End-to-end learning for high-precision lane keeping via multi-state model

High-precision lane keeping is essential for the future autonomous driving.However,due to the imbalanced and inaccurate datasets collected by human drivers,current end-to-end driving models have poor lane keeping the effect.To improve the precision of lane keeping,this study presents a novel multi-state model-based end-to-end lane keeping method.First,three driving states will be defined:going straight,turning right and turning left.Second,the finite-state machine(FSM)table as well as three kinds of training datasets will be generated based on the three driving states.Instead of collecting the dataset by human drivers,the accurate dataset will be collected by the high-performance path following controller.Third,three sets of parameters based on 3DCNN-LSTM model will be trained for going straight,turning left and turning right,which will be combined with FSM table to form a multi-state model.This study evaluates the multi-state model by testing it on five tracks and recording the lane keeping error.The result shows the multi-state model-based end-to-end method performs the higher precision of lane keeping than the traditional single end-to-end model.

Data Logic Structure and Key Technologies on Intelligent High-precision Map

Taking autonomous driving and driverless as the research object,we discuss and define intelligent high-precision map.Intelligent high-precision map is considered as a key link of future travel,a carrier of real-time perception of traffic resources in the entire space-time range,and the criterion for the operation and control of the whole process of the vehicle.As a new form of map,it has distinctive features in terms of cartography theory and application requirements compared with traditional navigation electronic maps.Thus,it is necessary to analyze and discuss its key features and problems to promote the development of research and application of intelligent high-precision map.Accordingly,we propose an information transmission model based on the cartography theory and combine the wheeled robot’s control flow in practical application.Next,we put forward the data logic structure of intelligent high-precision map,and analyze its application in autonomous driving.Then,we summarize the computing mode of“Crowdsourcing+Edge-Cloud Collaborative Computing”,and carry out key technical analysis on how to improve the quality of crowdsourced data.We also analyze the effective application scenarios of intelligent high-precision map in the future.Finally,we present some thoughts and suggestions for the future development of this field.

A Flexible Multi-Layer Map Model Designed for Lane-Level Route Planning in Autonomous Vehicles

An increasing number of drivers are relying on digital map navigation systems in vehicles or mobile phones to select optimal driving routes in order to save time and improve safety. In the near future, digital map navigation systems are expected to play more important roles in transportation systems. In order to extend current navigation systems to more applications, two fundamental problems must be resolved: the lane-level map model and lane-level route planning. This study proposes solutions to both problems. The current limitation of the lane-level map model is not its accuracy but its flexibility;this study proposes a novel seven-layer map structure, called as Tsinghua map model, which is able to support autonomous driving in a flexible and efficient way. For lane-level route planning, we propose a hierarchical route-searching algorithm to accelerate the planning process, even in the presence of complicated lane networks. In addition, we model the travel costs allocated for lane-level road networks by analyzing vehicle maneuvers in traversing lanes, changing lanes, and turning at intersections. Tests were performed on both a grid network and a real lane-level road network to demonstrate the validity and efficiency of the proposed algorithm.

A Lane-Level Road Marking Map Using a Monocular Camera

The essential requirement for precise localization of a self-driving car is a lane-level map which includes road markings(RMs).Obviously,we can build the lane-level map by running a mobile mapping system(MMS)which is equipped with a high-end 3D LiDAR and a number of high-cost sensors.This approach,however,is highly expensive and ineffective since a single high-end MMS must visit every place for mapping.In this paper,a lane-level RM mapping system using a monocular camera is developed.The developed system can be considered as an alternative to expensive high-end MMS.The developed RM map includes the information of road lanes(RLs)and symbolic road markings(SRMs).First,to build a lane-level RM map,the RMs are segmented at pixel level through the deep learning network.The network is named RMNet.The segmented RMs are then gathered to build a lane-level RM map.Second,the lane-level map is improved through loop-closure detection and graph optimization.To train the RMNet and build a lane-level RM map,a new dataset named SeRM set is developed.The set is a large dataset for lane-level RM mapping and it includes a total of 25157 pixel-wise annotated images and 21000 position labeled images.Finally,the proposed lane-level map building method is applied to SeRM set and its validity is demonstrated through experimentation.

