共享单车出行空间异质性特征及驱动因素研究

为实现基于轨迹数据挖掘的共享单车出行空间异质性特征及其驱动因素评估，本文应用核密度分析和热点探测，获取采样分析区域并以热力值表征共享单车出行发生量，减少尺度效应的干扰；引入空间统计学的半变异函数模拟共享单车出行发生量的结构性和随机性变化规律，挖掘空间异质性特征，确定邻域效应的尺度范围；利用空间序列的斜率表征变化趋势，同时，结合改进的空间滞后和残差模型，区分土地利用、邻域效应和其他建成环境各自对共享单车出行空间异质性特征的驱动力。以北京市为案例进行分析，结果表明：北京市的共享单车出行存在中等的、 正的空间自相关性，空间异质性特征的最佳拟合模型为指数模型；空间自相关性的衰减半径为 1860 m，大于此距离时邻域效应消失；建成环境对空间异质性特征的相对驱动力最大，邻域效应对其的相对驱动力则处于中间水平，而土地利用对其的相对驱动力最小。     

Measuring social effective speed to improve sustainable mobility policies in developing countries

Over the last few decades, many developing countries have experienced car fleet growth, which has contributed to congestion, increased travel times, and deteriorated public transport reliability and punctuality. However, alternatives to urban mobility can be found by creating policies to stimulate sustainable transportation modes with equal opportunities for all citizens. In this paper, measures of social effective speeds are presented to improve sustainable urban mobility policies in developing countries. Data from the 2018 Origin-Destination Survey of the Metropolitan Region of Recife (Brazil) were used to estimate social effective speeds. The results showed that motorized modes had lower effective speed than non-motorized modes. In addition, total external costs were $2 billion USD per year. The social effective speed will be valuable if inserted in sustainable urban mobility policies in developing countries.     

公共自行车使用时空特性挖掘及租还需求预测

基于宁波市公共自行车刷卡数据、POI(Point of Interest)数据、气象和空气质量等数据，从数据驱动视角，深入挖掘公共自行车使用的时空特征及站点租还车需求预测。在时间上，采用KMeans算法，将站点聚为5类，探讨各类站点的时变需求规律及影响因素；在空间上，提出基于POI 数据的站点用地类型识别方法，将站点分为居住类、交通设施类、办公类和商业休闲类。构建以 15，30，60 min 为间隔，以租还车需求为目标变量的随机森林预测模型，并与常用的 BP (Back Propagation)神经网络、K最近邻方法进行比较。结果表明，随机森林模型的精度更高，适用性更强。以30 min为间隔的站点租还车需求预测精度最高，考虑站点土地利用类型后能有效提高模型的预测精度。本文结果可作为未来站点平衡调度的依据并推广应用于共享单车系统，为改善服务水平提供技术和理论支撑。     

基于自然驾驶数据的驾驶人换道决策识别研究

为实现人机共驾模式下智能系统对驾驶人换道决策的准确识别,将换道决策细分并提出了基于改进的极端梯度提升(XGBoost)的换道决策识别模型。以实车试验采集的自然驾驶数据作为输入,并采用滑动时间窗法确定识别时刻,建立各识别时间窗口下基于XGBoost的换道决策识别模型,同时运用交叉检验和网格搜索(GS)算法进一步提升模型性能,最后利用验证集数据评估所构建GS-XGBoost模型的识别性能,并与机器学习及深度学习模型进行对比。结果表明,所提出的模型在具体换道决策辨识上具有较好的实时性和准确性,且在1.8 s和1.6 s时间窗下的识别准确率最高,达到86.2%。     

基于滚动时域优化的共享自动驾驶汽车动态调度方法

共享自动驾驶汽车被视为未来城市交通系统的重要组成部分。本文考虑随机订单需求研究共享自动驾驶汽车的动态调度优化方法。通过建立车辆调度时空网络，分别针对订单分配与空车移位生成车辆运行时间弧，提出车辆调度问题的刻画方法。基于马尔科夫决策框架，以时空节点流量为状态，以时空弧流量为决策变量，建立最大化系统净收益的车辆动态调度优化模型。 采取滚动时域优化思想，建立含前视时间窗的随机规划模型，并利用CPLEX优化引擎，滚动求解车辆动态调度决策结果。Sioux Falls网络算例结果表明，滚动时域优化方法可保证车辆动态调度决策效果，提升系统运营效率。在计算时间限制下，滚动时域方法应优先采用长时间窗中等规模 样本。在最大化系统净收益的同时进一步最小化乘客等待时间，可有效提升车辆动态调度决策效果。     

Trends in life cycle greenhouse gas emissions of future light duty electric vehicles

The majority of previous studies examining life cycle greenhouse gas (LCGHG) emissions of battery electric vehicles (BEVs) have focused on efficiency-oriented vehicle designs with limited battery capacities. However, two dominant trends in the US BEV market make these studies increasingly obsolete: sales show significant increases in battery capacity and attendant range and are increasingly dominated by large luxury or high-performance vehicles. In addition, an era of new use and ownership models may mean significant changes to vehicle utilization, and the carbon intensity of electricity is expected to decrease. Thus, the question is whether these trends significantly alter our expectations of future BEV LCGHG emissions.To answer this question, three archetypal vehicle designs for the year 2025 along with scenarios for increased range and different use models are simulated in an LCGHG model: an efficiency-oriented compact vehicle; a high performance luxury sedan; and a luxury sport utility vehicle. While production emissions are less than 10% of LCGHG emissions for today’s gasoline vehicles, they account for about 40% for a BEV, and as much as two-thirds of a future BEV operated on a primarily renewable grid. Larger battery systems and low utilization do not outweigh expected reductions in emissions from electricity used for vehicle charging. These trends could be exacerbated by increasing BEV market shares for larger vehicles. However, larger battery systems could reduce per-mile emissions of BEVs in high mileage applications, like on-demand ride sharing or shared vehicle fleets, meaning that trends in use patterns may countervail those in BEV design.     

