首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到19条相似文献,搜索用时 265 毫秒
1.
为了定量评估公路路侧行道树事故严重度,有针对性地提出安全改善措施,以减少车辆与路侧行道树碰撞的事故损失,分别引入加速度严重性指数(Acceleration Severity Index,ASI)、头部损伤判据(Head Injury Criteria,HIC)和胸部合成加速度(Chest Resultant Acceleration,CRA)作为乘员伤害指标;利用PC-crash汽车动力学仿真软件构建车辆刚体系统和乘员多体系统,通过设置不同车辆驶出速度、平曲线半径、行道树直径和行道树间距,分别开展小型车、大型车与路侧行道树的偏置碰撞试验,共收集2 256组数据;针对公路直线段和曲线段,分别拟合了基于CRA的小型车乘员伤害评估模型,以及基于ASI的大型车和小型车乘员伤害评估模型;根据Fisher最优分割法确定了路侧行道树事故严重度的合理评价等级及各级对应的ASI和CRA阈值,给出了基于CRA和ASI的路侧行道树事故严重度评价方法;随后提出了一种新的用于评估事故严重度分级准确性的指标-误分级程度,并将其应用于事故严重度评价方法的有效性验证中;最后将大型车比例引入ASI评估模型中并改进了模型。研究结果表明:在相同仿真试验条件下,驾驶人胸部损伤比头部损伤更严重,小型车ASI平均值大于大型车ASI平均值;CRA,ASI与驶出速度近似呈正线性相关,与行道树直径近似呈对数相关;行道树间距越大、平曲线半径越小,则车辆遭受二次碰撞的几率越小,乘员伤害风险越低;在案例分析中,2种分别基于CRA和ASI的路侧行道树事故严重度评价方法评价结果基本一致,且误分级程度分别为4.7%和4.3%,验证了提出的路侧行道树事故严重度评价方法的准确性,并证实了ASI可作为评估路侧行道树事故中乘员伤害的有效指标。  相似文献   

2.
康腾 《汽车文摘》2022,(10):52-56
针对智能驾驶车辆纵向速度跟随问题,为提高智能驾驶车辆在速度变化时的跟踪控制精度,设计了一种分层控制策略。上层控制器设计了一种基于遗传算法的PID控制器,在期望车速为恒速或变速的情况下得到最优的加速度,下层控制通过对加速踏板和制动踏板的标定,得到不同速度和加速度下节气门的开度和制动压力。建立CarSim/Simulink联合仿真模型,完成不同速度工况下的仿真验证,验证结果表明所设计的控制器有效地提高了速度跟踪精度。  相似文献   

3.
为有效刻画未来智能网联环境下交通流微观跟驰行为,以更加精确地进行车辆的运动决策,建立了基于安全势场理论下的车辆跟驰模型。模型以势场理论为基础,首先阐述了交通环境中安全势场的客观性、普遍性以及可测性,然后通过引入加速度参数对既有安全势场模型进行改进,改进后的安全势场模型能够有效刻画出在不同速度、加速度值下车辆安全势场的变化趋势。在分析安全势场变化基础上,构建的车辆跟驰模型强化了加速度参数对车辆跟驰行为的影响,由于不同速度、加速度信息在智能网联环境下车辆可以实时获取,因此该模型可应用于未来智能网联环境中。此外,在模型参数标定过程中,通过对NGSIM数据进行筛选,得到含有较多减速停车以及启动加速状态的轨迹数据,共筛选得到412组NGSIM真实跟驰车对数据,并最终利用人工蜂群算法对该模型进行参数标定。为评估模型仿真效果,选择OVM模型、IDM模型与本文模型进行比较,并选取均方根误差RMSE和平均绝对百分误差MAPE为参数标定结果评价与验证的指标,结果表明,建立的基于安全势场理论的车辆跟驰模型具有良好的精度,适用于描述考虑加速度参数条件下的跟驰行为,可为今后智能网联环境下车辆微观驾驶安全决策、交通流中观安全势场分布、交通流宏观状态估计等奠定理论基础。  相似文献   