Developing High-Precision Maps for Automated Driving in China:Legal Obstacles and the Way to Overcome Them

A high-precision map(HPM)is the key infrastructure to realizing the function of automated driving(AD)and ensuring its safety.However,the current laws and regulations on HPMs in China can lead to serious legal compliance problems.Thus,proper measures should be taken to remove these barriers.Starting with a complete view of the current legal obstacles to HPMs in China,this study first explains why these legal obstacles exist and the types of legal interests they are trying to protect.It then analyzes whether new technology could be used as an alternative to resolve these concerns.Factors such as national security,AD industry needs,and personal data protection,as well as the flexibility of applying technology,are discussed and analyzed hierarchically for this purpose.This study proposes that China should adhere to national security and AD industry development,pass new technical regulations that redefine the scope of national security regarding geographic information in the field of HPMs,and establish a national platform under the guidance and monitoring of the government to integrate scattered resources and promote the development of HPMs via crowdsourcing.Regarding the legal obstacles with higher technical plasticity,priority should be given to technical solutions such as“available but invisible”technology.Compared with the previous research,this study reveals the current legal barriers in China that have different levels of relevance to national security and different technical plasticity.It also proposes original measures to remove them,such as coordinating national security with the development of the AD industry,reshaping the boundary of national security and industrial interests,and giving priority to technical solutions for legal barriers that have strong technical plasticity.

Robust lane recognition for structured road based on monocular vision

A robust lane detection and tracking system based on monocular vision is presented in this paper. First, the lane detection algorithm can transform raw images into top view images by inverse perspective mapping （ IPM）, and detect both inner sides of the lane accurately from the top view im- ages. Then the system will turn to lane tracking procedures to extract the lane according to the infor- mation of last frame. If it fails to track the lane, lane detection will be triggered again until the true lane is found. In this system, 0-oriented Hough transform is applied to extract candidate lane mark- ers, and a geometrical analysis of the lane candidates is proposed to remove the outliers. Additional- ly, vanishing point and region of interest（ROI） dynamically planning are used to enhance the accura- cy and efficiency. The system was tested under various road conditions, and the result turned out to be robust and reliable.

High-precision group-delay dispersion measurements of optical fibers via fingerprint-spectral wavelength-to-time mapping

The group-delay dispersion of an optical fiber was measured with the time-of-flight method, using fingerprint-like characteristic spectra from a mode-locked fiber laser source. To determine the group-delay dispersion up to the fourth order, least-squares fitting was applied to the overall time waveform mapped on the time axis for the fingerprint-spectral broadband pulses through a long optical fiber. The analysis of all 4003 data points reduced statistical uncertainty, and provided second-, third-, and fourth-order dispersion with uncertainties of 0.02%, 0.4%, and 4%,respectively.

基于线性逼近的车道线弯道识别方法

为提高车道线识别算法在大曲率弯道下的识别性能,提出一种基于线性逼近的弯道识别方法.基于车道线先验知识,利用改进的局部逆透视变换和Hough变换对车道线进行初步提取.根据初步提取结果,对未知区域进行循环线性逼近并提取车道线边界点.通过最小二乘法利用B-样条曲线完成车道线拟合.实验证明,该算法对大曲率弯道的车道线识别具有较高的精确性.

一种鲁棒的非平坦路面车道线检测算法

提出了一种鲁棒的非平坦路面车道线检测算法.给出一种简单的逆透视变换方法,该方法不依赖于摄像机参数,计算简便.基于法向车道线模型研究了车道线的线特征提取方法,结合线特征的方向特性和强度信息,提出了改进的Hough变换车道线直线检测方法,有效提高了检测的鲁棒性和计算速度.利用检测出的直线对车道线进行精确定位,采用加权最小二乘曲线拟合方法完整地提取出图像中的车道线.实验证明,算法在弯道和非平坦路面上都能准确地提取出车道线,具有较强的鲁棒性.

