基于决策树模型的驾驶员期望车速

微观交通流仿真是智能运输系统(ITS)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,准确地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,利用决策树能融知识表示与获取于一身的优点,将决策树用于驾驶员期望车速的研究,以实现对驾驶员行为的模拟再现.仿真结果表明,该方法用于驾驶员期望车速的研究是可行的.     

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.     

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。     

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.     

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。     

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.     

基于SUMO平台的微观交通仿真研究

微观交通仿真在城市交通控制系统中有着重要地位,而微观仿真模型的建立是其主要内容之一。Krauss模型是基于安全车速范式的微观、空间连续的车辆跟驰模型,为避免原始Krauss模型中加速度突变的问题,本文在其基础上提出了融合车辆减速度渐变过程的新模型。在SUMO仿真平台上编程实现了改进后的车辆跟驰模型,并在同等条件下对原始模型和改进模型进行了实例仿真分析,结果表明改进后的模型在一定程度上避免了加速度突变问题,交通流运行的仿真情况在整体性能上有显著改善,仿真效果与现实交通情况更趋一致。     

改进的OVM交通流模型及数值模拟研究

传统的最优速度模型(OVM)中驾驶员灵敏度系数均取常数,这与实际情况不完全相符,为此,提出一种基于驾驶员灵敏度系数概率分布的最优速度模型(PDDS-OVM)。该模型根据概率统计理论,将驾驶员的灵敏度系数归纳为按一定概率分布的函数,交通流队列中的每辆车对应该分布的一个值。在Matlab7.0仿真平台上,对驾驶员灵敏度系数在定值、均匀分布、正态分布3种情况下,分别进行反复数值模拟仿真,结果表明PDDS-OVM模型能更好地描述交通流的波动特性。     

图像处理技术在标定微观交通仿真模型中的应用

城市交通控制的许多决策都是基于微观交通流仿真模型进行的。文章研究应用了图像处理技术来对微观交通流仿真模型的参数进行标定，并使用模拟退火算法使仿真的结果和被仿真对象的实际观测数据吻合。     

基于VR的驾驶仿真及安全教育系统开发

针对全国道路交通事故高发现状及传统驾驶安全教育方式单一、培训效果差的缺点,基于虚拟现实技术（VR）,在引发交通事故人为因素理论基础上,开发驾驶仿真及安全教育系统。系统基于Unity3D引擎,构建了基于道路实景数据的虚拟场景,并联合SUMO实现了道路交通流仿真,通过VR技术仿真驾驶环境及驾驶行为;基于碰撞检测原理,建立了关卡违规触发机制,编码自定义屏幕空间渲染方式模拟驾驶员视觉效果,并构建了基于图像的交通事故现场三维全景,从认知、感知层面培训驾驶员安全驾驶。实用性测试结果表明,系统实现了不同道路场景、气象条件与交通状况下的驾驶模拟及安全培训,增强了使用者的学习兴趣,提高了使用者驾驶安全素养,具有较强的实用性。     

Lane-keeping assistance control algorithm using differential braking to prevent unintended lane departures

This paper describes a hierarchical lane keeping assistance control algorithm for a vehicle. The proposed control strategy consists of a supervisor, an upper-level controller and a lower-level controller. The supervisor determines whether lane departure is intended or not, and whether the proposed algorithm is activated or not. To detect driver′s lane change intention, the steering behavior index has been developed incorporating vehicle speed and road curvature. To validate the detection performance on the lane change intention, full-scale simulator tests on a virtual test track (VTT) are conducted under various driving situations. The upper-level controller is designed to compute the desired yaw rate for the lane departure prevention, and for the guidance with ride comfort. The lower-level controller is designed to compute the desired yaw moment in order to track the desired yaw rate, and to distribute it into each tire′s braking force in order to track the desired yaw moment. The control allocation method is adopted to distribute braking forces under the actuator’s control input limitation. The proposed lane keeping assistance control algorithm is evaluated with human driver model-in-the-loop simulation and experiments on a real vehicle.     

