Differences between vehicle lateral displacement on the road and in a fixed-base simulator

This work investigates differences in lateral displacement when driving on curved and straight road sections in real-road and simulator conditions. We observed 100 licensed drivers on a rural road and 100 in a fixed-base simulator. Speed and lateral position on the real road were measured using videocameras. The analysis indicates that the mean vehicle lateral displacement is in general higher on the real road than in the simulator. However, these differences decrease for higher speeds at curved sections and for lower speeds at straight sections. It was also found that the standard deviation of the vehicle lateral displacement is significantly lower on the real road than the corresponding values in the simulator, at either curved or straight sections. Actual or potential applications of this research are related to a more realistic assessment of driving behavior scenarios derived on the basis of simulation experiment results.     

基于有向含权复杂网络的城市交通路网关键路段识别

针对目前基于复杂网络识别城市交通路网关键路段缺乏考虑现实影响因素和路段方向性问题,提出了一种基于有向含权复杂网络的关键路段识别方法。第一阶段利用复杂网络理论将城市交通路网构建成有向含权复杂网络模型;第二阶段利用LinkRank算法对复杂网络中边进行重要度排序,以此识别关键边,即城市交通路网关键路段;第三阶段利用变异的易感—感染（susceptible-infective,SI）模型对关键路段进行影响评估。通过对浙江省海宁市城区的城市交通路网分析,验证了方法的实用性和有效性。     

基于复杂网络的路网交通拥堵评估仿真模型

为了能够深入分析路网交通拥堵动态演进过程, 为交通拥堵治理提供决策分析工具, 提出了一个基于复杂网络的路网拥堵评估仿真模型。通过将路段阻抗概念引入复杂网络理论, 实现了路网拓扑模型和流量模型的结合; 此外, 还提出了虚拟测试车辆遍历的路网通行能力评估方法, 对不同路网条件下的道路通行能力进行评估。最后在PC系统上实现了完整的路网拥堵评估仿真系统, 并利用该系统对拥堵路段数量、交通流量和路网拓扑结构等因素对路网通行能力的影响进行了仿真分析。仿真实验结果与经典交通理论分析结果一致, 并能反映更多的动态过程信息, 表明该模型能够准确有效地进行交通路网拥堵评估, 可以为相应的交通拥堵管理决策提供依据。     

基于拥堵系数的道路交通网络关键路段辨识

城市道路交通的路段信息与车流量信息对道路交通的安全、高效运行至关重要.在交通高峰时期,通过对关键路段加以控制,可实现整个道路交通网络的完全能控.为寻找路网中的关键路段,将道路网络的交叉口-节点模型转化为道路网络的路段-节点模型,基于路段信息与车流量信息提出拥堵系数来衡量道路交通网络的车辆拥堵程度,并将其作为道路网络的路段-节点模型的边权重,最后运用关键路段辨识算法对道路交通网络的关键路段进行辨识.以沈阳市皇姑区主城区道路为例建立以拥堵系数为权重的网络模型, 按照所提方法辨识的关键路段数量为14条,约占道路网络总路段数的14.3%,具有较低的控制成本,且大部分为由北向南方向和由西向东方向.其中8条路段分布在皇姑区道路实时拥堵排行前5名,约占关键路段总数的57.1%,表明所给出的关键路段更多地分布在交通状态较为拥堵的路段上,符合实际情况.     

Research on the comprehensive traffic state evaluation model linked with drivers’ perception under the vehicle networking

Unified judgment standards and methods are often adopted to identify traffic state in certain road network based on traffic flow parameters. However, drivers often have different perceptions about the traffic state on different road sections, since their expectations on traffic state vary more or less from each other on different road sections. In particular, under the vehicle networking, out of considerations for safety and other relevant factors, requirements for the correlation and coordination of running vehicles have also raised significantly. Therefore, it is necessary to take driver’s perception about the driving conditions of certain road sections into consideration to adjust the release of traffic state. This paper has provided a comprehensive traffic state evaluation model linked with driver’s perception under the vehicle networking. The authors first establish an ANFIS model based on the T–S model and then conduct statistical analysis on drivers’ perceptions about certain traffic state. At last, the authors use the results of statistical analysis as regulatory factors to amend the parameters input through ANFIS. Through simulation, this paper has demonstrated that the model established has a high rate of convergence, a high identification precision and the generalization ability to conduct researches on the identification of traffic state.     

