基于人-车-路-环境综合计算的驾驶员期望车速

微观交通流仿真是智能运输系统研究与开发的重要手段。期望车速是微观交通流仿真研究的一个重要参数,受到驾驶员特性、车辆特性、道路条件、交通干扰、天气和承运任务急缓等多种因素的影响,准确确定期望车速是驾驶员行为研究的难点。从研究驾驶员心理-物理特性的角度出发,利用层次分析法,对驾驶员决策思维的递阶层次进行量化,建立基于人-车-路-环境综合计算的驾驶员期望车速模型。经过实测数据验证,该方法用于驾驶员期望车速模型的研究是可行的。     

基于Agent的驾驶员-车辆建模研究与实现

微观交通仿真技术是解决城市交通网络拥塞问题的有效工具.在各种交通元素中,驾驶员-车辆单元是交通流的主体.该文通过对交通流中驾驶员、车辆特性的分析,将驾驶员和车辆视为一个整体,并基于Agent理论对之进行建模.文中详细分析了Agent的生成和路径搜索及选择算法,研究了Agent的跟驰、换道和挤占道等行为.该文最后介绍了基于Agent模型建立的一种微观交通仿真器,并在该仿真器上进行仿真实验.结果表明该系统能够较好的仿真实际交通流状况.     

基于模糊推理的驾驶员车速决策行为建模与仿真

为了在微观交通仿真中更真实地模拟驾驶员的车速决策行为,在综合自由行驶和跟驰两种驾驶行为的基础上,采用模糊推理技术进行建模研究。选取车头时距、期望速度差、前车速度差作为模糊推理系统输入变量,加速度为系统输出,结合实际中加减速行为的不对称性及不同行驶状态下主要行驶意图的不同,构造模糊规则,建立基于模糊推理的车速决策模型。利用模糊系统的输入输出曲面进行了模型的校核,并在考虑驾驶员反应时间的基础上进行了仿真实验。仿真结果表明,车辆能够根据前车行驶状态和自身期望车速进行适当的速度决策,验证了所建模型的合理性。     

基于心理物理综合认知结构的微观交通仿真模型

针对驾驶行为的不确定性,在分析驾驶员心理-物理微观特性的基础上,构建了基于驾驶员任务集聚的心理-物理综合认知结构及其各行为运行模式下微观交通仿真的车辆跟驰模型.运用五轮仪试验系统所采获的实际数据和多元统计分析的数学方法对模型进行了标定,并使用与模型标定过程所用到的数据不同的另一部分数据验证了模型的有效性.结果表明,该文所提出的模型和算法能够很好地刻画驾驶员心理-物理行为特性的复杂性,再现人车单元的实际动态行为,为网络交通流一体化协同仿真和智能运输系统研究提供理论基础.     

蚁群决策算法在上下游短时交通流预测中的应用

根据上下游短时交通流的特性,在深入研究蚁群算法的基础上,利用蚁群思想及决策树思想构造了蚁群决策算法,描述了该算法用于城市道路上下游短时交通流建模预测以及与决策树算法进行了对比,论证了其可行性,最后利用Matlab进行仿真,给出了仿真结果。     

非机动车流矢量场模型及其参数变化规律研究

交通流特性参数是交通规划与控制研究中的基本参数指标,但是,交通流特性参数通常由经验确定,准确性很难得到保证;针对非机动车行驶总是向阻碍最小,空间最大的方向移动的特点,对矢量场微观模型进行了改进,将非机动车沿道路方向和垂直道路方向的运动分开建模,然后用改进后的模型对路段、路口进行微观仿真,并利用仿真得到的统计数据分析交通流特性参数,得到交通流特性参数与非机动车驾驶行为参数之间的定性定量关系,与实测数据吻合良好;根据该关系,可以在交通仿真和交通规划的研究中,对模型参数进行实时校正,使仿真和规划结果更加准确.     

车道变换决策仿真模型

由于影响车道变换因素的多样性、因素自身变化的随机性和影响因素的难测性,正确反映驾驶员换道行为的不确定性,是微观交通流模拟模型中的难点,也是驾驶员车道变换模型相对于跟驰模型落后的最主要原因之一。从驾驶员心理-物理特性的角度出发,利用层次分析法,对驾驶员决策思维的递阶层次进行量化,建立了基于层次分析的驾驶员车道变换决策模型。经过实测数据验证,该方法用于车道变换决策模型的研究是可行的。     