基于行为注记法的休闲街区夜间旅游活动研究

引入行为注记法对南京门东箍桶巷示范片区夜间旅游活动进行调研。通过分析旅游者行为与季节、节假日、夜晚时间点和休闲街区空间布局的相关性来研究夜游活动的时空规律。结果表明:人们习惯于在节假日、夏季夜晚出游,其中女性和中年旅游者比例最高,活动方式以动态活动为主,在19:30和20:30达到出游高峰;休闲街区人群密度与静态活动分布具有一致性,有多样吸引物的复合空间吸引力较大,女性对滨水空间、观影空间和手工艺展示区情有独钟,青少年偏爱滨水空间,而老年旅游者多集聚在亭廊空间中,中年人是户外咖啡座的主要使用人群。掌握不同旅游人群需求、拓展夜游时间广度、复合利用街区空间是休闲街区夜游开发应重视的问题。

基于道路结构特征的自主车视觉导航

基于计算机视觉技术的道路检测,针对红旗轿车自主驾驶系统的视觉导航,提出并实现了一种基于道路结构特征的自主车视觉导航方法。该方法根据高速公路上道路标志线平行、等宽等特征,将车载摄像机获取的道路图像投影到道路平面上,再运用这些特征来提取标志线像素。在此基础上根据公路道路模型,建立参数空间搜索最优参数,得到道路标志线的参数表达,实现视觉导航,并给出了C市环城高速上的实验结果。

逆透视投影下车道偏离时间的在线估计

提出了一种基于图像逆透视变换后的车道偏离时间的实时在线估计算法。该算法先对道路图像进行预处理,得到二值化的道路图像,然后通过逆透视变换方法消除图像的透视效果,用Hough变换方法检测车辆所在车道的左右道路标志线,最后估算车辆偏离车道的时间,判定车辆是否会偏离车道。对该算法进行了详细介绍并给出了实验结果,结果表明该算法能够准确地判断车道偏离。

通用化高精地图数据模型

高精地图逐渐成为自动驾驶不可或缺的组成部分,但是其数据模型和表达方式尚未形成统一标准,特别是在生产制作和数据交换阶段,缺乏具备通用性和大规模应用能力的数据模型。针对这一问题,本文分析了当前主流高精地图数据模型NDS、OpenDRIVE和lanelet的优缺点,提出了一种通用化的高精地图数据模型Whu map model。车道模型方面,采用车道组为数据管理单元,由同一路段上的一个或者多个车道组成。车道由车道的左边界线、右边界线、车道中心线、车道属性构成。通过多种常见车道数变化场景下的车道拓扑构建,验证了该模型在表达上的有效性和稳健性。交通标志物模型方面,定义了地面标志物和交通标志牌,分别表达形状、类型、语义以及与道路、车道的关联关系等内容。通过大规模数据制作、NDS和OpenDRIVE格式编译,以及基于ADASIS V3协议的电子地平线应用试验,验证了Whu map model模型的实用性和有效性。Whu map model可以作为通用的交换规格,也可以应用到高精地图生产制作的各个阶段,同时向下兼容、易于扩展,有助于实现高精地图数据模型标准化,从而推进高精地图的规模化生产和应用。

基于多通道融合和极线约束的道路检测与定位

计算机双目视觉道路检测及定位在实现无人运动平台自主导航中具有重要意义.根据双目摄像机系统模型,提出基于多通道阈值融合的车道线检测方法,融合车道线边缘和色彩信息进行图像阈值分割,采用透视变换和自适应动态滑窗法提取车道线像素,采用最小二乘法拟合道路模型并依据极线约束关系进行定位,投影至SLAM地图中.实验结果表明,算法在光照变化、阴影遮挡等场景中均能精确检测车道线,将车道线信息投影至三维地图可以有效地将车道信息与地图信息进行融合,提高了道路感知能力.

