FCW系统目标检测距离精度测试与研究

介绍常见的基于单目视觉传感器的目标测距原理,分析不同传感器类型的多款FCW系统报警时间测试现状。针对3种测试场景,对某型单目视觉和视觉与雷达融合的FCW系统进行深度测试,并分析影响两种FCW系统测距精度的主要因素。     

汽车主动防撞系统的规避控制研究

提出了一种汽车主动防撞系统,介绍了该防撞系统的工作原理,并对其规避控制进行了研究。依据汽车运动学理论对安全车距模型进行了分析,建立了包括安全临界、锁定目标、危险临界和极限临界的汽车纵向安全车距模型以及横向安全车距模型;结合安全车距对危险目标进行识别和分类;针对不同危险程度的目标制定了相应的规避控制策略。     

基于LPR的车距测量智能感知系统研究

本文基于车牌识别系统，提出一种基于单目视觉的前方车辆距离测量方法。全文根据图像变换、模型成像、视觉测量等方法，分析研究LPR测距的理论，设计出单目视觉测距的应用模型。利用车辆几何特征信息定位前方车辆的位置图像信息，最终利用车牌信息测量前方车辆距离。     

基于相对运动理论的动态安全车距计算模型

简要介绍了常见的几种汽车防撞报警系统的计算模型,在深入分析其特点的基础上指出了其不足之处,并针对目前汽车防撞报警系统计算模型的不足,分析实际交通情况,经过归纳总结提出了汽车防撞报警系统测距过程中的相对运动理论,并在此基础上提出了动态安全车距的计算模型。     

高速公路车辆防追尾碰撞系统的设计与控制研究

针对汽车追尾碰撞事故频发和事故中驾乘人员头颈部易受损伤等问题,利用激光雷达测距和机电控制相结合的技术,提出了一种车辆防追尾碰撞系统,对高位制动灯和主动式头枕进行控制。首先利用激光雷达和本车状态信息对行车环境进行预测;接着对后车分液压和气压两种制动形式进行行车安全车距的分析,推导出临界安全车距的计算公式;最后通过AT89C51单片机系统预设的程序,将实际行车间距与临界安全车距进行比较,并据此控制高位制动灯的开闭和主动式头枕控制系统的执行。所提出的方法有较好的工程实用性。     

ADAS系统实车道路测试路线方案研究

ADAS系统车辆在进行真实道路实车测试时,对其测试路线进行有效选择和制定是ADAS系统车辆道路测试亟需突破的问题之一。文章基于对ADAS系统环境感知技术的分析,考虑道路交通安全影响因素,提出了ADAS系统车辆测试的道路场景分类及路线选取原则,为提高道路测试效率和效果提供支持。     

基于视觉传感器的ADAS纵向行驶工况识别方法研究

汽车先进驾驶辅助系统在应用时要根据不同的车辆行驶工况对车辆进行相应的控制,而准确的车辆行驶工况识别信号是合理的控制策略的基础.为了得到准确的车辆行驶工况识别信号,利用视觉传感器分别对车辆跟踪定位,以及车道线检测技术进行了研究.利用adaboost分类器检测出前方车辆;应用文中提出的基于坐标映射与定比分线并能够抵抗俯仰角干扰的测距方法进行车辆定位,验证结果显示该测距方法误差小于1m;再应用改进后的基于置信度判断与Kalman滤波技术的车道线跟踪检测方法进行车道线检测,并通过实车道路试验对此进行了验证,验证结果显示该车道线检测方法误差小于1°.提出1种基于PreScan的将所应用的车辆跟踪测距与车道线跟踪检测方法相结合的方法,用以实现汽车ADAS纵向行驶工况的识别,并通过PreScan仿真场景验证了该工况识别方法,结果表明该方法能够为ADAS提供准确的工况识别信号.      

基于模型预测控制的智能车辆纵向控制研究

在ADAS的控制算法中，普遍的控制算法只能在本车道跟车，据此提出一种新方法，不仅能使车辆在本车道内跟车，还能在本车道无车的情况下，进行跨车道跟车。首先在考虑前后车辆制动距离的情况下，对车距算法进行了优化，并把其他车道的车辆通过算法投影至本车道；其次搭建了基于模型预测控制（MPC）算法的车辆离散化模型系统，对其控制参数施加约束；最后通过设置前车不同的车速和车况，在CarSim搭建车辆模型并与Matlab/Simulink联合仿真，针对车辆的纵向加速度变化的研究。     

变道切入场景下 ADAS系统测试与评价研究

为了满足变道切入场景下的ADAS系统测试评价需求,提出一种考虑场景风险系数的变道切入场景生成方法和 客观综合评价模型。通过采集自然驾驶数据,采用阈值法自动提取变道切入功能场景并深入分析变道切入行为特征。使 用单因素方差分析法与皮尔逊相关性检验法共同分析场景风险系数与场景要素的相关性来确定关键场景要素。结合 K-means算法对离散逻辑场景参数进行聚类,从而得到5个典型测试场景。基于场景风险系数,采用AHP与CRITIC法构建 多层次综合评价模型,采用灰色关联理论对 ADAS系统进行客观评价。借助 VTD 仿真软件构建变道切入虚拟测试场景 库,进行仿真试验验证。结果表明,相关性分析使场景要素维度降低了60%,生成的测试场景可以有效验证ADAS系统 的综合性能,综合评价模型可对ADAS系统表现进行客观有效的评价,为智能驾驶系统开发提供有效参考。     