交叉口黄灯期间驾驶员行为的模糊决策树模型

采集黄灯期间驾驶员行为的相关数据,考虑车辆位置、车速、倒计时表3个影响因素,分别设定其隶属度函数,应用模糊决策树中的FID3算法,以模糊信息熵为启发信息,构建驾驶员选择的模糊决策树模型,生成决策规则。利用测试样本对模型进行检验,结果表明,基于模糊决策树的预测结果准确率总体达到84.8%。     

考虑鸣笛效应和驾驶员异质性的新格子模型稳定性分析

道路环境及密集交通流随机波动是交通扰动的诱因, 文中考虑道路环境中的汽车鸣笛效应和驾驶员异质性的影响, 提出鸣笛发生临界密度的概念, 建立了更符合实际的格子流体动力学模型, 并揭示非饱和交通状态下诱发交通流失稳的机理.在线性稳定性分析中利用扰动法得到了该模型的稳定性条件, 并基于还原微扰法对该模型的非线性稳定性问题进行研究, 通过求解mKDV方程获取的扭结-反扭结孤立波描述了在临界点附近密度波的传输规则.仿真结果表明, 考虑有鸣笛效应的新格子模型相比于Nagatani模型的稳定性更强, 而较大的临界密度对交通流稳定性存在消极影响; 与以往微观模型相比, 本文模型能解释鸣笛现象发生的自然条件, 即密度高且流量低的地方, 同时驾驶员特性也对交通流的稳定性存在着显著影响.     

基于微观变量的交通流算法研究

中国城镇化发展迅速,伴随而来的城市交通状况也日益恶化,早日建成现代化的交通运输系统和交通信息管理系统成为了城市交通战略的首要任务.寻找能够正确描述交通流基本规律的交通流算法,更好地指导局部交通的优化管理和控制,是交通流研究的期望目标.基于微观变量和元胞自动机理论提出交通流算法模型.通过对微观交通流算法的设计及数值模拟,预测理想的交通流及出行分布情况,从而加深了对交通流中各种现象内在机理的认识,使其可以预测出最接近实际情况的交通流,为交通流的仿真和实时交通控制做了基础性的工作.     

基于模糊推理的汽车辅助驾驶系统控制算法

在建立汽车辅助驾驶系统模型的基础上,指出满足驾驶员的驾驶特征是车辆控制的一个重要指标,此外针对驾驶员驾驶行为的不精确性,提出了以模糊推理为基础的上位控制方法,并对其进行了现场实验。实验结果表明,用模糊控制理论模拟驾驶行为的不精确性是可行的。通过模糊控制自车的速度,能够实现自车在多种工况下保持安全状态。     

面向智能驾驶测试的仿真场景构建技术综述

随着汽车智能化程度的不断提高,智能汽车通过环境传感器与周边行驶环境的信息交互与互联更为密切,需应对的行驶环境状况也越来越复杂,包括行驶道路、周边交通和气象条件等诸多因素,具有较强的不确定性、难以重复、不可预测和不可穷尽。限于研发周期和成本、工况复杂多样性,特别是安全因素的考虑,传统的开放道路测试试验或基于封闭试验场的测试难以满足智能驾驶系统可靠性与鲁棒性的测试要求。因此,借助数字虚拟技术的仿真测试成为智能驾驶测试验证一种新的手段,仿真场景的构建作为模拟仿真的重要组成部分,是实现智能驾驶测试中大样本、极限边界小概率样本测试验证的关键技术,这对提升智能驾驶系统的压力和加速测评水平显得尤为重要。面向智能驾驶测试的仿真场景构建技术已成为当前汽车智能化新的研究课题和世界性的研究热点,作为一种新兴技术仍面临许多挑战。本文提出了面向智能驾驶测试的仿真场景构建方法,系统阐述了国内外研究工作的进展与现状,包括场景自动构建方法和交通仿真建模方法,重点分析一些值得深入研究的问题并围绕场景构建技术的发展趋势进行了讨论分析,最后介绍了团队相关研究在2020中国智能驾驶挑战赛仿真赛和世界智能驾驶挑战赛的仿真场景应用情况。     

Mixture of Automatically- and Manually-controlled Vehicles in Intelligent Transport Systems

This paper presents a technology which allows for the existence of mixed traffic, as a first step towards intelligent transport systems. We begin by designing an automatic driving controller called the intelligent vehicle driving system (IVDS). This is a two-layer system: the higher layer analyzes the current scenario and infers the control objective that associates with a certain index function; the lower layer optimizes the function provided by the upper layer. IVDS only uses the measurement of a vehicle's speed and distance relative to the vehicle in front, together with measurements of the vehicle's own state. Consequently, the vehicles equipped with the IVDS can operate together with manually-controlled vehicles. Next, a mathematical rule-based model for human drivers is developed. This model attempts to mimic human driver's behavior in vehicle following and lane-changing. Finally, we examine the control performance of the proposed controller and the potential benefits of mixed traffic by implementing the human driver model and IVDS on an automated highway simulator.     

