Autonomous Lateral Control of Vehicles in an Automated Highway System

SUMMARY

Lateral control of vehicles in IVHS requires the installation of on-board sensors as well as the installation of roadway hardware such as cables, magnets, etc. Existing control approaches in PATH require road curvature and vehicle lateral position (with respect to the center of the lane) information. Hence these approaches rely on roadway sensors to obtain relative lateral position. These methods will necessitate infrastructural changes to the highway.

This paper introduces the concept of autonomous lateral control or auto-tracking. The method allows us to use only line-of-sight sensor information to effect vehicle control. We present a detailed vehicle model. Controllers have been proposed to demonstrate the effectiveness of the proposed auto-tracking scheme. We also examine the possibilities of using this method for lane change purposes in an automated highway system.     

eTS fuzzy driver model for simultaneous longitudinal and lateral vehicle control

In this paper, evolving Takagi-Sugeno (eTS) fuzzy driver model is proposed for simultaneous lateral and longitudinal control of a vehicle in a test track closed to traffic. The developed eTS fuzzy driver model can capture human operator’s driving expertise for generating desired steering angle, throttle angle and brake pedal command values by processing only information which can be supplied by the vehicle’s on-board control systems in real time. Apart from other fuzzy rule based (FRB) models requiring human expert knowledge or off-line clustering, the developed eTS driver model can adapt itself automatically, even ‘from scratch’, by an on-line learning process using eTS algorithm while human driver is supervising the vehicle. Proposed eTS fuzzy driver model’s on-line human driver identification capability and autonomous vehicle driving performance were evaluated on real road profiles created by digitizing two different intercity express ways of Turkey in IPG© CarMaker® software. The training and validation simulation results demonstrated that eTS fuzzy driver model can be used in product development phase to speed up different tests via realistic simulations. Furthermore eTS fuzzy driver model has an application potential in the field of autonomous driving.     

基于LGSVL/Apollo的网络延迟攻击下自动驾驶车辆定位估算

为提高网络延迟攻击下自动驾驶车辆定位估计算法的精确度,研究了延迟模型下自动驾驶车辆定位的无偏差有限脉冲响应(UFIR)估计器设计方法,并仿真实验.搭建延迟攻击下的车辆运动学模型,拓展模型至有限长度的时间窗口,推导UFIR算法按批处理式与迭代式表达形式,分析Apollo系统各功能模块的数据流动,基于LG开源自动驾驶仿真器...     

基于扩展卡尔曼滤波算法的智能泊车航位推算研究

针对智能泊车系统对高精度车辆航位估计的要求,设计了基于轮速及方向盘转角信号的扩展卡尔曼滤波航位推算算法.离线仿真实验将本算法与传统航位推算算法进行了对比,结果显示本算法具有更高的精度;实车试验进一步验证了本算法的实际应用价值.     

北斗卫星与车载传感器融合的车辆定位

为了改善北斗卫星定位性能,基于卡尔曼滤波设计了北斗卫星与车载传感器的数据融合算法。算法包括车辆方向融合和车辆位置融合两部分,前者融合电子罗盘和陀螺测量得到的北向角及其变化率,估算北向角的真实值;后者首先同步车速矢量与北斗卫星测量得到的车辆位置矢量,再根据融合结果估算车辆定位信息。为了验证数据融合算法,设计了北斗卫星与车辆状态信息采集系统,利用本系统采集的实车数据进行的仿真计算表明,算法能够提高定位频率、减小定位误差,提高北斗卫星定位的性能。     

Autonomous Lateral Control of Vehicles in an Automated Highway System

Lateral control of vehicles in IVHS requires the installation of on-board sensors as well as the installation of roadway hardware such as cables, magnets, etc. Existing control approaches in PATH require road curvature and vehicle lateral position (with respect to the center of the lane) information. Hence these approaches rely on roadway sensors to obtain relative lateral position. These methods will necessitate infrastructural changes to the highway.

This paper introduces the concept of autonomous lateral control or auto-tracking. The method allows us to use only line-of-sight sensor information to effect vehicle control. We present a detailed vehicle model. Controllers have been proposed to demonstrate the effectiveness of the proposed auto-tracking scheme. We also examine the possibilities of using this method for lane change purposes in an automated highway system.     