基于单目摄像头的车辆前方道路三维重建

通过构建6自由度车载单目摄像头测距模型,实现了摄像头任意方位变换下车辆前方道路信息的三维重建。同时考虑摄像头的5个畸变参数,可消除由于畸变引起的测距误差。提出一种基于地平线位置的标定方法,在非车载情况下完成了对摄像头的标定,给出了一种利用道路消失点计算道路坡度和车辆偏航角的方法。试验结果表明,所提测距模型和标定方法具有良好的精度和可操作性。     

先进驾驶辅助系统的接受程度及其影响因素分析

研究驾驶人对驾驶辅助系统(ADAS)的接受程度及其影响因素,有利于ADAS的推广和功能改善.招募46名被试,分2次驾驶未安装和安装有ADAS的车辆,行驶于武汉市典型道路各105km,并完成驾驶人基本信息和关于ADAS接受程度问卷.基于技术接受模型(TAM)分析驾驶人对ADAS的接受程度,应用方差分析方法研究驾驶人对ADAS接受程度的影响因素.结果表明,43名驾驶人对ADAS的接受程度均值为80.9%(SD=0.191);驾驶人的性别、年龄和驾驶经验对ADAS的接受程度没有显著性影响;ADAS类别对驾驶人的接受程度有显著性影响,驾驶人对于FCW系统的接受程度较高,而对LDW系统接受程度较低;道路类型对驾驶人的接受程度也有显著性影响,驾驶人在城市道路上对ADAS的接受程度最低.      

Technology analysis and low-cost design of automotive radar for adaptive cruise control system

Recently, the advanced driver assistance system (ADAS), which helps mitigate car accidents, has been developed using environmental detection sensors, such as long and short range radar, lidar, wide dynamic range cameras, ultrasonic sensors and laser scanners. Among these detection sensors, radars can quickly provide drivers with reliable information about the velocity, distance and direction of a target obstacle, as well as information about the vehicle in changing weather conditions. In the adaptive cruise control system (ACCS), three radar sensors are usually needed because two short range radars are used to detect objects in the adjacent lane and one long range radar is used to detect objects in-path. In this paper, low-cost radar based on a single sensor, which can detect objects in both the adjacent lane and in-path, is proposed for use in the ACCS. Before designing the proposed radar, we analyzed the world-wide radar technology and market trends for ACCS. Based on this analysis, we designed a novel radar sensor for the ACCS using radar components, such as an antenna, transceiver module, transceiver control module and signal processing algorithm. Finally, target detection experiments were conducted. In the experimental results, the proposed single radar can successfully complete the detection required for the ACCS. In the conclusion, the perspective and issues in the future development of the ACCS radar are described.     

Design factor optimization of 3D flash lidar sensor based on geometrical model for automated vehicle and advanced driver assistance system applications

Sensor technologies have been innovated and enhanced rapidly for highly automated vehicle and advanced driver assistance systems (ADAS) in automotive industry; however, in order to adopt sensors into mass production vehicle in near future, various requirements should be satisfied such as cost, durability, and maintainance without any loss of overall performance of the sensors. In this sense, a 3D flash lidar is one of primising range sensors because of no moving parts, compact package, and precise measure for distance by using a laser. In spite of the several advantages, the 3D flash lidar is not commonly used in automotive industry because it is quite expensive for adoption and it is manufactured with only general purpose currently; therefore, the cost reduction and optimal design to satisfy various purposes of ADAS or autonomous driving should be accomplished. In this paper, we propose a novel approach for design factor optimization of the 3D flash lidar based on a geometrical model by using structural similarity between the 3D flash lidar and 2D digital camera. In particular, focal length and area of a receiver (focal plane array and read-out integrated circuit) which directly affect on sensor performance (field of view and maximum detection range) are optimized as the design factors. From the optimization results in simulation, we show that optimal design factors according to various purposes required in ADAS could be easily determined and the sensor performances could be evaluated before manufacturing. It will reduce temporal and economic burdens for design and manufacturing in development process.     

