基于无线通信的车辆主动防撞预警系统设计

提出了一种基于无线通信的车辆主动防撞预警系统,利用梯度方向直方图特征与支持向量机配合单目测距模型实现前方车辆的实时检测与测距,并利用传感器无线通信网络获取相对车速信息,最后根据相对车距与相对车速配合TTC预警模型实现碰撞预警。试验结果表明,系统平均处理时间100ms,车辆检测准确率95%,单目测距误差小于±4m,实现了实时、准确的车辆预警。     

高速公路场景的车路视觉协同行车安全预警算法

目的 基于视觉的车辆行驶安全性预警分析技术是目前车辆辅助驾驶的一个重要研究方向,对前方多车道快速行驶的车辆进行精准的跟踪定位并建立稳定可靠的安全距离预警模型是当前研究难点。为此,提出面向高速公路场景的车路视觉协同行车安全预警算法。方法 首先提出一种深度卷积神经网络SF_YOLOv4（single feature you look only once v4）对前方车辆进行精准的检测跟踪;然后提出一种安全距离模型对车辆刹车距离进行计算,并根据单目视觉原理计算车辆间距离;最后提出多车道预警模型对自车行驶过程的安全性进行分析,并对司机给予相应安全提示。结果 实验结果表明,提出的SF_YOLOv4算法对车辆检测的准确率为93.55%,检测速度（25帧/s）领先对比算法,有效降低了算法的时间和空间复杂度;提出的安全距离模型计算的不同类型车辆的刹车距离误差小于0.1 m,与交通法建议的距离相比,本文方法计算的安全距离精确度明显提升;提出的多车道安全预警模型与马自达6（ATENZA）自带的前方碰撞系统相比,能对相邻车道车辆进行预警,并提前0.7 s对前方变道车辆发出预警。结论 提出的多车道预警模型充分考虑高速公路上相邻车道中的车辆位置变化发生的碰撞事故;本文方法与传统方法相比,具有较高实用性,其预警效果更加客观,预警范围更广,可以有效提高高速公路上的行车安全。     

Aerodynamic drag reduction on a realistic vehicle using continuous blowing

The aerodynamic drag reduction of a realistic vehicle model through continuous blowing was numerically analyzed based on the open-source computational fluid dynamics (CFD) program, OpenFOAM. Simulations were performed on a realistic passenger vehicle model with available wind tunnel test data, DrivAer, at four different Reynolds numbers (Re). The aerodynamic drag coefficient decreased with increasing Re. The CFD technique was validated by comparing the aerodynamic drag coefficients at Re = 4.87 × 10⁶. Predicted drag coefficients of the DrivAer estate model show less than 3% difference from wind tunnel test data, whereas those of fastback and notchback vehicles showed less than 1% difference. Sectional pressure distributions agreed well with wind tunnel test data. The effect of continuous blowing was investigated using the DrivAer estate model with a blowing position at the end of the roof for vertical blowing and at the C-pillar for lateral blowing. Simulations were performed at Re = 4.87 × 10⁶ and 9.75 × 10⁶ and blowing speeds of 20%, 40%, 60%, and 100% of the vehicle driving speed. The effect of continuous blowing increased with Re. The drag reduction was more than 6% for roof blowing due to increasing rear pressure when the blowing speed equaled the vehicle driving speed. The maximum drag reduction was approximately 7.5% for simultaneous roof and lateral blowing. The results indicate that continuous blowing can efficiently reduce vehicle aerodynamic drag and consequently greenhouse gas emissions.

     

基于车车通信的前向碰撞预警策略

针对车车（V2V）通信下前向碰撞预警（FCW）系统延时时间内,传统模型假定主车匀速和全球定位系统（GPS）无误差从而明显低估碰撞风险的问题,提出了一种修正GPS误差及考虑延时时间内主车运动状态的FCW策略。首先,分析了基于V2V通信的FCW系统的整体工作流程,并对其中的关键延时采用高斯模型进行建模;其次,确立了修正GPS误差并考虑延时时间内主车运动状态的碰撞避免模型,并根据远车匀速、加速、减速分为三种不同场景制定相应的预警策略;最后,针对延时时间内主车加速运动的情形,通过Matlab对提出的FCW策略进行仿真。仿真结果显示该预警策略的平均成功避撞率可达96%,表明了它在不同场景下预警的有效性。     