4.
我国道路情况复杂多变,构建合适的测试场景对汽车智能驾驶系统测试和评价的有效性起着决定性作用。本文中从我国实际道路出发,从自然驾驶数据中提取具有中国特色的典型场景,筛选出自然驾驶数据中危险工况数据片段,基于此提取出汽车智能驾驶系统综合测试的场景特征要素,并利用聚类分析法得到3类典型危险场景。采用马尔可夫链理论表征前车人类驾驶员驾驶车辆的随机运动特性,将聚类得到各场景下的自车数据作为前车历史工况数据,归纳学习得出马氏链转移概率,并通过马尔可夫链蒙特卡洛模拟预测未来时刻的状态,基于此得到危险场景中前车随机运动预测模型,通过对比原始工况数据验证预测模型的有效性,有效解决了由于采集设备精度低导致的前车数据不准、在测试场景中不能准确表征前车人类驾驶员驾驶车辆随机运动的问题。  相似文献   

5.
为在车辆主动安全系统开发测试中提供具有危险性的典型分心驾驶场景,基于375例分心驾驶事故深度调查案例,确定了包括道路环境、参与方速度和运动状态3个方面的场景参数,对比分析国家统计数据与样本各事故类型间的特征,分别提取出关键特征参数,利用二阶聚类分析方法得到不同事故类型的11类分心驾驶事故典型场景,并结合关键特征参数进一步提炼得到4类核心测试场景。  相似文献   

6.
针对现有端到端自动驾驶模型输入数据类型单一导致预测精确度低的问题,选取RGB图像、深度图像和车辆历史连续运动状态序列作为多模态输入,并利用语义信息构建一种基于时空卷积的多模态多任务(Multimodal Multitask of Spatial-temporal Convolution,MM-STConv)端到端自动驾驶行为决策模型,得到速度和转向多任务预测参量。首先,通过不同复杂度的卷积神经网络提取场景空间位置特征,构建空间特征提取子网络,准确解析场景目标空间特征及语义信息;其次,通过长短期记忆网络(LSTM)编码-解码结构捕捉场景时间上、下文特征,构建时间特征提取子网络,理解并记忆场景时间序列信息;最后,采用硬参数共享方式构建多任务预测子网络,输出速度和转向角的预测值,实现对车辆的行为预测。基于AirSim自动驾驶仿真平台采集虚拟场景数据,以98 200帧虚拟图像及对应的车辆速度和转向角标签作为训练集,历经10 000次训练周期、6 h训练时长后,利用真实驾驶场景数据集BDD100K进行模型的测试与验证工作。研究结果表明:MM-STConv模型的训练误差为0.130 5,预测精确度达到83.6%,在多种真实驾驶场景中预测效果较好;与现有其他主流模型相比,该模型综合场景空间信息与时间序列信息,在预测车辆速度和转向角方面具有明显的优势,可提升模型的预测精度、稳定性和泛化能力。  相似文献   

7.
武和全  张家飞  胡林 《汽车工程》2021,(2):226-231,304
为提高自动驾驶车辆的安全性,提出用一种旋转速度曲线把座椅旋转至指定角度,研究此旋转速度下的乘员生物力学响应。首先,根据所建立的碰撞模型与假人试验数据进行对比验证;其次,改变座椅旋转方向和速度研究乘员旋转至指定位置乘员的生物力学响应。结果表明:在200 ms内采用等腰梯形旋转速度曲线旋转至±45°和±90°不会引起乘员额外的损伤风险。  相似文献   