Effect of a Traffic Speed Based Cruise Control on an Electric Vehicle’s Performance and an Energy Consumption Model of an Electric Vehicle

This paper proposes a cruise control system (CCS) to improve an electric vehicle’s range, which is a significant hurdle in market penetration of electric vehicles. A typical driver or a conventional adaptive cruise control (ACC) controls an electric vehicle (EV) such that it follows a lead vehicle or drives close to the speed limit. This driving behaviour may cause the EV to cruise significantly above the average traffic speed. It may later require the EV to slow down due to the traffic ripples, wasting a part of the EV’s kinetic energy. In addition, the EV will also waste higher speed dependent dissipative energies, which are spent to overcome the aerodynamic drag force and rolling resistance. This paper proposes a CCS to address this issue. The proposed CCS controls an EV’s speed such that it prevents the vehicle from speeding significantly above the average traffic speed. In addition, it maintains a safe inter-vehicular distance from the lead vehicle. The design and simulation analysis of the proposed CCS were in a MATLAB simulation environment. The simulation environment includes an energy consumption model of an EV, which was developed using data collected from an electric bus operation in London. In the simulation analysis, the proposed system reduced the EV’s energy consumption by approximately 36.6% in urban drive cycles and 15.4% in motorway drive cycles. Finally, the experimental analysis using a Nissan e-NV200 on two urban routes showed approximately 30.8% energy savings.      

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。     

关于道路交通行车安全距离预测仿真

为了提高道路交通安全,针对行车安全距离的非线性带来的难以准确预测的问题,提出了一种临界行车安全距离的预测方法。以驾驶员驾驶风格类型、前车速度、后车速度、前车减速度为系统输入,以临界行车安全距离为系统的输出,应用最小二乘支持向量机(LS-SVM)建立预测模型。结合仿真软件采集到的样本数据进行训练,得到行车安全距离的预测结果,并与目前普遍采用的BP (Back Propagation)神经网络模型的预测结果进行了对比。实验结果表明,所提出的预测模型能准确地预测临界行车安全距离,且预测准确度明显优于BP神经网络。     

The Indirect Shared Steering Control Under Double Loop Structure of Driver and Automation

Due to the critical defects of techniques in fully autonomous vehicles, man-machine cooperative driving is still of great significance in today’s transportation system. Unlike the previous shared control structure, this paper introduces a double loop structure which is applied to indirect shared steering control between driver and automation. In contrast to the tandem indirect shared control, the parallel indirect shared control put the authority allocation system of steering angle into the framework to allocate the corresponding weighting coefficients reasonably and output the final desired steering angle according to the current deviation of vehicle and the accuracy of steering angles. Besides, the active disturbance rejection controller (ADRC) is also added in the frame in order to track the desired steering angle fleetly and accurately as well as restrain the internal and external disturbances effectively which including the steering friction torque, wind speed and ground interference etc. Eventually, we validated the advantages of double loop framework through three sets of double lane change and slalom experiments, respectively. Exactly as we expected, the simulation results show that the double loop structure can effectively reduce the lateral displacement error caused by the driver or the controller, significantly improve the tracking precision and keep great performance in trajectory tracking characteristics when driving errors occur in one of driver and controller.      

虚拟驾驶环境中车辆智能体的驾驶行为模型

建立虚拟交通环境的多智能体结构,分析车辆智能体的驾驶行为分层模型以及感知、决策和操作等过程。采用模糊专家系统建立车辆智能体的驾驶行为模型。为模拟现实中的驾驶员行为特性,加入驾驶员因子,使驾驶模拟器的虚拟交通环境更符合现实。运用OpenGVS产生和显示实时交互的虚拟驾驶场景。结果表明该模型能体现实际驾驶行为的多样性、随机性和模糊性。该模型通用有效,它使驾驶模拟器的虚拟交通场景更真实满意。     

Multi-driver agent-based traffic simulation systems for evaluating the effects of advanced driver assistance systems on road traffic accidents

A recent investigation revealed that there is a substantiated need for the development of a micro-simulation system designed for traffic safety assessment. This paper describes the development of a road traffic simulation system, which uses a ‘nanoscopic model’ of driver behaviour and an integrated analysis-evaluation system designed for traffic safety assessment. The primary focus is on estimating the effects of an advanced driver assistance system thereby reducing traffic accidents. The effectiveness and validity of the present system are demonstrated through comparison with measured traffic data. This paper also proposes algorithms embedded in a ‘driver-agent’, for recognising driver’s intentions regarding choosing steering-control modes, lateral control tasks, and the driving mood. This is because the driver assistance systems need to recognise the driver’s intention when choosing steering-control. The results of a simulation study, using the data drawn from actual driving, show that the systems would achieve a high recognition capability. As an example of how driving mood recognition applies to driver assistance systems, an advanced steering system and the adaptability to the driver’s mood, have also been presented.