基于802.11p协议改进的车辆测距算法

随着交通事故的增长和智能交通的发展,基于车辆碰撞预警和交通管理的新服务引起了广泛关注。目前,基于全球导航卫星系统(GNSS)的定位技术已应用到车辆环境中。由于GNSS存在的盲区(例如森林,隧道等)会导致定位结果不准确,在车辆自组织网络(VANET)中,提出了基于IEEE 802.11p标准的定位方法。提出了用IEEE 802.11p短前导码的高效到达时间(TOA)或测距估计方法,以降低低信噪比(SNR)的影响。使用了自相关和互相关(混合相关)来执行到达时间(TOA)估计,对相关结果进行间隔求和的方法以达到更精确定位的目的。在加性高斯白噪声(AWGN)信道中的仿真结果表明:在低SNR条件中,提出的测距方法相比传统方法达到了更高的精度。     

风力发电机在线状态监测仪的设计及应用

设计了基于TMS320 F2812芯片的DSP在线状态监测系统,此系统既可独立运行,又可与上位机配合工作,实现了数据采集、数据分析、故障预警、数据存储与上位机通信等功能.采集的数据经过滤波后,计算时域指标并将其与设定阈值比较,作为预警依据,之后对其进行FFT分析和Hilbert解调分析,分别得到信号的幅值谱和包络谱,以此来对风力发电机的状态进行监测.仿真分析和齿轮故障实验验证了DSP监测仪的有效性和可靠性.     

基于单目视觉的车辆碰撞预警系统

基于单目视觉的车辆碰撞预警系统能够发现道路前方的车辆并估算出与前方车辆之间的距离,利用预警机制及时提醒驾驶员危险状况。车道检测和车辆识别是该系统需要解决的两个主要难题，提出了利用边缘分布函数EDF检测车道标线，利用车辆底部纹理和对称性特征识别车辆，并根据图像坐标系和世界坐标系之间的几何映射关系测距。实验结果表明，提出的方法能够有效检测出车道标线，并能很好地测定与前车的距离。     

重型车辆侧翻预警算法研究

针对重型车辆在行驶过程中非绊倒型侧翻预警实现问题,建立了三自由度车辆侧翻模型并设计了以侧翻时间（TTR）为预警标准的算法。考虑到预警算法中动态门限值中某些参数难于直接测取的问题,将Kalman滤波技术融合于其中,提出了基于车身侧倾角估计的TTR侧翻预警算法,实现车辆动态侧翻特性的精确预测。而后利用Matlab/Simulink与Trucksim软件联合仿真对侧翻预警算法进行验证。结果表明,基于车身侧倾角估计的重型车辆侧翻预警算法能够顺利运行,为非绊倒型侧翻预警问题提供了一种新的设计思路。     

Design and research of automobile anti-collision warning system based on monocular vision sensor with license plate cooperative target

At present, detection method for the target vehicle based on monocular vision sensor uses the whole vehicle as targets. The automobile anti-collision technology proposed in this paper adopts monocular vision sensor for automobile measurement based on vehicle license plate cooperative target. Monocular vision sensor has advantages of good real-time performance and low cost. The technique can improve the detection capability of vehicle collision avoidance warning systems. In addition to the target vehicle positioning, it can also realize attitude determination. This technology eliminates the limits of road surface roughness and fluctuation. This paper designs the realization scheme of collision warning system based on monocular vision sensor from the automobile license plate cooperative target. Technology roadmap of automobile collision warning system is given. In this paper, license plate frame location is as the research background. The paper presents an analytic solution of positioning method for the license plate frame image. The method uses four vertex characteristics of license plate frame image to locate. Positioning speed of the method is fast. And it has a unique solution. This method can be used to positioning for the license plate frame. Simulation experiment is done for the collision warning location. The simulation results show that this method can locate the position for license plate frame image. License plate is regular shape, uniform, with identity recognition function markers on the automobile body. In the previous research on automotive collision warning and intelligent vehicle, we have not seen the research methods similar to the method introduced in this paper. The research enriches automobile anti-collision technology and theory of intelligent vehicle technology. It can also provide an auxiliary method for navigation and obstacle avoidance research for unmanned vehicle. It has certain scientific significance. Vehicle collision warning system can help the driver judgment, prompting warning, improving driving safety, and has broad application prospects.     

A novel obstacle avoidance algorithm: “Follow the Gap Method”

In this paper, a novel obstacle avoidance method is designed and applied to an experimental autonomous ground vehicle system. The proposed method brings a new solution to the problem and has several advantages compared to previous methods. This novel algorithm is easy to tune and it takes into consideration the field of view and the nonholonomic constraints of the robot. Moreover the method does not have a local minimum problem and results in safer trajectories because of its inherent properties in the definition of the algorithm. The proposed algorithm is tested in simulations and after the observation of successful results, experimental tests are performed using static and dynamic obstacle scenarios. The experimental test platform is an autonomous ground vehicle with Ackermann steering geometry which brings nonholonomic constraints to the vehicle. Experimental results show that the task of obstacle avoidance can be achieved using the algorithm on the autonomous vehicle platform. The algorithm is very promising for application in mobile and industrial robotics where obstacle avoidance is a feature of the robotic system.     