车路协同信息融合的智能汽车行驶状态模糊评判

为了监测与评判道路上行驶的智能汽车的实时状态,基于研发的智能汽车的车载感知系统,包括通过视觉传感器、激光雷达、GPS定位、车载传感器系统及车载总线获取车内及周围环境信息。采用V2X通讯设备等获取路侧端雷视一体机、路侧传感器、气象传感器传输的交通信息,通过V2X通讯设备、4G通讯模块传送到云服务器并建立模糊评判模型。基于可信度的模糊推理算法对环境信息和交通信息进行融合,并以此为依据对行驶车辆的状态进行评判。首先,建立针对车辆行驶状态的模糊评判集合和各参数隶属度函数,计算出各参数的隶属度,并对行驶车辆的各个参数建立典型的行驶状态评判参数数据集合。其次,采用模糊假言推理方法,以典型的数据集合为基础建立带可信度和阈值的模糊规则库。应用麦姆德尼方法,建立与规则库的每个规则所对应的模糊关系矩阵库。以车辆行驶时接收到的车载端和路侧端信息作为输入,应用规则库规则进行带有可信度的模糊推理。然后,以相似度作为匹配度,对推理规则设定阈限,按照证据与规则的前件不相等的情况,计算结论的可信度得出结论。对结论进行冲突消解时,冲突消解的策略为取可信度高的结论。最后,应用匹配度对结论的可靠性进行验证,并在多个道路场景实时行驶的车辆上对算法进行试验验证。研究结果表明:算法对行驶车辆状态的评判与实车的状态相一致,可实现对车辆不安全状态的报警与行驶状态的干预,对保障行车安全有显著积极的实际应用意义。     

Vehicle sideslip estimation and compensation for banked road

The sideslip driving status is of fundamental importance to the stability of a vehicle. This paper presents a practical vehicle sideslip driving status estimation method that uses ESP (electronic stability program) sensors. ESP sensors such as wheel speed, lateral acceleration, yaw rate and steering wheel angle sensors are used to determine the sideslip driving status and distinguish a banked road. This estimation algorithm contains front-rear sideslip and banked road detection methods. The proposed sideslip estimation algorithm was designed to use the analytical redundancy of these sensors and Lagrange interpolation methods. The performance and effectiveness of the proposed estimation and compensation algorithm were investigated using vehicle tests. This paper presents the results of two cases that were used for the experimental verification: a curved flat road and banked road.     

Evaluation of odometry algorithm performances using a railway vehicle dynamic model

In modern railway Automatic Train Protection and Automatic Train Control systems, odometry is a safety relevant on-board subsystem which estimates the instantaneous speed and the travelled distance of the train; a high reliability of the odometry estimate is fundamental, since an error on the train position may lead to a potentially dangerous overestimation of the distance available for braking. To improve the odometry estimate accuracy, data fusion of different inputs coming from a redundant sensor layout may be used. Simplified two-dimensional models of railway vehicles have been usually used for Hardware in the Loop test rig testing of conventional odometry algorithms and of on-board safety relevant subsystems (like the Wheel Slide Protection braking system) in which the train speed is estimated from the measures of the wheel angular speed. Two-dimensional models are not suitable to develop solutions like the inertial type localisation algorithms (using 3D accelerometers and 3D gyroscopes) and the introduction of Global Positioning System (or similar) or the magnetometer. In order to test these algorithms correctly and increase odometry performances, a three-dimensional multibody model of a railway vehicle has been developed, using Matlab-Simulink?, including an efficient contact model which can simulate degraded adhesion conditions (the development and prototyping of odometry algorithms involve the simulation of realistic environmental conditions). In this paper, the authors show how a 3D railway vehicle model, able to simulate the complex interactions arising between different on-board subsystems, can be useful to evaluate the odometry algorithm and safety relevant to on-board subsystem performances.     

基于多信息融合的全轮独立电驱动车辆车速估计

鉴于用非驱动轮轮速信号来估计车速的方法已不适用于没有非驱动轮的全轮独立电驱动车辆,提出了借融合车载普通传感器信号和驱动电机反馈信号等多信息源,并基于稳态工况下的轮速信号卡尔曼滤波和瞬态工况下的加速度积分的全轮驱动车辆车速估计方法.通过实车试验对该方法的有效性、适用性和精度进行了验证.     