8.
为实现周围车辆行驶轨迹的准确预测,运用深度学习方法,设计了一种基于图神经网络与门控循环单元(GRU)的驾驶意图识别及车辆轨迹预测模型。驾驶意图识别模型将车-车间的交互关系构造成时空图,运用图神经网络学习其交互规律,并利用Softmax函数计算出不同驾驶意图的概率;轨迹预测模型采用编码-解码的GRU网络,编码器将车辆历史轨迹信息进行编码并融合识别的驾驶意图信息,再通过解码器实现轨迹预测。最后采用NGSIM数据集对模型进行训练和验证,结果表明:所提出的模型能够更好地识别车辆的驾驶意图,且考虑驾驶意图的车辆轨迹预测模型能够有效提高预测精度。  相似文献   

9.
汽车的操纵稳定性是汽车动态性能的重要组成部分,在汽车开发过程中的不同阶段,通常运用主观评价方法或客观评价方法对操纵稳定性进行验证和评价。文章进行了基于驾驶模拟器的汽车操纵稳定性主客观关联技术研究。首先基于驾驶模拟器,运用试验数据标定后的车辆模型,生成了用于主客观关联研究的大量车辆性能数据;基于这些数据,运用岭回归的方法,建立了主客观关联模型,并对模型精度进行了验证。文章的研究成果可以优化车辆性能开发流程,提升车辆开发效率,为汽车的操纵稳定性开发、评价等提供支撑。  相似文献   

10.
为评估智能网联环境下高速公路辅助驾驶车辆编队的效果,首先基于V2X (Vehicle to Everything)和智能驾驶人模型(Intelligent Driver Model,IDM)对网联环境下的车辆跟驰行为进行建模,并对其进行参数校准;其次从安全性评价指标和通行效率两方面构建编队效果评价体系;然后通过VISSIM和VBA联合仿真,改变编队的车道、交通流量、网联车渗透率等变量进行试验。仿真结果表明,网联环境下车辆辅助驾驶编队在不同层面对于安全性与效率性都有提升;最后以不同期望速度在网联环境和非网联环境下分别进行实车辅助驾驶编队试验,以验证评价指标体系以及仿真试验的有效性。其中,实车试验结果显示,期望速度为70 km·h-1时,网联环境下的辅助驾驶编队通行效率比非网联环境提升56%,90 km·h-1时提升37.2%,110 km·h-1时提升39.8%。通过与仿真试验结果对比,表明网联环境下车辆辅助驾驶编队对交通流安全性有一定程度的提升。  相似文献   

11.
A traffic accident is a complex phenomenon with vehicles and human beings involved. During a collision, the vehicle occupant is exposed to substantial loads, which can cause the occupant injuries that depend on the level of passive safety, as well as on the occupant's individual characteristics. Correct estimation of injury severity demands a validated human body model and known impact conditions. A human body modelling procedure for the purpose of accident analysis is introduced. The occupant body has been modelled as a multibody system with rigid body segments connected. Geometrical and inertial properties of individual body segments were estimated using computed tomography. Frontal impact conditions were simulated on a sled test facility, while the human body dynamic response was measured. Comparison of experimental data and computer simulation revealed an influence of joint resistive properties on the occupant motion in collisions. The difference between measured and simulated response was minimised using optimisation method. Individualised human body modelling procedure enabled better prediction of the occupant motion during vehicle collision and thus more precise estimation of possible injuries in real-life traffic accidents.  相似文献   

12.
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.  相似文献   

13.
The aim of the paper was to determine the kinematic parameters that influence the occupant injury risk through a mathematical model. The developed model is a 2D model composed of 4 bodies (2 vehicles, thorax and head). The head and thorax are interconnected with a rotation joint and a torsion spring meant to stiffen the relative movement between the bodies. The thorax is connected with the vehicle body by a linear spring meant to simulate the seatbelt stiffness. The model was solved using Lagrange principle and the validation of the model was made through a crash test performed using the same initial conditions and comparing the obtained values of the displacement, velocity and acceleration parameters with the ones obtained with the mathematical model. The head and torso were chosen due to the fact that they are the common parts of the body that get injured, especially the head with the change of 80 % to cause fatal injury in car’s frontal collision. Once the model was validated, the stiffness of the seatbelt was modified in order to determine the behavior of the occupant in case of car frontal collisions. When the seatbelt stiffness was reduced, the occupant displacement and velocity increased, while by increasing the stiffness, these parameters decreased. The values of the developed model presented a high degree of similarity with the results obtained from the crash test with an error of 10 %. This model can be used by engineers to easily asses the occupant injury risk in case of vehicle frontal collisions.  相似文献   