Driving violations observed: an Australian study

This study analyses 2,765 cases of driving behaviours in three Australian states - New South Wales, Queensland and Victoria. Data were gathered from in-car coordinated video and audio recording sequences in free-flowing traffic along two-, three- and four-lane highways with varying speed limits on all days of the week in daylight and fine weather conditions. Explanatory variables included driver age group and gender, passenger characteristics and vehicle age and type. Response variables included driving violations and other driving behaviours, including lane use, speeding, close following (tailgating), driver's hands position and mobile phone use. Data were analysed qualitatively and quantitatively. By focusing upon vehicle and driver characteristics, and their impact on driving behaviours, including identified violations, this study explores some implications both for future research and for traffic policy makers.     

Round-trip driving effects on driving performances and mental workload under different traffic rules

This study investigates the effect of switching between different traffic rules (left-versus right-hand traffic) on driving performance and mental workload. A driving simulation environment was developed according to the real environment. Two urban roads with different traffic systems were simulated. Twenty participants executed intersection turns and continuous car-following behavior in four simulated driving stages, including driving with familiar, unfamiliar, second time unfamiliar, and back to familiar traffic rules. The mean and standard deviations for speed, distance headway, and the standard deviation of lateral position were recorded as driving performance. Mental workload was determined using the NASA-TLX and Rating Scale Mental Effort questionnaires. One-way analysis of variance was used to evaluate the differences between the four driving stages using subjective and objective measures. The results showed that significant differences were obtained in all measures when driving in the four driving situations, except for the speed standard deviation. The car-following behavior was the most unsafe (significantly larger standard deviations for distance headway and mental workload) when driving in unfamiliar road traffic compared with the other stages. When driving under unfamiliar traffic rules for the second time, the mental workload was significantly relieved and the lane-keeping ability significantly improved. The results indicated that providing an adaptive runway for drivers to familiarize themselves with different traffic rules is necessary to improve driving performance and safety. These findings provide useful information for designing bridges linking two places with different traffic rules to increase traffic safety.     

Predictive car-following scheme for improving traffic flows on urban road networks

Driving behavior is one of the main reasons that causes bottleneck on the freeway or restricts the capacity of signalized intersections. This paper proposes a car-following scheme in a model predictive control (MPC) framework to improve the traffic flow behavior, particularly in stopping and speeding up of individual vehicles in dense urban traffic under a connected vehicle (CV) environment. Using information received through vehicle-to-vehicle (V2V) communication, the scheme predicts the future states of the preceding vehicle and computes the control input by solving a constrained optimization problem considering a finite future horizon. The objective function is to minimize the weighted costs due to speed deviation, control input, and unsafe gaps. The scheme shares the planned driving information with the following vehicles so that they can make better cooperative driving decision. The proposed car-following scheme is simulated in a typical driving scenario with multiple vehicles in dense traffic that has to stop at red signals in multiple intersections. The speeding up or queue clearing and stopping characteristics of the traffic using the proposed scheme is compared with the existing car-following scheme through numerical simulation.     

考虑前车动态效应的高速跟驰交通流研究

为描述交通中存在的“高速跟驰”现象,在NaSch模型的基础上,考虑了前车的运动特性,并结合驾驶员的驾驶行为差异,建立了考虑前车动态效应的高速跟驰交通流模型（DPM）。通过数值模拟得到了高速跟驰规律,当道路车流密度为0.18时,车道上的高速跟驰率为4.93%;同时,通过分析车辆运动的时空特性,模拟出交通流中自由流、同步流以及宽幅运动阻塞现象;还得出了不同驾驶员占比下的速度-流量-密度的关系;并分析了车辆随时间变化的速度及车头间距波动情况,较NaSch模型有更高的交通稳定性。通过NGSIM数据集及国内实测数据验证了DPM模型的有效性和实用性。     

速度与挡位匹配提醒系统的研究与设计

近年来,交通运输已成为我们生活中比较重要的一部分,私家车及驾驶员的数量均越来越多。本文针对这种情况,为驾驶员,尤其是初学者提供一套手动挡汽车速度与挡位匹配的控制系统。此系统以单片机为控制核心,结合监测、控制、显示、语音播报ISD4004、报警等模块实现行车过程的实时监测、控制及提醒。本系统为初学者提供辅助教学,为驾驶员提供经济的行车方式,同时提高我国的汽车行业的竞争力。