取;同时设计并行可分离的辅助分割分支,对局部特征进行建模以提高检测精度.采用行方向位置分类车道线检测方式,在主干...     

隧道与互通出口小净距路段换道可靠性研究

为分析高速公路隧道与互通出口小净距路段在不同交通流状况下的车辆驶出概率,提出了基于交通仿真的安全换道概率模型。首先,采用VISSIM标定仿真模型并进行正交试验,获取小净距路段在不同净距长度、交通量、驶出比例、大型车比例下的交通数据,在此基础上确定瞬时交通流密度及相应车流平均速度的计算方法,构建相应的分布模型,通过K均值聚类算法研究不同速度下的瞬时交通流密度大小和出现概率;同时引入可靠度方法并利用微分法来构建车辆安全换道概率模型,综合考虑车速、车流密度、目标车道临界可插入间隙等因素的不确定性,应用蒙特卡罗仿真法搭建求解概率模型的算法,并通过MATLAB对模型进行求解;针对分流车初始位置的不同,分别得到了不同交通量、大型车比例、净距长度下的换道驶出成功率,进而研究不同交通流状况组合下的净距长度。结果表明：交通量、大型车比例、净距长度对净距路段内侧车道车辆换道驶出成功率有显著性影响,研究结果可为规范的进一步完善提供参考。     

Analysing classes of motion drive algorithms based on paired comparison techniques

A paired comparison experiment using 23 subjects was run on the VIRTTEX driving simulator to compare a lane position based motion drive algorithm (MDA) with a classical MDA for a highway speed, lane change manoeuvre. Two different tuning states of the lane position algorithm and four different tuning states for the classical algorithm were tested. The subjective fidelity of the six different motion cases was compared with each other and a Bradley–Terry model was fit to find the fidelity merit of each case. In addition, the driving performance of the subjects for six motion cases was recorded and compared. The motion-tuning cases were selected such that the trade-off in motion quality between overall motion scaling and motion shape distortion (shape-error), as well as the trade-off between lateral specific force and roll-rate motion errors, could be studied. It was found that when the overall scaling is the same, drivers perform better with the lane position algorithm than with the the classical algorithm. A well-tuned, manoeuvre-specific, classical MDA, however, did achieve a subjective fidelity level on a par with the lane position MDA. A generically tuned classical MDA, however, has a significantly reduced fidelity and driving performance when compared with a lane position algorithm with the same scale factor. A strong trade-off between motion shape-errors and overall motion scaling was found. A small increase in motion cue shape-error, combined with an increase in the scale factor from 0.3 to 0.5, led to improved performance and increased subjective fidelity. The results of the experiment also suggest that simulator motion can be improved by reducing the angular-rate shape-error at the expense of the specific force shape-error (while keeping the total normalised shape-error constant).     

基于驾驶人不满度的高速公路自动驾驶换道决策

为了实现高速公路的自由换道行为决策，并满足行车安全高效性、决策结果平稳无震荡、与运动规划模块结合引导车辆行驶等要求，提出了一种基于驾驶人不满度的换道行为决策方法。首先，根据驾驶人的速度期望建立了驾驶人不满度累积模型，并基于驾驶人速度不满累积度产生换道意图。其次，依据不同车道障碍车的运动状态，设计了2种目标车道选择策略，通过预测引擎对各个待选车道进行预测和评估，选取其中行车效率较高的车道作为目标车道，同时建立换道最小安全距离模型，用以在换道全过程中判断换道的可行性。然后，将换道行为决策的结果以目标车道的形式传递给基于改进人工势场的运动规划模块，用于运动规划模块目标的选取，以引导车辆横纵向运动。最后，在CarSim/PreScan/Simulink的联合仿真平台和硬件在环平台上建立多种测试场景，验证换道行为决策算法。试验结果表明：换道行为决策算法能够依据驾驶人速度不满累积度产生稳定的换道意图，进而根据所设计的换道策略选取具有更高行车效率的目标车道，并在换道过程中持续判断换道的可行性，以应对障碍车辆突然加减速等突发状况，保证换道过程的高效性和安全性；换道行为决策算法通过目标车道的转换，引导运动规划模块调整车辆的运动，实现跟车、换道等行为。     