基于多传感融合的车道线检测与跟踪方法的研究

车道线的有效检测与跟踪是智能车正确识别道路的前提。针对现有车道线检测与跟踪算法效率不高的难题,提出了一种基于视觉传感器与车道级高精度地图相融合的车道线检测与跟踪方法。该方法首先用改进的Hough变换提取边缘线段;然后基于滤波预测与更新车道线模型状态参数;最后结合高精度地图中车道线先验模型参数,跟踪车道线轨迹。现场实测结果表明,算法的实时性和鲁棒性满足算法性能评价体系的各项指标,较符合智能车对车道线检测的要求。

基于梯度增强和逆透视验证的车道线检测

为解决高速公路和城市道路上复杂条件下的弱线漏检问题,提出了一种基于梯度增强和逆透视验证的车道线检测方法。该方法使用车道线的结构和对比度特征提取车道线区域,利用提取的车道线区域进行车道线和道路样本的选择,并采用基于模糊线性鉴别分析获得从彩色RGB图像到灰度图像变换的最佳投影系数,以确保车道线和道路像素间的灰度差异最大,从而有效突出道路上的弱线;利用逆透视变换对候选车道线间的空间位置关系进一步验证,以此找回漏检的虚线。不同场景、不同天气状况下的实际道路图像的实验表明,方法具有很好的鲁棒性和准确性。

车载移动执法中违规车辆智能检测研究

提出了一个面向高速道路交通车辆违规行为移动执法智能检测模型。系统模型分为车道线检测、车辆检测与跟踪、逆透视变换及几何量算、面向车道定位的地图精细匹配等4个子模块。该系统模型算法在实际高速公路环境中进行了车辆违规行为检测,以及车道线检测、车辆目标及跟踪等专项测试以表征其对车辆违规行为的检测能力。测试结果表明,该系统模型具备在一定的复杂交通环境中车辆违规行为辨识能力。相关专项测试表明,该模型可以快速及准确地检测记录违规车辆。

Banach空间中型如F_X－A_X＝0方程解的存在性定理

本文结合弱内向性条件给出了几个关于型如Ｆ＿Ｘ－Ａ＿Ｘ＝０算子方程解的存在性定理，它们推广和改进了［１，２，７］中某些重要结论，

基于逆透视变换的车辆排队长度检测方法及硬件实现

交通路口的车辆排队长度检测是智能交通系统的重要组成部分,传统的检测方法易受背景噪声、摄像机透视效果等因素的干扰造成检测失败,而且其实现都是基于串行结构的处理器,不能用于实时处理的场合;设计了一种充分利用平直道路几何特征并适合FPGA实现的排队长度自动检测算法,该算法利用逆透视变换消除图像几何失真,引入公路的结构性约束有效检测了车道线;接着采用Sobel边缘算子检测出各车道的车辆轮廓,通过一种基于信息量的度量方法提取排队的队尾,从而确定了车辆排队长度,并且通过硬件化设计使得整个检测过程达到实时的处理速度;试验结果表明,在消除了视觉偏差的图像上进行的排队长度检测结果比校正前更加真实准确,所提出的检测方法可以很容易工程化并用于实际交通路口的车流量自动实时检测。

基于移动测量技术的车道级道路电子地图制作

高精度车道级道路电子地图是实现车道级导航与监控的基础地理信息数据和必要条件,未来在无人驾驶汽车方面具有广阔的应用空间。据此,研究了车道级道路电子地图的制作,实现了路径为通过高精度、高分辨率道路得到的航空影像,结合具有三维激光扫描和全景数据采集功能的移动测量车采集相关道路数据,提取了满足亚米级的导航与监控要求的道路路网数据,包括车道数、车道宽等属性数据等,按照导航电子地图的要求制作了高精度的道路电子地图。