车路视觉协同的高速公路防碰撞预警算法

目的 基于视觉的前车防碰撞预警技术是汽车主动安全领域的一个重要研究方向,其中对前车进行快速准确检测并建立稳定可靠的安全距离模型是该技术亟待解决的两个难点。为此,本文提出车路视觉协同的高速公路防碰撞预警算法。方法 将通过图像处理技术检测出来的视频图像中的车道线和自车的行驶速度作为输入,运用安全区实时计算算法构建安全距离模型,在当前车辆前方形成一块预警安全区域。采用深度神经网络YOLOv3（you only look once v3）对前车进行实时检测,得到车辆的位置信息。根据图像中前车的位置和构建的安全距离模型,对可能发生的追尾碰撞事故进行预测。结果 实验结果表明,重新训练的YOLOv3算法车辆检测准确率为98.04%,提出算法与马自达CX-4的FOW（forward obstruction warning）前方碰撞预警系统相比,能够侧向和前向预警,并提前0.8 s发出警报。结论 本文方法与传统的车载超声波、雷达或激光测距的防碰撞预警方法相比,具有较强的适用性和稳定性,预警准确率高,可以帮助提高司机在高速公路上的行车安全性。     

Test road experiment on imminent warning rear lighting and signaling

OBJECTIVE: This paper describes an experiment directed toward refinement and initial field testing of two potential countermeasures for the problem of rear-end (RE) crashes. The countermeasures consist of "imminent warning" signals intended to direct the following driver's visual glance to the lead vehicle as it brakes rapidly to a stop and for a short time thereafter. BACKGROUND: RE crashes are the most frequently occurring type of light vehicle crash, making up at least 25% of all crashes. METHOD: A preliminary experiment was conducted to facilitate improvement of the attention-getting capability of an alternating pair of lamps. In the main experiment, an oscillating narrow beam lamp (a promising candidate from a previous experiment) and an improved alternating pair (improved as compared with that in a previous experiment) were compared with ordinary rear lighting. Seventy-two drivers were purposely distracted by in-vehicle tasks as the lead (surrogate) vehicle braked hard. RESULTS: Results showed improvements of 0.25 to 0.35 s in brake activation times for the two enhanced configurations as compared with ordinary rear lighting. CONCLUSION: The two enhanced lighting configurations show promise in reducing the number and severity of RE crashes. APPLICATION: The methods and results of this study can be applied to the future design and evaluation of automotive rear-end lighting designed to reduce RE crashes.     

一种用于高速公路上防车辆连环碰撞的V2V广播协议

目前,V2V网络主要通过周期性广播紧急预警消息(emergency warning message,EWM)来解决高速公路上经常发生的连环碰撞事件,但是周期性广播EWM容易产生广播风暴,造成大量消息的传输失败和传输延时,从而影响了预警网络的可靠性和效率.通过研究V2V网络中的各种无线广播协议,提出了一种用于高速公路上防止车辆连环碰撞的广播协议.协议在方向性广播的基础上,通过发送ACK帧选择广播车辆并由广播车辆负责广播EWM来解决广播协议中的EWM冗余问题.仿真实验表明:协议能有效地控制EWM的冗余问题,提高EWM传输的可靠性并降低传输延时.     

基于时空自编码网络的风电齿轮箱状态监测

在风电机组状态监测问题中,常规自编码网络通常仅使用截面SCADA(supervisory control and data acquisition)数据,使得网络对数据时间特征的学习不足。因此,提出一种基于时空自编码网络的风电齿轮箱状态监测方法：使用1维卷积网络(1DCNN)级联双向长短时记忆网络(Bi-LSTM)作为编码层,序贯提取面板数据的空间及时间特征,以输入的重构误差作为预警指标实现在线状态监测。使用河北省某风电场实际数据验证,结果表明：相比故障记录时刻,时空自编码网络能提前20 d发出报警信号,且故障检出率和误报警次数均优于常规方法;通过分析重构误差各分量的贡献率,可知该齿轮箱故障中主要异常参数为油路压力和油池温度。     

Efficient stochastic hybrid heuristics for the multi-depot vehicle routing problem

The paper addresses the problem of multi-depot vehicle routing in order to minimize the delivery time of vehicle objective. Three hybrid heuristics are presented to solve the multi-depot vehicle routing problem. Each hybrid heuristic combines elements from both constructive heuristic search and improvement techniques. The improvement techniques are deterministic, stochastic and simulated annealing (SA) methods. Experiments are run on a number of randomly generated test problems of varying depots and customer sizes. Our heuristics are shown to outperform one of the best-known existing heuristic. Statistical tests of significance are performed to substantiate the claims of improvement.     

