Adaptive spatial-temporal graph attention network for traffic speed prediction

Considering the nonlinear structure and spatial-temporal correlation of traffic network,and the influence of potential correlation between nodes of traffic network on the spatial features,this paper proposes a traffic speed prediction model based on the combination of graph attention network with self-adaptive adjacency matrix(SAdpGAT)and bidirectional gated recurrent unit(BiGRU).First-ly,the model introduces graph attention network(GAT)to extract the spatial features of real road network and potential road network respectively in spatial dimension.Secondly,the spatial features are input into BiGRU to extract the time series features.Finally,the prediction results of the real road network and the potential road network are connected to generate the final prediction results of the model.The experimental results show that the prediction accuracy of the proposed model is im-proved obviously on METR-LA and PEMS-BAY datasets,which proves the advantages of the pro-posed spatial-temporal model in traffic speed prediction.

Traffic Speed Interface Development in Route Choice Decision

In this paper,a method has been developed based on historic traffic data(speed),which helps the commuters to choose routes by their intelligence knowing the traffic conditions in Google maps.Data has been collected on basis of video analysis from several segments between Tuker Bazar and Bandar Bazar route.For each of the video footage,a reference length has been recorded with measurement tape for use in video analysis.A software has been also developed based on Java language to get the traffic information from historic data,which shows the output as images consisting of traffic speed details on the available routes by giving day and time limit as inputs.The developed models provide useful insights and helpful for the policy makers that can lead to the reduction of traffic congestion and increase the scope of intelligence of the road users,at least for the underdeveloped or developing country where navigation is still unavailable.

A BP neural network based information fusion method for urban traffic speed estimation

Obtaining comprehensive and accurate information is very important in intelligent tragic system （ITS）. In ITS, the GPS floating car system is an important approach for traffic data acquisition. However, in this system, the GPS blind areas caused by tall buildings or tunnels could affect the acquisition of tragic information and depress the system performance. Aiming at this problem, a novel method employing a back propagation （BP） neural network is developed to estimate the traffic speed in the GPS blind areas. When the speed of one road section is lost, the speed of its related road sections can be used to estimate its speed. The complete historical data of these road sections are used to train the neural network, using Levenberg-Marquardt learning algorithm. Then, the current speed of the related roads is used by the trained neural network to get the speed of the road section without GPS signal. We compare the speed of the road section estimated by our method with the real speed of this road section, and the experimental results show that the proposed method of traffic speed estimation is very effective.

Effect of Traffic Speed on Stresses and Strains in Asphalt Perpetual Pavement

Increasing traffic volumes and loads as well as public expectation for a long-lasting transportation infrastructure have necessitated designing perpetual pavements. The KDOT （Kansas Department of Transportation） conducted a field trial to investigate the suitability of perpetual pavement concept for Kansas highway pavements. The experiment involved construction of four thick pavement structures. To verify the approach of designing perpetual pavements on the basis of an endurance strain limit, the pavements were instrumented with gauges for measuring tensile strains at the bottom of asphalt base layers at various speeds. Pavements were also instrumented with pressure cells to measure stress on the top of subgrade. Pavement response measurements under known vehicle load were performed in August 2006. FWD （Falling-weight deflectometer） was also used to collect deflection data at 15 m intervals on the same date. FWD first-sensor （center） deflections were normalized and corrected to 20 ℃ temperature based on measured mid-depth pavement temperature. The result shows that strain and stress measurements show significant amount of variations. Measurements in the thickest section are the most consistent. The higher the traffic speed, the lower the strains and stresses. The difference between strains and stresses at 30 kmhar and 65 km/hr is higher than the difference between 65 km/hr and 95 kin/hr. This shows the effect of speed on stresses and strains decreases as the speed increases. Softer binder in the asphalt base layer results in lower strains, which confirms that softer binder results in higher fatigue life.

Extended speed gradient model for traffic flow on two-lane freeways

In this paper, the speed gradient （SG） model is extended to describe the traffic flow on two-lane freeways. Terms related to lane change are added into the continuity equations and velocity dynamic equations. The empirically observed two-lane phenomena, such as lane usage inversion and lane change rate versus density, are reproduced by extended SG model. The local cluster effect is also investigated by numerical simulations.

