车辆碰撞预警系统对行车风险的干预效果

各类碰撞预警系统已广泛应用于具有驾驶辅助功能的车辆上,为研究预警系统对风险状态下车辆交互行为特征的影响机理,并评估其对行车风险的干预效果,采用15辆搭载预警系统的试验车辆在真实高速公路场景下进行实车群组试验,通过有-无预警情形对比试验及分析,从车辆交互行为特征指标、道路总体运行风险、驾驶员对预警系统认可度3个维度,对行...     

Development of a Driving Behavior-Based Collision Warning System Using a Neural Network

An advanced driver assistance system (ADAS) uses radar, visual information, and laser sensors to calculate variables representing driving conditions, such as time-to-collision (TTC) and time headway (THW), and to determine collision risk using empirically set thresholds. However, the empirically set threshold can generate differences in performance that are detected by the driver. It is appropriate to quickly relay collision risk to drivers whose response speed to dangerous situations is relatively slow and who drive defensively. However, for drivers whose response speed is relatively fast and who drive actively, it may be better not to provide a warning if they are aware of the collision risk in advance, because giving collision warnings too frequently can lower the reliability of the warnings and cause dissatisfaction in the driver, or promote disregard. To solve this problem, this study proposes a collision warning system (CWS) based on an individual driver’s driving behavior. In particular, a driver behavior model was created using an artificial neural network learning algorithm so that the collision risk could be determined according to the driving characteristics of the driver. Finally, the driver behavior model was learned using actual vehicle driving data and the applicability of the proposed CWS was verified through simulation.     

考虑驾驶人风格的跟车预警规则研究

为研究驾驶人的跟车特性及探究可适用于不同风格驾驶人的跟车预警规则,为自动驾驶车辆开发可满足不同用户驾驶需求和驾乘体验的主动安全预警系统,选取50名被试驾驶人开展实车试验,采集驾驶人跟车行为表征参数并基于雷达数据确定跟车事件提取规则。选取平均跟车时距和平均制动时距为二维向量,使用基于K-means聚类结果的高斯混合模型将驾驶人聚类为3种风格类型(冒进型、平稳型、保守型)。通过分析3组驾驶人的跟车及制动数据,将不同类型驾驶人的制动时距分位数作为跟车预警阈值,结合实际预警数据及不同制动时距分位数对应的预警正确率,对现有跟车预警规则进行调整,以适应不同类型驾驶人的驾驶需求。研究结果表明:3组驾驶人的平均跟车时距和平均制动时距差异显著,冒进型驾驶人倾向于选择较小的跟车时距和制动时距,保守型驾驶人的跟车时距和制动时距则普遍较大;3组驾驶人的实际跟车预警次数为215次,驾驶人采取制动操作而系统未予以预警的次数为329次,系统整体预警正确率为21.9%,漏警率为87.5%,通过分析信息熵等判定当前预警规则并不合理;将每类驾驶人制动时距的10%分位数作为阈值时的预警效果较好,调整后的跟车预警规则能在一定程度上适应不同的驾驶人类型。     

普通公路驾驶员期望车速调查分析与建模

为了解普通公路驾驶员的车速选择机理,对驾驶员进行了期望车速问卷调查,对驾驶员的个人信息、车辆特征、以及驾驶员对超速10%的认可态度等可能影响期望车速的因素进行了重点调查。根据限速值的不同,分80、60和40 km/h 3个等级进行了调查,并为各等级公路选取了代表路段,由具有类似驾驶经历的驾驶员认真填写。对435份有效问卷进行了分析,发现期望车速广泛存在于驾驶员心中,驾驶员在行车过程中会使车速尽量维持在期望车速附近。期望车速主要受限速值、驾驶员的驾龄、对超速10%的态度以及车辆性能等因素的影响,驾驶员的性别和年龄对期望车速的影响不显著。采用逐步回归法,得到了期望车速的计算方法。对期望车速的特点、交通安全措施以及调查方案中可供改进的地方进行了总结。     

Evaluating the effectiveness of a smartphone speed limit advisory application: An on-road study in Port-Harcourt,Nigeria