14.
基于交通事故卷宗、交通事故视频信息数据,研究机非混行交通环境下典型交通事故形态,构建了面向机非混行交通环境下的自动驾驶汽车测试场景,旨在针对我国较为特殊的机非混行环境下的自动驾驶汽车的测试场景及测试评价方法提供参考。本文首先分析了自动驾驶测试场景的构建需求,建立交通事故数据筛选标准,得到133例可用于构建自动驾驶汽车测试场景的机动车与非机动车交通事故数据集;其次基于《中华人民共和国道路交通安全法》行驶要求,对133例交通事故的发生地点、车辆行为、道路类型、环境光线等方面进行解构分析;最后通过聚类分析,建立了5类典型的自动驾驶测试场景模型,并分析了不同场景模型的关键要素,为实际道路测试提供理论指导。  相似文献   

15.
To increase car passenger safety, the Brazilian National Traffic Council (CONTRAN) released Resolution 221, which defines the maximum passenger and driver biomechanical criteria in the event of a vehicle frontal impact. The vehicle maximum allowed biomechanical injury criteria will be enforced from January 2012 for new vehicles and in January 2014 for vehicles in production before January 2014. To standardize the test method to measure the driver and front passenger injury values in a frontal crash, Resolution 221 states that the tests must be performed according to the ABNT NBR 15300-1 standard, followed by the ABNT NBR 15300-2 standard or the ABNT NBR 15300-3 standard. The use of ABNT NBR 15300-2 or ABNT NBR 15300-3 standards is a free choice for the manufacturer of the vehicle. The ABNT NBR 15300-1 + 15300-2 test is similar to the FMVSS 208 standard in the United States in terms of its vehicle frontal impact test perpendicular to a rigid barrier with the use of seat belts by male model dummies. The test according to ABNT NBR 15300-1 + 15300-3 follows the European ECE R94 and 96/79/EC standards. However, ABNT NBR 15300-2 focuses on occupant protection during vehicle deceleration rather than occupant protection during vehicle deformation in a crash test. ABNT NBR 15300-3 tests occupant protection during vehicle deformation more than it tests occupant protection during vehicle deceleration. Therefore, this paper aims to show the types of test results produced by the ABNT NBR 15300-2 and ABNT NBR 15300-3 standards and their differences concerning occupant protection verification and discuss the manufacturer??s freedom of choice.  相似文献   

16.
采用FC-Crash对道路交通事故进行重构已是比较成熟的方法,从中可以获取事故车辆的三维加速度与角加速度波形,但无法模拟出乘员的伤情指标,而Madymo软件是建立包含车体、安全带、安全气囊、假人在内的约束系统模型,在给定的加速度下可以计算出人员的伤害指标。故将PC—Crash与Madymo进行耦合计算,即可获得事故车辆在事故过程中的运动参数,再现驾乘者的运动响应,进而得到人员的伤情指标。这一新的事故再现方法的研究结果表明:PC-Crash与Madymo的耦合计算可较为准确地再现事故车辆的减速和旋转运动状态,以及驾乘人员的响应运动状态,对结合致伤机理深入分析事故原因具有重要的意义,也可为交通事故鉴定提供新思路。  相似文献   