Speed–density functional relationship for heterogeneous traffic data: a statistical and theoretical investigation

This study is an attempt to establish a suitable speed–density functional relationship for heterogeneous traffic on urban arterials. The model must reproduce the traffic behaviour on traffic stream and satisfy all static and dynamic properties of speed–flow–density relationships. As a first attempt for Indian traffic condition, two behavioural parameters, namely the kinematic wave speed at jam(Cj) and a proposed saturation flow(k), are estimated using empirical observations. The parameter Cjis estimated by developing a relationship between driver reaction time and vehicle position in the queue at the signalised intersection. Functional parameters are estimated using Levenberg–Marquardt algorithm implemented in the R statistical software.Numerical measures such as root mean squared error, average relative error and cumulative residual plots are used for assessing models fitness. We set out several static and dynamic properties of the flow–speed–density relationships to evaluate the models, and these properties equally hold good for both homogenous and heterogeneous traffic states.From the numerical analysis, it is found that very few models replicate empirical speed–density data traffic behaviour.However, none of the existing functional forms satisfy all the properties. To overcome the shortcomings, we proposed two new speed–density functional forms. The uniqueness of these models is that they satisfy both numerical accuracy and the properties of fundamental diagram. These new forms would certainly improve the modelling accuracy, especially in dynamic traffic studies when coupling with dynamic speed equations.

Mathematical Modeling,Field Calibration and Numerical Simulation of Low-Speed Mixed Traffic Flow in Cities

Ｗｉｔｈｔｈｅｒａｐｉｄｄｅｖｅｌｏｐｍｅｎｔｏｆｔｒａｎｓｐｏｒｔａｔｉｏｎａｎｄａｕｔｏｍｏｂｉｌｅｉｎｄｕｓｔｒｙ，ｔｈｅｃｏｎｆｌｉｃｔｂｅｔｗｅｅｎｍｏｔｏｒｍａｎｕｆａｃｔｕｒｅａｎｄｈｉｇｈｗａｙｃｏｎｓｔｒｕｃｔｉｏｎｂｅｃｏｍｅｓｓ...

A cellular automata traffic flow modeling of desired speed variability

The satisfaction rate of desired velocity in the case of a mixture of fast and slow vehicles is studied by using a cellular automaton method. It is found that at low density the satisfaction rate depends on the maximal velocity. However, the behavior of the satisfaction rate as a function of the coefficient of variance is independent of the maximal velocity. This is in good agreement with empirical results obtained by Lipshtat [Phys. Rev. E 79 066110 （2009）]. Furthermore, our numerical result demonstrates that at low density the satisfaction rate takes higher values, whereas the coefficient of variance is close to zero. The coefficient of variance increases with increasing density, while the satisfaction rate decreases to zero. Moreover, we have also shown that, at low density the coefficient variance depends strongly on the probability of overtaking.

Evaluating Traffic Congestion Using the Traffic Occupancy and Speed Distribution Relationship: An Application of Bayesian Dirichlet Process Mixtures of Generalized Linear Model

Accurate classification and prediction of future traffic conditions are essential for developing effective strategies for congestion mitigation on the highway systems. Speed distribution is one of the traffic stream parameters, which has been used to quantify the traffic conditions. Previous studies have shown that multi-modal probability distribution of speeds gives excellent results when simultaneously evaluating congested and free-flow traffic conditions. However, most of these previous analytical studies do not incorporate the influencing factors in characterizing these conditions. This study evaluates the impact of traffic occupancy on the multi-state speed distribution using the Bayesian Dirichlet Process Mixtures of Generalized Linear Models (DPM-GLM). Further, the study estimates the speed cut-point values of traffic states, which separate them into homogeneous groups using Bayesian change-point detection (BCD) technique. The study used 2015 archived one-year traffic data collected on Florida’s Interstate 295 freeway corridor. Information criteria results revealed three traffic states, which were identified as free-flow, transitional flow condition (congestion onset/offset), and the congested condition. The findings of the DPM-GLM indicated that in all estimated states, the traffic speed decreases when traffic occupancy increases. Comparison of the influence of traffic occupancy between traffic states showed that traffic occupancy has more impact on the free-flow and the congested state than on the transitional flow condition. With respect to estimating the threshold speed value, the results of the BCD model revealed promising findings in characterizing levels of traffic congestion.

Steady state speed distribution analysis for a combined cellular automaton traffic model

Cellular Automaton （CA） based traffic flow models have been extensively studied due to their effectiveness and simplicity in recent years. This paper develops a discrete time Markov chain （DTMC） analytical framework for a Nagel-Schreckenberg and Fukui Ishibashi combined CA model （W^2H traffic flow model） from microscopic point of view to capture the macroscopic steady state speed distributions. The inter-vehicle spacing Maxkov chain and the steady state speed Markov chain are proved to be irreducible and ergodic. The theoretical speed probability distributions depending on the traffic density and stochastic delay probability are in good accordance with numerical simulations. The derived fundamental diagram of the average speed from theoretical speed distributions is equivalent to the results in the previous work.

Speed Spatial Distribution Models for Traffic Accident Section of Freeway Based on Computer Simulation

Simulation models for accident section on freeway are built in microscopic traffic flow simulation environment. In these models involving 2-lane,3-lane and 4-lane freeway,one detector is set every 10 m to measure section running speed. According to the simulation results,speed spatial distribution curves for traffic accident section on freeway are drawn which help to determine dangerous sections on upstream of accident section. Furthermore,the speed spatial distribution models are obtained for every speed distribution curve. The results provide theoretical basis for determination on temporal and spatial influence ranges of traffic accident and offer reference to formulation of speed limit scheme and other management measures.