The development of mobile phone applications that provide speed limit advice and warnings offers opportunities for use of the technology in the improvement of driver safety. This paper looks at the effect of an advisory Intelligent Speed Assistance (ISA) application on driver speeding behaviour. Twenty participants (all males within the age range of 35–60 years) completed a within-group experimental design. Participants drove in real traffic on a 46 km test route which incorporated three-speed limits zones (50 km/h, 60 km/h, and 80 km/h speed limits) and aggregated into 10 different segments. Compared with baseline levels, possible impacts of ISA system functionalities on driver behaviour were studied through appropriate metrics including cumulative speed distribution, mean speed, speed deviation, 85th percentile speed, percentage distanced travelled above the speed limit, and safety benefit estimation. Results indicated the use of the ISA application led to significant improvement in speed limit compliance particularly in the 60 km/h and 80 km/h zones where speeding was eliminated. There were no observed negative effects on driver speeding behaviour from the use of the system. In general, the findings suggest the use of the ISA system, resulted in the adoption of vehicle speeds that are likely to improve road safety.     

Comparison of In-Vehicle Auditory Public Traffic Information With Roadside Dynamic Message Signs

Dynamic message signs (DMS) have been widely used by transportation agencies to disseminate traffic information (referred to in this article as “public traffic information”) for decades. Unfortunately, their effectiveness is limited, based on the following reasons: they are costly, can only present a limited amount of information, and typically only display information in one language. The wide availability of smart devices and the development of connected vehicles offer the possibility to create “virtual” DMS (VDMS), utilizing geofencing and audible messages to convey public traffic information. This research compares the ability of VDMS to convey public traffic information with existing DMS. A mixed repeated-measure experiment using a driving simulator was designed that examined the impacts of driver age, information transmission mode, amount of information, and driving complexity on message comprehension. Forty-two participants were recruited and each of them was tested under different combinations of the three within-subject factors. Participant performance was measured in terms of message comprehension, distraction, and self-reported overall difficulty level in receiving messages. Results revealed that VDMS generally performs better than DMS as information content increases and driving condition complexity increases, regardless of driver age. VDMS increased message comprehension by 16% under relatively complex driving conditions, reduced driver reaction time to unexpected stimuli (as measured with a reduced time-to-brake of 0.39 s), and made the same messages easier to process and retain for drivers than DMS. Based on these results, it is recommended that transportation agencies give careful consideration to VDMS as a future strategy for delivering public traffic information in a connected vehicle environment.     

Human driving data-based design of a vehicle adaptive cruise control algorithm

This paper presents a vehicle adaptive cruise control algorithm design with human factors considerations. Adaptive cruise control (ACC) systems should be acceptable to drivers. In order to be acceptable to drivers, the ACC systems need to be designed based on the analysis of human driver driving behaviour. Manual driving characteristics are investigated using real-world driving test data. The goal of the control algorithm is to achieve naturalistic behaviour of the controlled vehicle that would feel natural to the human driver in normal driving situations and to achieve safe vehicle behaviour in severe braking situations in which large decelerations are necessary. A non-dimensional warning index and inverse time-to-collision are used to evaluate driving situations. A confusion matrix method based on natural driving data sets was used to tune control parameters in the proposed ACC system. Using a simulation and a validated vehicle simulator, vehicle following characteristics of the controlled vehicle are compared with real-world manual driving radar sensor data. It is shown that the proposed control strategy can provide with natural following performance similar to human manual driving in both high speed driving and low speed stop-and-go situations and can prevent the vehicle-to-vehicle distance from dropping to an unsafe level in a variety of driving conditions.     

Driver propensity characterization for different forward collision warning times

The forward collision warning system, which warns danger to the driver after sensing possibility of crash in advance, has been actively studied recently. Such systems developed until now give a warning, regardless of driver’s driving propensity. However, it’s not reasonable to give a warning to every driver at the same time because drivers are different in driving propensity. In this study, to give a warning to each driver differently, three metrics classifying driver’s driving propensity were developed by using the driving data on a testing ground. These three metrics are the predicted time headway, required deceleration divided by the deceleration of the leading vehicle, and the resultant acceleration divided by the deceleration of the leading vehicle. Driving propensity was divided into 3 groups by using these metrics for braking and steering cases. In addition, these metrics were verified by making sure that braking propensity could be classified on public roads as well.     