复杂路段的角度差和后续点地图匹配方法

针对仅依靠距离和轨迹与路径的相似性来判断正确道路的方法,在并行和交叉路段的复杂路网环境中,易匹配到相邻路段或部分不可达的路段,导致匹配错误的问题,提出采用线性回归模型的方法,其能更精确地描述道路形状在转弯处的变化,根据路段方向和移动对象移动的方向差判断并行或交叉路段,并通过参照多个后续点的匹配情况,实现复杂路段处的地图匹配,减少匹配错误。此外,还提出简化聚类的路网补全方法,可以解决部分GPS点周围缺失候选路段无法匹配的问题,并采用四叉树索引地图数据,提高效率。对比实验结果表明在轨迹点数较少时,与现有的基于隐马尔可夫模型的概率匹配方法相比,时间最多减少了62%,更适合时效性要求高的应用场景,与传统的几何匹配方法相比,匹配精度提高了3%,且更适合复杂路段匹配。     

智慧城市路网交通流量均衡性优化调度方法

早高峰和晚高峰时段的路网交通混乱,极易发生拥堵情况,为缓解交通系统压力,设计节点元胞划分下智慧城市路网交通流量均衡性优化调度方法。获取不同交通路线间的流量分离函数,定义路径交通流量和可用路段费用,得到出行者在某段路径上的概率函数,计算智慧城市路网各路段交通流量;获取流量守恒和车辆传递函数,计算可变元胞的单独序列,建立交通节点元胞划分模型;设计交通流量均衡性优化调度算法,得到城市路网均衡性的优化调度结果。设置仿真参数,对比优化前后三个路网模型的路径流量,仿真结果显示：早高峰和晚高峰时段路段内的路径流量明显降低,在其他时段,优化后的路径流量也不同程度下降,且路网模型越复杂,该优化方法的调度效果越好。     

基于出租车轨迹数据的最优路径规划方法

针对传统的路径规划算法并不一定能计算得到现实中最优路径的问题,提出一种融合了出租车驾驶经验并以时间为度量的路径规划算法。该算法的实现是将路径规划这个以计算为中心的技术变为以数据为中心的数据驱动挖掘技术。首先,从大量的出租车轨迹数据中提取真实的载人轨迹数据,并将载人轨迹数据匹配到路网数据中;然后,根据地图匹配结果计算路段的访问频次,选取前Top-k个路段作为热点路段;其次,计算热点路段间行车轨迹的相似度,对轨迹进行聚类分析,在路网的基础上构建该k个路段的热点路段图;最后,使用一种改进的A^*算法实现路径规划。实验结果表明,与传统的最短路径规划算法和基于驾驶经验路网分层的路径规划算法相比,所提出的基于热点路段图的路径规划方法有效地缩短规划路径的长度及路径行驶时间,提高路径规划的用时效率。     

基于Hough变换的高分辨率遥感影像城市直线道路提取

根据高分辨率遥感影像城市直线道路特性,提出在图像分割获得道路网轮廓的基础上,使用Hough变换检测道路所在直线,对直线进行道路判断,再将所得道路段进行修剪、连接形成道路网,实现道路提取。实验结果表明,该方法能有效的从高分辨遥感影像中提取城市直线道路。     

基于负载均衡的电动汽车充电路径优化方法

Under the premise that the remaining electricity is sufficient, the path planning problem of electric vehicles to the target charging pile is the key to the optimization of charging strategies. Normally, when the system is recommended to the user, the sys- tem will make some or a few road sections which have been recommended to different users many times. When a large number of us- ers choose overlapping road sections, they will reduce the current recommendation. The traffic capacity of the road segment makes these charging paths into optimal paths only in a mathematical sense, resulting in local optimization issues. This paper proposes a global path planning method based on load balancing, takes into account the degree of congestion of the section and the user's driv- ing time, to suggest the user a shorter and smooth charging path. Finally, through the simulation experiment, the short-time predic- tion of the traffic flow can reduce the average waiting time of the charging queuing, and the global optimal charging path method based on load balancing can improve the utilization of charging piles and avoid traffic congestion issues.     