基于双目视觉计算的车辆跟驰状态实时感知系统

双目视觉技术能够实现目标的识别与距离计算，在自动驾驶领域有很大的应用空间。然而，现阶段双目视觉存在光照干扰、遮挡、弱纹理区域歧义匹配等问题，影响其测量的准确性和可靠性。提出基于双目视觉的跟驰状态实时感知系统，该系统采用基于车辆跟驰模型的扩展卡尔曼滤波方法对车辆跟驰状态进行实时估计，包括跟驰距离、前后车速度差等。通过实际道路试验，证明了该系统能够识别并修正测量数据中的异常值，解决弱纹理区域误匹配问题。试验结果表明：25 mm焦距与12 mm焦距的双目系统跟驰间距测量值的平均误差分别为2.66%与9.14%；在相对速度测量方面，2种焦距系统的测量精度基本相同，平均误差均为1 m·s^-1左右。所提出的方法在自动驾驶车辆环境感知领域有较好的应用前景。     

Vehicle distance estimation using a mono-camera for FCW/AEB systems

For robust vision-based forward collision warning (FCW) and autonomous emergency braking (AEB) systems, not only reliable detection performance including high detection rate and low false positives but also accurate measurement output of a target vehicle is required. Especially, in order to reduce false alarm or activation of FCW/AEB systems, the systems require the precise measurement output of a target object, such as position, velocity, acceleration, and time-to-collision (TTC). In this study, we developed a measurement estimation algorithm of a target vehicle using a monocular camera. This method estimates two cases of vehicle widths for a target vehicle by using the detected lane information and a pin-hole camera model. After that, the position, velocity, acceleration, and TTC of a target vehicle are estimated by using a Kalman filter for the each estimated vehicle width. To improve robustness, the both estimation results using the detected lane information and the pinhole camera model are fused. This estimation algorithm was evaluated and compared with the state-of-the-art technology. As a result, the proposed measurement output estimation method can improve the performance of the FCW/AEB systems.     

Design and simuation of a vehicle test bed based on intelligent transport systems

As growing demand of vehicle safety system, especially regarding intelligent transport systems (ITS), automotive manufacturers are focusing more on driving safety and efficient transportation for vehicle users. Many safety systems have been launched in the market recently so, it is important to evaluate the vehicle safety systems and ITS. The ITS based intelligent vehicle test bed was constructed to meet the growing demand of test and verification for such ADAS and ITS systems. First, this paper describes in detail concept of the test-bed. This test-bed is carefully designed to meet the requirements of ISO/TC204 standards. In order to verify the design of the test-bed, virtual test with driving siulator was processed on a virtual test tracks. This test-bed will be used to conduct testing on various ITS and ADAS technologies, such as adaptive cruise control (ACC), lane departure warning system (LDWS), cooperative intersection warning system as well as rollover stability control (RSC) and electronic stability control (ESC), etc.     

基于ADAS联网时空数据的路段交通参数估算模型

交通参数实时获取是道路交通管控的重要基础。针对固定检测器观测范围受限和浮动车数量需求大的问题，研究了1种利用车载ADAS联网数据进行路段交通参数估算的方法。通过分析车载ADAS感知的前向目标参数与交通参数的关系，结合广义交通量定义，并考虑多车道条件下ADAS车辆及其邻近前车的相对运动变化特性，建立了1种非稳态交通条件下的交通参数估算模型。在仿真实验环境下获得定参数据集和验证数据集，完成对模型的参数标定和验证，并探讨时空分辨率和ADAS车辆渗透率对模型估算精度的影响规律。基于实验数据分析，结果表明，时间分辨率降低5 min，所提模型估算误差平均减小3.4%，降低时间分辨率可以提升所提模型的估算精度；空间分辨率降低500 m，流量和密度的估算误差平均减小1.68%，却可能导致速度估算误差平均增加5.19%；ADAS车辆渗透率的增长可以增强估算交通参数和观测交通参数在路段时空区域的契合程度。在ADAS逐渐装车应用的背景下，所提的交通参数估算模型可快速、精准获取路段连续时空范围内的交通量信息。      

基于神经网络的智能驾驶模式识别研究

为满足智能驾驶汽车高级驾驶辅助系统(ADAS)功能研发和验证的需求,提高ADAS功能的准确性,设计了一款基于神经网络的智能驾驶模式识别程序,该程序由数据采集、目标检测、场景识别预测3个模块组成。数据采集模块利用ESR毫米波雷达、前置摄像头对交通环境及周围车辆的数据信息进行采集;目标监测模块通过控制算法选择判断触发各类ADAS功能场景的最可疑目标;场景识别处理模块以汽车制造商提供的大量自然驾驶数据的场景挖掘结果为依据,利用神经网络学习各类ADAS场景的特征行为,并通过约束条件对各类ADAS功能场景的识别结果进行实时判定。通过开放道路试验进行验证,结果表明,该程序的场景识别结果准确率可达到99.86%。     

自动驾驶整车在环仿真平台研究及模拟实现

针对目前主流自动驾驶整车测试方法及ADAS整车在环仿真测试方法的特点。利用虚拟现实和实时仿真技术,搭建自动驾驶整车在环仿真平台,并在室内进行仿真平台的模拟实现和案例测试。该平台不仅可以提供丰富的测试环境,危险场景以及难复现的复杂场景进行可重复性测试,而且使用的是真实车辆的车辆动力学特性,无需复杂的车辆动力学模型,同时测试成本也相对低廉。