人机共驾智能车驾驶模式决策属性析取研究

为了深入分析驾驶模式决策影响因子,通过实车试验采集了人-车-路多源特征信息。用驾驶人主观经验将驾驶模式划分为人工驾驶、警示辅助、自动驾驶3种状态,并利用采集的驾驶人血流量脉冲（BVP）和皮肤电导（SC）值进行K均值聚类,将驾驶人当前合适的驾驶模式自动聚类为3级。通过融合驾驶人自汇报结果和聚类结果对驾驶模式进行准确标定。采用以信息增益为依据的Ranker算法对多特征进行排序,并在此基础上,根据多分类器分级结果确定最优特征属性集合。研究结果表明：当选取车速、车头时距、车道中心距离、前轮转角标准差、驾驶经验5个指标为特征子集时,支持向量机、朴素贝叶斯及K近邻这3种分类器的识别准确率都超过90%;除警示辅助模式与自动驾驶模式下的车速值和车道中心距之外,其余所有不同模式决策属性值均呈显著性差异;研究结果可为人机共驾智能车驾驶模式决策提供依据。     

不同干预方式下右转车辆避让行人效果研究

为探究车辆右转过程中不同干预方式对驾驶人未规避行人行为的改善情况,设计听觉警示、触觉警示、形式惩罚、利益惩罚和道德惩罚5种干预方式,分为控制组、警示组和惩罚组,试验基于眼动仪和模拟驾驶仪展开。定义注视次数、注视点分布信息熵、平均注视时间、视线转移路径、区域关注概率和瞳孔面积6项指标表征驾驶人眼动特性,提取制动踏板深度比例、行车速度2项指标反映车辆运行状态。经方差分析确定各干预方式差异的显著性水平,从注视特性指标、扫视特性指标、瞳孔面积指标、驾驶人制动指标和机动车制动指标5个方面分析不同干预下驾驶人视觉及操纵响应特征,并收集被试反馈的追踪问卷。试验结果表明：不同干预方式对右转车辆未避让行人均有规范作用,各组干预效果由强到弱依次为利益惩罚、道德惩罚、形式惩罚、触觉警示和听觉警示。利益惩罚性主动干预效果优势显著,注视点分布信息熵最高为0.74,右侧平均注视次数为6次,平均注视时间增加至13.25 s,驾驶人对右侧注视概率增加至0.403,瞳孔面积明显增大,制动踏板深度比例维持在0.8,右转车速下降至20 km·h^-1以下,谨慎驾驶程度和避让行人意识均有提升。一致性追踪问卷调查表明,结束试验时32%的驾驶人对利益惩罚印象深刻,驾驶人对其主观认可度高达83%,具有较强的推广性;该干预方式可帮助驾驶人规范驾驶行为,树立避让行人的安全驾驶意识。     

面向人因的车路协同系统综合测试及影响评估

面向冬奥主干通道兴延高速，以驾驶人适应性为导向，构建一种面向人因的车路协同系统硬件在环效能测试平台，针对多种道路条件、交通状态、特殊事件等面向高速公路设计13种交通情境，从主、客观2个维度实现车路协同系统包括主观感受、高效性、安全性、生态性、舒适性、有效性6个方面的驾驶人适应性评价，分析车路协同驾驶状态下的综合评估指标及影响机理。主观评估结果显示，车路协同技术对驾驶人有积极作用，52%的被试认为车载预警信息可以使行车过程更安全。客观运行结果表明：由于车路协同状态下驾驶人对于前方道路危险状况的可预知性，导致驾驶人提前降速，运行速度降低，效率有所下降；车路协同条件下的加速度和换道次数明显减小，其安全性显著提升；由于车路协同系统避免了驾驶人对于突发危险状况的紧急制动，因此车辆的油耗、排放均明显降低，其生态性改善效果显著；归因于驾驶人对于车路协同系统熟悉程度不足，导致舒适度各系统存在不一致的结论，也表明驾驶人对于车路协同系统的接受度和信任度均有待进一步提高；驾驶人在车路协同条件下可获取不同路段的限速值和超速提示，其有效性表现出明显的优势，速度跟随比有显著提升。所构建的测试平台和指标体系为进一步深层次挖掘车路协同的作用机理奠定了基础。     