雾天桥梁可变限速值的效用评估及优化

为改善高速公路桥梁路段雾天环境的交通安全,文中考虑可变限速标志设置对驾驶行为的影响,从服从效应角度提出其量化评估方法,以期获得最优作用效能。文中以鄂东长江大桥为原型,选取该桥梁近年最低能见度(100 m)和自由流服务水平作为测试环境,设计3种限速策略,分别为对照组SⅠ(无限速策略)、实验组SⅡ(90~70 km/h限速策略)、实验组SⅢ(90~70~50 km/h逐级限速策略);依托驾驶模拟器,实现不同限速条件的雾天桥梁场景微观驾驶行为数据的细粒度感知,采用重复测量方差分析方法从驾驶人响应的快速性、稳定性及准确性剖析可变限速标志的作用机理及驾驶人特征表现,并通过模糊综合评价方法评估不同限速策略的有效性。研究结果表明:雾天桥梁可变限速标志能够使驾驶人更早地采取减速措施,车辆在雾区行驶过程的稳定性更好;在雾天能见度100 m情况下,90~70~50 km/h逐级限速策略的稳态频数更大,空间稳定性更好,且速度超调量和跟随比更小,响应准确性更高。模糊综合评估结果显示,90~70~50 km/h逐级限速策略作为最优方案,能够有效地提升雾区驾驶行为的调节适应能力,降低驾驶风险,提高车辆运行的稳定性。本研究成果为雾天桥梁可变限速标志的优化设置提供了解决方案,可为雾天桥梁的主动安全防控提供有效支撑。

城市隧道允许变车道分界线设置方法研究

为了缓解低速车辆对隧道行车安全的影响,探讨城市隧道内部允许变车道分界线的设置方法,采用VISSIM仿真软件,分析城市隧道内部车道分界线设置为允许变道和禁止变道两种状态下低速行驶车辆对隧道交通流的影响。结果表明:城市隧道内低速行驶车辆对本车道的交通流平均速度影响最大,车道分界线设置为允许变道时可以明显缓解低速行驶车辆对交通流平均速度的影响。低速车辆的存在显著增加了本车道的平均延误时间,且车辆时速越低、道路交通量越大,平均延误时间越长;禁止变道状态下,低速车辆的存在造成本车道后方车辆的排队积压,导致交通密度显著增大,设置允许变道能够缓解低速车辆对交通流的影响。研究成果可为城市隧道的运营管理提供科学依据。

基于层次时空注意力图卷积的交通速度预测方法

针对交通速度预测方法主要考虑实际交通路网而忽略人群活动热点区域的影响问题,提出一种层次时空图卷积网络模型(hierarchical spatio-temporal graph convolutional network,H-STGCN)。首先,通过计算路段节点之间的距离构建路网结构图,并使用聚类算法得到热点区域的聚类图;其次,利用图卷积网络层和时空注意力机制层来提取交通速度数据的时空特征;最后,引入过往邻近时间段、昨天相同时间段及上周同一时间段3个时间分量的交通速度数据分别进行训练,以挖掘交通速度在相同时间段的规律。实验结果表明,模型在预测时长为30、60和120 min时,相比于经典的时空图卷积模型,平均绝对误差分别降低了6.9%、13.6%和14.6%,实现了更准确的预测,能更好地服务于智能交通系统。

基于规则的信号交叉口纯电动公交节能驾驶策略

为解决纯电动公交在通过信号交叉口时能耗较大的问题,本文提出一种旨在最小化电量消耗的基于规则的两阶段驾驶策略,能够实现通行策略场景的合理划分选择及充分优化加减速调整曲线凹凸性,同时,不牺牲乘客舒适度和通行时间。在策略第1阶段,结合车辆运行状态和通过车路协同技术获取的交叉口信号相位和时序信息,提出4种交叉口通行策略的划分与判断选择方式,包括匀速通过策略、加速通过策略、减速通过策略和制动停车策略;在策略第2阶段,利用基于XGBoost算法的能耗估算模型和基于加减速特征参数的曲线模型,优化策略场景中匀速过程、加速过程和减速过程的速度曲线;最后,结合VISSIM仿真验证4种通行策略的有效性。结果表明,所提出的策略可以有效减少电量消耗,在4种驾驶场景下,降低了29.8%~34.2%的能耗。此外,分析发现,在经济车速以上和以下的最佳速度节能曲线均为凹凸形曲线,因此,通过对比实验进行不同速度调整范围的最节能曲线凹凸性规律总结,该结论可以为纯电动公交车的节能驾驶提供更易于操作的驾驶引导。