Highly Automated Driving Impact on Drivers’ Gaze Behaviors during a Car-Following Task

ABSTRACT

The ever-increasing degree of automation in vehicles, with drivers delegating part of the manual driving task to automation, sets new research questions in terms of human–machine cooperation. Manual steering requires drivers to gaze at a distant road sections to ensure that the vehicle follows the road curvature and at a near road sections to maintain the vehicle within the lane limits. In this experiment, gaze behaviors engaged under highly automated driving (HAD) and manual driving conditions were compared. The results show a critical decrease of the number of gazes at the near road sections for the HAD condition compared to the manual driving condition. Two human-based highly automated “driving styles” were also compared, but did not translate into significant gaze behaviors modifications. Finally, no after-effect of the HAD was found on subsequent manual driving.     

一种面向严重受损路网的抢修队调度算法

受损路网抢修是灾害应急响应中的一个非常重要的基础环节,主要研究如何对道路抢修队进行有效调度,以快速恢复受灾路网的交通能力,为后续顺利展开应急救援工作提供有效的保证.已有方法在路网受损严重的情形下往往难以给出有效的调度策略.为此,在已有工作的基础上,简化路网模型和决策模型,并基于动作集裁减和Q学习设计一种面向严重受损路网的抢修队调度算法.在该算法中,抢修队只能从当前可达的未修复受损路段集合中选择下一个动作,以确保Q学习的连续性.仿真实验结果表明,在节点数和受损率都较大的严重受损路网环境中,所提算法可以保证所有需求节点均可达,具有更高的稳定性和可靠性,且能够在更小的时间和修复代价内给出更优的调度方案.     

基于全局时空特性的城市路网交通速度预测模型

城市路网交通速度预测是智能交通系统中的重要组成部分,其可为出行者提供实时的交通信息,对提升道路通行能力具有重要意义。现有基于图卷积网络的预测模型一定程度上加强了对一阶相邻路段间空间关联程度的挖掘,但在非一阶相邻路段关联度大于一阶相邻路段关联度的情况下,如果仍输入原始的邻接矩阵,会遗失一些相对重要的路段空间信息,无法得到较好的预测结果。为准确挖掘城市路网中的时空特性,提出一种基于全局图卷积和门控循环单元的城市路网交通速度预测模型G-GCGRU。考虑全局路网下非一阶相邻路段间的空间影响程度,利用相关性分析方法计算得到路段间的关联度矩阵,并作为新的卷积方式进一步加深对空间特征的挖掘,在此基础上,采用门控循环单元方法提取路网时间特征。使用深圳市罗湖区城市路网车速数据进行实验,结果表明,该模型预测性能优于图卷积网络（GCN）、门控循环单元（GRU）和GCN-GRU混合模型,以均方根误差为评价指标,预测精度分别提高25.3%、4.7%和2.1%。     

基于JPEG2000的交通监控图像高速实时压缩应用仿真研究

随着交通公路运输的快速发展,公路交通安全形势日趋突出,尤其在低等级公路地势险峻的路段交通事故时有发生,因此迫切需要建立针对这些路段的交通监控系统.但是,传统的交通监控系统设计模式不能满足低成本建设的要求.针对山区及边远地区公路车流量较少的应用环境,提出了使用CCD相机拍摄图片,利用无线网络进行监控图片传输的设计构想.并针对交通监控图像的实时、高速、高压缩率传输需求,在Visual C 环境下,建立了对监控图像进行压缩、传输、解压、接收、显示等过程进行仿真研究的仿真系统.该系统主要使用JPEG2000算法进行了仿真分析,在仿真系统的设计实现中采用图像分块压缩等关键技术,并针对压缩速度提出了压缩效率、信噪比等评价指标.仿真结果证明了图像数据压缩系统的有效性.本项研究成果可以用于对监控图像实时压缩技术进行仿真研究和分析,并可以指导相关监控设备的研发及监控系统设计.     

M/G/c/c state dependent queuing model for a road traffic system of two sections in tandem

We propose in this article a M/G/c/c state dependent queuing model for road traffic flow. The model is based on finite capacity queuing theory which captures the stationary density-flow relationships. It is also inspired from the deterministic Godunov scheme for the road traffic simulation. We first present a reformulation of the existing linear case of M/G/c/c state dependent model, in order to use flow rather than speed variables. We then extend this model in order to consider upstream traffic demand and downstream traffic supply. After that, we propose the model for two road sections in tandem where both sections influence each other. In order to deal with this mutual dependence, we solve an implicit system given by an algebraic equation. Finally, we derive some performance measures (throughput and expected travel time). A comparison with results predicted by the M/G/c/c state dependent queuing networks shows that the model we propose here captures really the dynamics of the road traffic.     