城市快速路匝道合流区车辆交互行为模式

在城市快速路匝道合流区,驾驶任务难度主要来自于车辆与其周边车辆之间的动态交互,目前对这种交互行为的特征和机理的认识还不十分清楚。基于从无人机视频中提取的高精度车辆轨迹数据,提取出表征车辆交互行为的指标TTC和GAP,并结合速度、加速度、车道位置等其他指标,对车辆的交互过程加以刻画,从中获得了大量交互行为实例,并在此基础上归纳总结出9种典型的车辆交互行为模式。通过分析各模式特征发现：即使在相同的外部环境下,车辆交互行为模式也可能存在差异,这表明交互行为不仅与车辆之间的相对位置、时空距离、速度状态等环境因素有关,还与驾驶人的应对能力、动机及风险意识等认知心理有关;另外,不同的交互模式面临的风险不同,并且该风险既可能是周边车辆行为发生改变而被迫卷入,也可能是驾驶人自身主动寻求的结果;9种不同类型的交互行为模式,构成了驾驶人自行感知的4种风险状态互相转换的具体实现形式;在驾驶过程中,驾驶人努力寻找契机并选择某种交互行为模式在各个风险状态之间来回切换,并非仅由心理压力较大的危险态向压力较小的自由态转换,也会发生反向转换,前者主要由降低事故风险和减少认知努力的动机驱动,后者旨在追求行车效率,但同时驾驶人会付出更多的认知努力以对抗风险的增加,这充分反映了驾驶人试图在行车效率、事故风险与认知努力三方面取得平衡。研究成果对深化理解驾驶行为及其背后的决策机制具有积极意义。     

A driver-adaptive stability control strategy for sport utility vehicles

Conventional vehicle stability control (VSC) systems are designed for average drivers. For a driver with a good driving skill, the VSC systems may be redundant; for a driver with a poor driving skill, the VSC intervention may be inadequate. To increase safety of sport utility vehicles (SUVs), this paper proposes a novel driver-adaptive VSC (DAVSC) strategy based on scaling the target yaw rate commanded by the driver. The DAVSC system is adaptive to drivers’ driving skills. More control effort would be exerted for drivers with poor driving skills, and vice versa. A sliding mode control (SMC)-based differential braking (DB) controller is designed using a three degrees of freedom (DOF) yaw-plane model. An eight DOF nonlinear yaw-roll model is used to simulate the SUV dynamics. Two driver models, namely longitudinal and lateral, are used to ‘drive’ the virtual SUV. By integrating the virtual SUV, the DB controller, and the driver models, the performance of the DAVSC system is investigated. The simulations demonstrate the effectiveness of the DAVSC strategy.     

Intelligent collision warning using license plate segmentation

Given the increase of vehicles in traffic, traffic accidents have become a crucial and urgent issue for some countries. Particularly, in heavy traffic conditions, rear-end collisions make up the majority of traffic accidents, which make the traffic jam worse. This article proposes a novel approach to rear-end collision warning systems using areas of license plates acquired with a single camera mounted on a car. The edges of the front car's license plate are segmented and a rectangle is sketched to calculate the area, which is used for estimating distance between the cars. Relative speed of the front car is computed using the differences of the rectangles in a specific time. Distance and relative speed are obtained from the estimated areas of the license plates and transferred to the fuzzy inference system to send a warning signal to the driver for collision prevention, in emergency cases. The experiments are greatly encouraging, indicating that number plate segmentation can be utilized to estimate the distance and fuzzy inference system can be developed to create a warning signal to the drivers.     

Comparison of driving characteristics between drivers in Korea and in the united states of America based on driver-vehicle interaction field database

Research and development involving intelligent vehicles of today is geared to safe, driver-friendly and sensitive vehicles that provide a driver with a pleasant and convenient driving environment while preventing him or her from possible risks of accident. In developing convenient and safe vehicles, research on drivers’ driving patterns, reactions and state characteristics depending on road conditions in actual field is essential in order to devise more driver-friendly intelligent vehicles. This paper describes how a driver-vehicle interaction (DVI) field database is built in order to obtain a driver’s input in normal road driving condition on highways, country roads, and city roads, and his or her state information, as well as data on the vehicle and traffic conditions. And the newly built database is compared with the RDCW FOT database established by UMTRI of the US for analysis to suggest that the driving tendencies of drivers in Korea and the road driving conditions are not the same as those in the US, reconfirming the need to establish a DVI field database, which will be used for the development of intelligent vehicles suitable for the Korean environment. The DVI data collected from actual driving in field are anticipated to be widely utilized as basic data for research on various intelligent driving safety systems, advanced driver assistance systems (ADAS) and human-vehicle interface (HVI) that are suitable for the driving environment in Korea.     