Young people and the private car: A love-hate relationship

Urban mobility is one of the main concerns of the public authorities in developed countries. In France, household travel surveys are conducted every ten years in major cities to gather weekday mobility data. They enable decision-makers to better understand travel patterns, their change and their determinants, in order to adapt transport infrastructures to the population′s needs. While the automobile has allowed the level of mobility to increase since 1950, an unexpected finding has emerged from recent surveys in most developed countries, namely that there has been a marked decline in car use. Analyses show that this trend is mainly because young adults (18–34 years old) are less likely to acquire a driver′s license. This paper tries to better understand the decrease in the rate of driver′s license holding among young adults in the Lyon conurbation and to quantify the impact of the main explanatory factors in a temporal perspective. It also aims to analyze the consequences of this trend on private car use as a driver for daily trips. It quantifies the influence of economic, socio-demographic and spatial factors on driver ′ s license holding and car use by considering the responses to the last three household travels surveys conducted in the Lyon conurbation area (1995, 2006 and 2015). The temporal dimension allows us to highlight a change in the relationship between young adults and the private car in the French context.     

共享停车泊位数量可变下交通流逐日演化规律

为了揭示在共享停车泊位数量可变条件下的网络交通流逐日演化规律,首先构建了共享泊位交易系统,并考虑了交易市场中的共享泊位提供者可以选择2种异质性的价格预期方式,即理性预期方式和幼稚预期方式;而后对共享泊位的均衡价格、2种提供者的占比差、高峰时段公交和小汽车需求的演化规律进行了分析;其次,以2条平行路径的路网为例,对网络交通流量分配的最终演化结果进行了分析;最后,在对上述2个系统的最终演化状态给出定量判据后,以北京市实际路网为例进行了数值试验。理论分析和数值试验结果表明:①对于共享泊位交易系统,若供给曲线斜率小于需求曲线斜率,则共享泊位交易系统的唯一均衡解可实现无条件渐进稳定;否则若理性提供者的交易与预测成本之和大于幼稚提供者,则存在临界提供者选择强度,使得共享泊位交易系统在大于此临界值条件下出现分岔或混沌现象;②对于网络交通流系统,若出行成本对路径流量敏感度小,路径选择概率对出行成本敏感度小,小汽车需求量不大,则系统唯一的均衡解可能是渐进稳定的,否则系统会出现分岔或混沌状态;③当共享泊位交易系统处于渐进稳定状态时,若提供者对共享泊位的价格变动不敏感,用户对其价格变动敏感,潜在共享泊位需求量不大,理性提供者的交易与预测成本之和并非远大于幼稚提供者,提供者选择强度不大,则由于受到共享泊位交易总量的限制,高峰时段的均衡小汽车需求不大,导致网络交通流系统的最终演化状态容易趋向于渐进稳定;④当共享泊位交易系统处于混沌状态时,网络交通流系统会产生更加严重的分岔与混沌现象。     

考虑匹配优先级的共享混合停车位租用与分配问题研究

为充分利用混合停车场的停车和充电资源，本文依据出行者需求的差异性设置匹配优先级，在此基础上以共享平台接受并出租车位的收益扣除拒绝请求的惩罚成本的总收益最大化为目标，以充电量不超过停车场负荷为约束条件，建立考虑匹配优先级的共享混合停车位租用与分 配(MPRA)模型。基于匹配优先级原则和模型特征改进蚁群算法，设置分块冲突矩阵，根据分块冲突矩阵设计蚂蚁信息素更新策略和路径选择策略并进行求解。最后算例证实了考虑匹配优先级的必要性，并分析了问题规模对MPRA分配方案的影响。研究结果表明：在充电需求匹配率方面，MPRA方案高于利润最大化方案，平均提升率为28.96%，这一优势与出行者数量或车位数量成反比，且利润提升率随着问题规模的增加而增加；车位数量有限时，MPRA方案相较于先到先停方案可以极大化提升车位利用率和充电需求匹配率，平均提升率分别为17.87%和113.96%。     

Policy packages for modal shift and CO2 reduction in Lille,France

This paper proposes different policy scenarios to cut CO₂ emissions caused by the urban mobility of passengers. More precisely, we compare the effects of the ‘direct tool’ of carbon tax, to a combination of ‘indirect tools’ – not originally aimed at reducing CO₂ (i.e. congestion charging, parking charges and a reduction in public transport travel time) in terms of CO₂ impacts through a change in the modal split. In our model, modal choices depend on individual characteristics, trip features (including the effects of policy tools), and land use at origin and destination zones. Personal “CO₂ emissions budgets” resulting from the trips observed in the metropolitan area of Lille (France) in 2006 are calculated and compared to the situation related to the different policy scenarios. We find that an increase of 50% in parking charges combined with a cordon toll of €1.20 and a 10% travel time decrease in public transport services (made after recycling toll-revenues) is the winning scenario. The combined effects of all the policy scenarios are superior to their separate effects.