Real-Time Traffic State and Boundary Flux Estimation with Distributed Speed Detecting Networks

The rapid development of 5G mobile communication and portable traffic detection technologies enhances highway transportation systems in detail and at a vehicle level. Besides the advantage of no disturbance to the regular traffic operation, these ubiquitous sensing technologies have the potential for unprecedented data collection at any temporal and spatial position. While as a typical distributed parameter system, the freeway traffic dynamics are determined by the current system states and the boundary traffic demand-supply. Using the three-step extended Kalman filtering, this paper simultaneously estimates the real-time traffic state and the boundary flux of freeway traffic with the distributed speed detector networks organized at any location of interest. In order to assess the effectiveness of the proposed approach, a freeway segment from Interstate 80 East (I-80E) in Alameda, Emeryville, and Northern California is selected. Experimental results show that the proposed method has the potential of using only speed detecting data to monitor the state of urban freeway transportation systems without access to the traditional measurement data, such as the boundary flows.

基于多智能体深度强化学习的高速公路可变限速协同控制方法

面向高速公路多路段可变限速协同控制需求,针对高维参数空间高效训练寻优难题,提出了应用多智能体深度确定性策略梯度(MADDPG)算法的高速公路可变限速协同控制方法。区别于既有研究的单个智能体深度确定性策略梯度(DDPG)算法,MADDPG将每个管控单元抽象为具备Actor-Critic强化学习架构的智能体,在算法训练过程中共享各智能体的状态、动作信息,使得各智能体具备推测其余智能体控制策略的能力,进而实现多路段协同控制。基于开源仿真软件SUMO,在高速公路典型拥堵场景对提出的控制方法开展管控效果验证。实验结果表明,提出的MADDPG算法降低了拥堵持续时间和路段运行速度标准差,分别减少69.23%、47.96%,可显著提高交通效率与安全。对比单智能体DDPG算法,MADDPG可节约50%的训练时间并提高7.44%的累计回报值,多智能体算法可提升协同控制策略的优化效率。进一步,为验证智能体间共享信息的必要性,将MADDPG与独立多智能体DDPG(IDDPG)算法进行对比:相较于IDDPG,MADDPG可使拥堵持续时间、速度标准差均值的改善提升11.65%、19.00%。

大咖揭秘系列科普——车祸为什么会发生

道路交通事故频发,使儿童和青少年面临着巨大威胁。现通过解答公众关心的交通事故相关问题,科普专业的交通知识,揭开车祸发生的神秘面纱。首先深入剖析了涵盖人、车、路、环境四方面的车祸频发原因,其中的人为因素占比高达93%。针对红绿灯问题,强调了按其指示出行的重要性,但红绿灯并非绝对保障,同时也需要多观察周围环境。此外,还探讨了车速与安全的相对性,提出适宜的车速应依据道路条件而定,并警示感冒及服药后驾驶的潜在风险。最后讨论了无人驾驶技术的影响,其虽有望减少人为失误,但仍尚存挑战。通过科普的形式,旨在提高公众对交通事故的科学认知,增强公众的交通安全意识,减少交通事故的发生。

考虑车流速度分布扰动的干道绿波最大带宽协调控制

城市车辆速度受多种因素影响呈现某种分布,鲁棒的干道协调控制模型应考虑不同速度下的车辆带宽需求。针对速度波动变化干道传统协调控制方法适用性差的问题,分析了带干扰的干道车辆速度时空分布特征,以推荐速度带宽最大与期望带宽最大为目标,提出了考虑车流速度分布扰动的干道绿波最大带宽协调控制方法。针对佛山市同济路4交叉口干道,速度分布扰动干道协调方法能够提供更符合车辆分布特性的协调方案,比Maxband模型和改进的Maxband模型提升约70%和14%的期望带宽。研究结果表明:笔者方法能够降低Maxband模型平均停车次数25%,平均延误45%和平均排队长度17%;针对不同速度期望和方差情况下的灵敏度分析实验表明,该方法能够为干道提供更具有鲁棒性的干道协调控制方案。

面向车次取消的票额分配与停站方案组合优化研究

当列车因严重干扰而取消时,大量旅客将在车站滞留,同时铁路公司收益也会受到一定影响,合理的票额分配是解决此类问题的有效方法。在差异化设置换乘旅客优先权基础上,构建了以铁路公司收益最大化和偏离原时刻表最小化为目标的票额分配和停站方案组合优化模型,并通过增加不等式组约束条件将其线性化;利用求解器GUROBI对上述模型进行求解并分析算例。研究结果表明:当列车因干扰而取消时,与不采用任何措施相比,灵活停站策略能有效地减少滞留旅客数量19.7%以上;铁路公司收益增加21.8%以上。