智能汽车的人机共驾技术研究现状和发展趋势

智能汽车的人机共驾技术(HM IoIV)是解决其智能化级别难以快速跨越至高度自动化水平的有效过渡手段.HMIoIV涉及了L0～L3级别的智能汽车的多种自动化技术,包括先进辅助驾驶系统.针对当前国内外智能汽车人机共驾技术的研究现状,对其概念、结构和研究内容进行总结,根据独立驾驶人参与的数量和驾驶操作方参与的数量将现有的人...     

An adaptive lateral preview driver model

Successful modelling and simulation of driver behaviour is important for the current industrial thrust of computer-based vehicle development. The main contribution of this paper is the development of an adaptive lateral preview human driver model. This driver model template has a few parameters that can be adjusted to simulate steering actions of human drivers with different driving styles. In other words, this model template can be used in the design process of vehicles and active safety systems to assess their performance under average drivers as well as atypical drivers. We assume that the drivers, regardless of their style, have driven the vehicle long enough to establish an accurate internal model of the vehicle. The proposed driver model is developed using the adaptive predictive control (APC) framework. Three key features are included in the APC framework: use of preview information, internal model identification and weight adjustment to simulate different driving styles. The driver uses predicted vehicle information in a future window to determine the optimal steering action. A tunable parameter is defined to assign relative importance of lateral displacement and yaw error in the cost function to be optimized. The model is tuned to fit three representative drivers obtained from driving simulator data taken from 22 human drivers.     

Factors associated with crashes due to overcorrection or oversteering of vehicles

The objective of this research is to identify factors associated with crashes due to overcorrection or oversteering of vehicles. Crash data was collected from 2011 to 2013 for the State of North Carolina in the United States. Logistic regression modeling was used to analyze crash data because of the dichotomous nature of the dependent variable (overcorrection or oversteering). The crash involvement due to overcorrection or oversteering of a vehicle decreased as the age of the driver increased. Drivers are 2.22 times more likely to overcorrect or oversteer when ill, 3.44 times more likely to overcorrect or oversteer when under fatigue, and 1.61 times more likely to overcorrect or oversteer when fallen asleep compared to normal physical conditions. Overall, driver characteristics and speed limit tend to play a major role in overcorrection or oversteering of vehicles. Programs to reduce impaired driving might help in the reduction of overcorrection or oversteering related crash fatalities or injuries. Additionally, training and driver education programs focusing on identified factors associated with crashes due to overcorrection or oversteering of vehicles will benefit drivers on how to respond during emergency or panic situations.     

节能导向的信号交叉口生态驾驶策略研究

为解决信号交叉口区域车辆频繁启停及怠速停车造成的燃油浪费和污染物排放问题,研究了以节能为导向的信号交叉口的生态驾驶策略问题.借助交叉口区域的V2I通信系统获得车辆自身定位和运动状态数据,以及信号灯状态与配时信息,对车辆所处车速引导场景及可通行性进行判定.对各场景下车辆时空运动轨迹进行分析,综合考虑交叉口上下游的燃油消耗,以平均每公里油耗最小建立统一的优化目标函数,求得生态驾驶轨迹最优解,以向驾驶员提供车速建议.利用M atlab开展的随机仿真实验表明,与不采用生态驾驶车速引导相比,采用生态驾驶车速引导至少可降低10% 以上的燃油消耗.对于划分的6种车速引导场景而言,最优生态驾驶策略在场景2下的节油效果最为显著,可达到30% ~60%;其次是场景4,可达到25% ~50%;在场景3和场景5中表现略差.从节约能源的角度而言,车辆在通过信号交叉口时应尽量避免停车等待,防止发动机长时间空转造成的燃油浪费,必要时可采取适当加减速的方式通过交叉口.      

Influencing driver chosen cornering speed by means of modified steering feel

This paper presents an investigation about influencing the driver's behaviour intuitively by means of modified steering feel. For a rollover indication through haptic feedback a model was developed and tested that returned a warning to the driver about too high vehicle speed. This was realised by modifying the experienced steering wheel torque as a function of the lateral acceleration. The hypothesis for this work was that drivers of heavy vehicles will perform with more margin of safety to the rollover threshold if the steering feel is altered by means of decreased or additionally increased steering wheel torque at high lateral acceleration. Therefore, the model was implemented in a test truck with active steering with torque overlay and used for a track test. Thirty-three drivers took part in the investigation that showed, depending on the parameter setting, a significant decrease of lateral acceleration while cornering.