电动车辆路径优化研究与进展

随着绿色物流的兴起,电动车辆应用研究引起人们的极大关注.电动车辆路径优化问题(Electric vehicle routing problem,EVRP)是电动车运行管理和物流优化中的核心问题之一.对此,首先介绍电动车辆路径问题的研究现状;然后,从充电优化、路径优化和车队配置优化的不同侧重角度,着重介绍3种路径优化分支,并对各种求解方法进行分类对比讨论;最后,对电动车辆路径优化的未来发展趋势进行展望.     

The impact of artificial vehicle sounds for pedestrians on driver stress

Electrically based vehicles have produced some concern over their lack of sound, but the impact of artificial sounds now being implemented have not been examined in respect to their effects upon the driver. The impact of two different implementations of vehicle sound on driver stress in electric vehicles was examined. A Nissan HEV running in electric vehicle mode was driven by participants in an area of congestion using three sound implementations: (1) no artificial sounds, (2) manually engaged sounds and (3) automatically engaged sounds. Physiological and self-report questionnaire measures were collected to determine stress and acceptance of the automated sound protocol. Driver stress was significantly higher in the manually activated warning condition, compared to both no artificial sounds and automatically engaged sounds. Implications for automation usage and measurement methods are discussed and future research directions suggested.

Practitioner Summary: The advent of hybrid- and all-electric vehicles has created a need for artificial warning signals for pedestrian safety that place task demands on drivers. We investigated drivers’ stress differences in response to varying conditions of warning signals for pedestrians. Driver stress was lower when noises were automated.     

基于3S技术的危运监控预警平台设计

危险品道路运输的安全监管涉及多个部门,建立统一的监控与预警平台很有意义.车载模块集成多传感节点实时采集危运车辆实时数据,GPS技术应用于车辆定位功能,GPRS用于信息上传,GIS技术完成车辆定位的地图显示与操作,同时也集成了车辆、车主、危险品的信息.综合应用3S技术,论文设计危运监控预警平台,将车辆跟踪定位、车况实时采集、应急预警处理集中到平台上,有效解决现有监控智能化与数据整合度不足等问题.     

Head-up Display Graphic Warning System Facilitates Simulated Driving Performance

This study aims to investigate the usability of a head-up display (HUD) in presenting warning messages during driving and create a new and effective vehicle early warning system for drivers. Two experiments were conducted. In Experiment 1, 36 drivers were randomly assigned to a group using HUD and a control group. The simulated driving performance of the two groups was compared to determine if the HUD graphic early warning system facilitates driving safety. Results revealed that the HUD-using group demonstrated better driving performance than the control group in terms of collision, mean deceleration, accelerator release reaction time, brake reaction time, reduced velocity, reduced energy, steering reaction time, mean reaction time, and minimum reaction time. We investigated the influence of the presentation mode of warning messages on simulated driving performance in Experiment 2. Forty-eight drivers were randomly assigned to an HUD warning group, an audio warning group, and an audiovisual group that integrated HUD and audio warning. The drivers in the HUD warning group performed better than those in the two other groups in terms of mean deceleration. The audiovisual group that integrated HUD and audio warning showed an advantage in reduced velocity. The findings indicated that HUD technology has the potential to promote safe driving by improving the early warning system.     

基于高斯混合隐马尔科夫模型的自由换道识别

驾驶辅助系统被认为是解决交通安全问题的有效手段, 开发驾驶辅助系统的基础是对车辆的行为进行准确的识别, 以应用于车辆安全预警, 路径规划, 智能导航等方面. 目前存在的基于支持向量机模型, 隐马尔科夫模型, 卷积神经网络等行为识别方法还存在计算量与精度平衡的问题. 本文结合了隐马尔科夫模型与高斯混合模型, 提出了高斯混合隐马尔科夫模型, 利用美国联邦公路管理局NGSIM数据集对此方法进行了实验验证, 结果表明该方法对自由换道行为识别具有较高的精度. 本文还对高斯混合隐马尔科夫模型的实验参数进行了优化, 以期达到最好的识别效果, 为未来智能驾驶的车辆行为识别提供了参考.