基于城市区域路网的分散协调控制研究

根据城域多路口交通系统的特点,摒弃统一信号周期的方法,以各单路口为基点,采用分散协调控制策略,综合考虑各相邻路口及两路口间的交通流,实时控制各路口交通信号,并智能的加以协调,使区域内道路的交通通行能力得到提高,降低车辆的延误时间。为提高系统的控制精度和鲁棒性,采用神经网络技术实现模糊控制。仿真结果表明,该方法控制效果良好。     

Computer simulation and field measurement of dynamic pavement loading

Two methods, i.e. computer simulation and field measurement, are used in this paper to investigate dynamic pavement loading (DPL) generated by vehicle–pavement interaction. A profilometer is used for measuring road surface roughness. Based on the power spectral density of the measured surface roughness, a computer simulation program is developed using quarter vehicle model. In field measurement methods, an experiment is designed to gain the time history of DPL. An IVECO vehicle is taken as a test vehicle and eight vibration cells were used to pick up vertical accelerations of vehicle body and axle. The test data are collected and recorded while the test vehicle is moving along 11 different pavement sections of highway and bridge at six different speeds. Statistical characteristics of vertical accelerations and DPL of the test vehicle are obtained and analyzed by means of random process theory. The result of computer simulation matches the result of field measurement very well. It is found that DPL is primarily concentrated between 1.8 and 14.8 Hz and coefficient of variation of DPL falls into the range of 5–35% of static vehicle load. An approximate relationship between coefficient of variation of DPL and vehicle speed and road surface roughness is established.     

基于浮动网格的路段检索方法

地图匹配是将车辆原始的GPS轨迹数据映射到实际道路网络上的过程, 其中为GPS轨迹点检索候选路段是地图匹配的首要环节, 然而不同的候选路段检索方式会直接影响地图匹配的准确性和效率. 本文针对城市路网环境下的低频采样GPS轨迹数据, 提出了一种基于浮动网格的路段检索方法. 该方法利用GeoHash网格编码, 采用浮动GeoHash网格的方式, 为轨迹点检索候选路段. 其次为了验证方法的可行性, 本文通过隐马尔可夫模型, 结合道路网络的拓扑结构以及轨迹的时空约束条件, 采用增量的方式, 利用维特比算法计算得到局部最优解. 最后使用贪心策略, 从已经得到的局部最优解中依次延伸得到全局最佳匹配路径.     

面向智能交通系统的仿真路网快速建模方法

提出了一种面向智能交通系统的仿真路网模型,与传统路网模型相比,增强了几 何表达和拓扑表达能力,同时其上可附着丰富的交通属性数据,能够满足精细化智能交通仿真 的需求。在此基础上,研究了一种路网数据迁移方法,从现有电子地图快速提取并构建面向智 能交通系统的道路路网。通过对几何精确性、拓扑完备性和建模高效性的测试表明,该路网模 型及其建模方法,提高了交通仿真基础路网建模的效率,降低了建模成本,为智能交通仿真的 广泛应用提供了高效、可靠的道路数据来源。     

一种快速的基于边缘的道路检测算法

道路检测是机器人视觉导航中的重要环节。本文提出了一种新的非结构化道路检测算法。算法基于这样的一个基本假设，即道路的轮廓由一些具有一定长度的连续直线段组成。在一定的范围中通过计算边缘点，然后通过Hough变换求得直线段，从而确定道路边界的位置。但是边缘图像中不仅仅包含道路的边缘，还有阴影，植物等其他的边缘。如果不消除这类边缘的影响，将大大削弱算法的效率和准确性。本文提出一种基于颜色和方差的规则有效地消除这类非道路的边缘。一旦当前帧中获取道路的边缘，通过限定下一帧中的感兴趣区域（ROD减少搜索范围从而快速定位帧中的道路边缘，从而进一步提高算法的效率。大量实地（校内公园道路）实验验证了该算法的快速和鲁棒性．