Lateral controller design for an unmanned vehicle via Kalman filtering

This paper proposes a lateral control system for an unmanned vehicle that is designed to improve the responsiveness of the system with the use of a PD control. The vehicle heading error can be stabilized, and the transient response characteristics can be improved using the proposed controller. A mathematical model of the vehicle dynamics using two degrees of freedom was developed for the controller design. The waypoint tracking method for autonomous navigation was tested with incorporation of the Point-to-Point algorithm with position and heading measurements received from GPS receivers via Kalman filtering. The performance of the designed controller was verified through experiments with a real vehicle.     

汽车电子控制系统快速开发

车辆动力学仿真软件提供控制算法离线仿真平台,车辆模型、传感器、快速开发系统、零部件和控制系统硬件构成硬件和环试验平行,动力传动系和制动系、测功机及其控制器和控制系统硬件组成测功机硬件在环试验台,而车载开发平台包括样车、数据采集系统、传感器和控制系统硬件。在完成控制原型快速开发的基础上,完成基于目标控制器的控制系统快速开发。实例表明：上述开发流程大大缩短了开发周期。     

An overview: modern techniques for railway vehicle on-board health monitoring systems

Health monitoring systems with low-cost sensor networks and smart algorithms are always needed in both passenger trains and heavy haul trains due to the increasing need for reliability and safety in the railway industry. This paper focuses on an overview of existing approaches applied for railway vehicle on-board health monitoring systems. The approaches applied in the data measurement systems and the data analysis systems in railway on-board health monitoring systems are presented in this paper, including methodologies, theories and applications. The pros and cons of the various approaches are analysed to determine appropriate benchmarks for an effective and efficient railway vehicle on-board health monitoring system. According to this review, inertial sensors are the most popular due to their advantages of low cost, robustness and low power consumption. Linearisation methods are required for the model-based methods which would inevitably introduce error to the estimation results, and it is time-consuming to include all possible conditions in the pre-built database required for signal-based methods. Based on this review, future development trends in the design of new low-cost health monitoring systems for railway vehicles are discussed.     

基于分段学习模型的自动驾驶行为决策算法研究

在具有车道线的特定自动驾驶场景中,针对目前端到端的行为决策算法直接输入原始图像进行决策导致的网络模型迁移性差、预测精度欠佳、泛化能力不足等问题,提出一种基于分段学习模型的车辆自动驾驶行为决策算法。首先,基于GoogLeNet建立一种端到端的车道线检测网络模型,并引入车道中心线作为决策的重要线索提高算法的迁移能力,同时利用YOLOv3目标检测模型对本车道内前方最近障碍物进行位置检测;而后,经几何测量模型将两者检测结果转换成环境状态信息向量为决策做支撑;最后,构建基于长短期记忆(LSTM)网络的驾驶行为决策模型,根据编码的历史状态信息刻画出动态环境中车辆的运动模式,并结合当前时刻的状态推理得到驾驶行为参量。使用建立的真实驾驶场景数据集对模型分别进行训练、验证与测试,离线测试结果显示车道线检测模型的检测位置误差小于1.3%,车道内前方障碍物检测模型的检测精度达98%以上,驾驶行为决策网络模型表征预测优度的决定系数 大于0.7。为进一步验证算法的有效性,搭建了Simulink/PreScan联合仿真平台,多种工况下的仿真验证试验中多个评价指标均达到工程精度要求,实车测试的试验结果也表明该算法可实现复杂驾驶场景下平稳、准确无偏航的预测效果并满足实时性要求,且与传统端到端模式的算法相比,具有更好的迁移性和泛化能力。     

基于光电导航无人驾驶电动汽车自动寻迹控制系统研究

在轮毂电机驱动电动汽车技术的基础上,采用光电传感器自动辨识行驶路径,利用车辆行驶预瞄理论,开发了无人驾驶汽车自动寻迹行驶控制系统.试验表明,该系统稳定性好、控制精度高和响应速度快.     