17.
多车协同驾驶是智能车路系统领域的研究热点之一,可有效降低道路交通控制管理的复杂程度,减少环境污染的同时保障道路交通安全。基于多车协同驾驶控制结构,提出了一种无人驾驶车辆换道汇入的驾驶模型及策略,系统分析了多车协同运行状态的稳定条件。在综合分析无人驾驶车辆换道汇入的协作准则、安全性评估后,基于高阶多项式方法,结合车辆运行特性,通过引入乘坐舒适性的指标函数,设计得到无人驾驶车辆换道汇入的有效运动轨迹。通过研究汇入车辆与车队中汇入点前、后各车辆的运动关系,详细分析车辆发生碰撞的类型和影响因素,给出避免碰撞的条件准则,从而确保无人驾驶车辆汇入过程中多车行驶的安全性和稳定性。基于车辆运动学建立车辆位置误差模型,结合系统大范围渐进稳定的条件,选取线速度和角速度作为输入,应用李雅普诺夫稳定性理论和Backstepping非线性控制算法,设计了无人驾驶车辆换道汇入后的路径跟踪控制器。仿真试验和实车试验结果表明:所设计的换道汇入路径是可行、安全的,控制器具有良好的跟踪效果,纵向和横向的距离误差在15 cm以内,方向偏差的相对误差在10%以内。研究结果为智能车路系统中的多车状态变迁与协同驾驶研究提供了参考,可服务于未来道路交通安全设计和评价。  相似文献   

18.
为了总结面向智能车辆的现役道路设施行驶适应性,即现役道路基础设施承载智能车辆行驶的适宜程度,阐述自主智能驾驶定义与驾驶自动化等级分类,在此基础上剖析不同等级间的人机功能差异,并分别从感知层、感知-决策层、决策-控制层探讨与道路设计要素相关联的人机功能差异,通过归纳总结智能车辆与道路几何要素、路面性能及其他道路要素(如道路标线)的相互作用机制研究,从道路工程角度及其他道路要素方面回顾该领域的研究现状,指出存在的问题和未来发展方向。研究结果表明:相比传统车辆,配置高等级自动驾驶系统的智能车辆对现役道路设施行驶适应性最高,主动安全系统次之,而驾驶辅助及有条件自动驾驶系统适应性不足。而目前研究主要问题包括:难以归纳、标定不同驾驶自动化等级间的人机功能差异及其对于道路设计参数的需求设计值;测试道路场景条件过于理想,考虑的驾驶自动化等级单一,试验规模和样本有限;道路几何、路面性能以及道路标志、标线等道路要素与智能车辆间的相互作用机制研究不足,缺乏与不同道路场景相匹配的智能车辆驾驶特征数据的获取手段。因此建议:重视并推动与道路设计要素相关联的关键人机功能差异指标信息共享;联合高保真且可交互的道路场景、高精度感知传感器物理模型、车辆动力学模型及微观交通流模型,利用测试场景自动化生成、极限工况场景搜寻与泛化等技术开展智能驾驶虚拟测试,突破现有研究的深度和广度;探索反映不同等级智能车辆的道路行驶适应性特征指标与评价标准,精准、有效地评估预测复杂道路场景及不利道路条件下的行驶适应性。  相似文献   

19.
Automobile black boxes are devices that collect information regarding vehicle operation and the driver’s operating situation in the case of a traffic accident. The information collected from the automobile black box, which can also be used during normal driving, can provide information about dangerous driving cognition. This study was designed to analyze characteristics of dangerous driving data and build a dangerous driving cognition system as follows. First, dangerous driving is divided into four types by considering the vehicle’s movement, such as acceleration, deceleration, turning and statistical data of traffic accidents. Second, dangerous driving data were collected by vehicle tests using the automobile black box, and characteristics of the driving data were analyzed to classify dangerous driving. Third, a standard threshold was chosen to recognize dangerous driving, and an algorithm of dangerous driving cognition was created. Finally, verification was conducted by vehicle tests with automobile black boxes embedded with the developed algorithm. The presented recognition methods of dangerous driving can be used for on/off-line management of drivers and vehicles. Scientific traffic accident databases can be built with this driving and accident information, and can be used in various industrial areas.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号