交通分配中的梯度投影算法及其改进模型

最近的研究表明基于路径的交通分配算法具有很强的生命力和广阔的应用前景。在这些算法中,梯度投影算法(GP)由于其极高的计算效率引起了研究者极大的兴趣。但是研究同样表明GP算法在求高精度分配解时遇到了收敛问题。文章首先介绍了GP算法的理论基础及算法步骤,然后分析了算法产生收敛问题的关键原因,针对其高精度解不能很好收敛的问题,采用二分法改进了其中关键的步长确定策略,提出了改进的GP算法(IGP,Improved GP),并通过计算实例比较了GP和IGP的表现,分析了IGP的优势。并用计算实例证明IGP在求解高精度分配解和整体收敛速度两方面都优于GP。     

基于预期偏移距离的人机权值分配策略研究

针对智能车辆横向运动控制中驾驶员和辅助系统的控制权限冲突问题,本文中提出一种人机权值分配策略。采用车辆在预瞄点处的预期偏移距离(PDLC)衡量车道偏离危险度,预期偏移距离通过对预瞄偏差修正获取。权值分配函数设计时以PDLC为自变量,以保证驾驶员的权值为优先控制目标,以一定的横向运动控制精度为先决条件。在CarSim/Simulink联合仿真平台和CarSim/Labview RT硬件在环实验台上对提出的控制策略进行了实验验证和数据分析。结果表明,采用权值分配策略协调驾驶员和辅助系统的控制,可在有效跟踪理想道路中心线的前提下保证驾驶员的控制权值,降低其工作负荷以及纠正驾驶员的误操作行为。     

面向多元场景结合GLNet的车道线检测算法

各种复杂环境下路面车道线的高效精确检测是自动驾驶领域中车道偏离预警系统的关键性技术之一。由于车辆实际运行环境的复杂性和路面车道线的多样性，现有方法在车道线检测的准确性和鲁棒性上仍需不断增强。提出一种面向多元场景结合GLNet的车道线检测算法。首先采用改进Gamma校正对待检测路面图像预处理，消减光照不均匀、夜晚等环境干扰，增强车道线纹理。然后为增强数据集的多样性，在LaneNet网络的基础上引入对抗生成网络DCGAN，构建GLNet网络模型。该模型采用编码-解码的网络结构提取车道线特征（车道蒙板和像素点），通过DBSCAN聚类算法将不同车道线划分为不同的实体，使用H-Net网络学习的视觉转换矩阵优化并拟合输出车道线。最后基于已训练好的GLNet权重模型对车道线进行精确提取，并在Tusimple数据集和自制数据集上测试验证。试验结果表明：该方法的检测准确率可达97.4%，相较于基于LaneNet网络的车道线检测算法明显提高；DCGAN网络的加入丰富了数据集类型，并提高了该模型的表征及分类能力；DBSCAN聚类算法的平均聚类时间约为0.016 s，相较于Meanshift算法运行效率更高。所提出的方法考虑了不规范、环境复杂等多种道路类型的车道线检测任务，提升了对复杂噪声与多元场景的处理能力，在车辆辅助驾驶领域具有较好的鲁棒性和适用性。     

Proposed quick method for applying dynamic lane assignment at signalized intersections

Almost all researches about dynamic lane assignment were conducted to evaluate the effectiveness of applying this technique at signalized intersections. However, little attention was given to the method of identifying quickly the optimum lane group. This research suggests a quick method to find the optimum lane group for 3-lane and 4-lane approaches at junctions where each approach has green by itself in turn using the percentage of turning movements. MATLAB environment was used to build an optimization model to find the optimal lane groups at all intersection approaches for hypothetical massive traffic demand combinations using an objective function of minimizing intersection delay. This finding represents a plausible quick method to predict the optimum lane group in the field instantaneously using the percentage of turning movements at the approach without conducting massive calculations.