智能车辆安全辅助驾驶技术研究近况

论述了安全辅助驾驶技术的研究现状、研究的必要性以及研究进展。安全辅助驾驶技术包括车道偏离预警与保持、前方车辆探测及安全车距保持、行人检测、驾驶员行为监测、车辆运动控制与通讯等。分析了各种传感器的优缺点及其在实际应用过程中存在的问题,基于单一传感器不能很好地解决安全辅助驾驶技术可靠性和环境适应能力的要求,应结合激光雷达技术解决图像模糊问题,利用红外传感器增强机器视觉识别的可靠性,未来的安全辅助驾驶技术应该采取多种传感器融合的技术,结合毫米波雷达和激光雷达系统具有深度测量精确的特点,将极大的推动汽车安全辅助驾驶系统的应用和推广。     

基于多属性决策的无人驾驶自主变道决策技术研究

在无人驾驶领域,随着车辆上布置的传感器不断丰富,无人驾驶系统可以从周围环境获得更多的信息,从而为车辆的自主判断行为决策带来可能。然而即使是有经验的驾驶员在进行变道动作的时候也需要格外的小心,因此无人驾驶系统的变道行为分析需要做到足够准确和谨慎,才能保证安全性,这也正是目前为止还没有非常完善的无人驾驶变道决策系统的原因。本文提出一种基于多属性决策的无人驾驶自主变道决策技术,帮助无人驾驶车辆在道路行驶中进行更有效、更安全的自主变道决策。     

Fault Diagnostics for GPS-based Lateral Vehicle Control

Summary This paper develops a fault diagnostic system to monitor the health of the lateral motion sensors on an instrumented highway vehicle. The fault diagnostic system utilizes observer design with the observer gains chosen so as to ensure that each sensor failure causes estimation errors to grow in an unique direction. The performance of the fault diagnostic system is verified through extensive experimental results obtained from an instrumented truck called the “Safetruck”. The fault diagnostic system is able to monitor the health of a GPS system, a gyroscope and an accelerometer on the Safetruck. It can correctly detect a failure in any one of the three sensors and accurately identify the source of the failure. A GPS-based geographic database containing information on road coordinates, curvature and bank angles plays a key role in ensuring accurate experimental performance of the observers.     

基于注意力机制的多模态自动驾驶行为决策模型

针对现有端到端自动驾驶模型未考虑驾驶场景中不同区域的重要性和不同语义类别之间的关系而导致预测准确率低的问题，受驾驶人注意力机制和现有端到端自动驾驶模型的启发，充分考虑驾驶场景的动态变化、驾驶场景的语义信息和深度信息对驾驶行为决策的影响，以连续多帧驾驶场景的RGB图像为输入，构建一种基于注意力机制的多模态自动驾驶行为预测模型，实现对方向盘转角和车速的准确预测。首先，通过语义分割模型和单目深度估计模型分别获取RGB图像的语义图像和深度图像；其次，为剔除与驾驶行为决策无关信息，以神经科学和空间抑制理论为基础，设计一种拟人化注意力机制作为能量函数来计算驾驶场景中不同区域的重要度；为学习语义图像中与驾驶行为决策最为相关类别之间的关系，采用图注意力网络(Graph Attention Network,GAT)对驾驶场景的语义图像进行特征提取；然后，以保留RGB特征为原则对提取的驾驶场景的图像特征、语义特征和深度特征进行融合，采用卷积长短期记忆网络(Convolutional Long Short Term Memory,ConvLSTM)实现融合特征在连续多帧之间的传递，进而实现下一帧驾驶场景对应驾驶行为的预测；最后，与其他模型的对比试验、消融试验、泛化试验和特征可视化试验来充分验证所提出自动驾驶行为预测模型的性能。试验结果表明：与其他驾驶行为预测模型相比，所提出模型的训练误差为0.021 2，预测准确率为86.97%，均方误差为0.031 5，其驾驶行为的预测性能优于其他模型；连续多帧的语义图像和深度图像、拟人化注意力机制和面向语义特征提取的GAT有助于提升驾驶行为预测的性能；该模型具有较好的泛化能力,其做出驾驶行为预测所依赖的特征与经验丰富的驾驶人所关注的特征基本一致。     

Application of Elementary Neural Networks and Preview Sensors for Representing Driver Steering Control Behaviour

This paper demonstrates the use of elementary neural networks for modelling and representing driver steering behaviour in path regulation control tasks. Areas of application include uses by vehicle simulation experts who need to model and represent specific instances of driver steering control behaviour, potential on-board vehicle technologies aimed at representing and tracking driver steering control behaviour over time, and use by human factors specialists interested in representing or classifying specific families of driver steering behaviour. Example applications are shown for data obtained from a driver/vehicle numerical simulation, a basic driving simulator, and an experimental on-road test vehicle equipped with a camera and sensor processing system.