车-车协同下无人驾驶车辆的换道汇入控制方法

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。     

混凝土公路斜桥的动反应研究

随着车辆质量、速度的逐渐增大和桥梁结构的逐渐轻柔化，车桥相互作用问题越来越受到关注。分别应用拉格朗日方程和模态叠加法建立三维非线性车辆模型和桥梁的振动方程，车轮与桥梁在接触点满足接触力和位移协调条件，利用迭代技术求解二者的相互作用问题。并以公路斜桥为分析对象，研究了不同斜交角、不同车辆行驶状态下以及不同行车速度情况下，横向不同梁的动挠度和动态增量。结果显示，斜交角、车辆行驶状态以及车速均是影响桥梁动反应的重要因素；当车辆行驶速度在30、40km／h左右时，梁的动态增量达到最大；而且随着斜交角的增大，离车辆行驶位置越远的梁的动态增量也越大。     

Two-Dimensional Motion of Four-Wheel Vehicles

This paper deals with two-dimensional motion of vehicles. Since the general four-wheel vehicle model is statically indeterminate, the motion of vehicles has been analyzed by replacing the vehicle with the equivalent two-wheel one proposed by E. Marquard. Because this approximation is based on the axisymmetry of vehicles, it causes significant errors in the general case. To improve the accuracy of the analysis of vehicle motion, a four-wheel model is suggested. In this model, it is assumed that the chassis remains in a flat plane during motion. By introducing this condition, the motion of the vehicle can be analyzed. Several results from the four-wheel model and the equivalent two-wheel model are shown for comparison, and the vehicle trajectories with time are discussed.     

Two-Dimensional Motion of Four-Wheel Vehicles

This paper deals with two-dimensional motion of vehicles. Since the general four-wheel vehicle model is statically indeterminate, the motion of vehicles has been analyzed by replacing the vehicle with the equivalent two-wheel one proposed by E. Marquard. Because this approximation is based on the axisymmetry of vehicles, it causes significant errors in the general case. To improve the accuracy of the analysis of vehicle motion, a four-wheel model is suggested. In this model, it is assumed that the chassis remains in a flat plane during motion. By introducing this condition, the motion of the vehicle can be analyzed. Several results from the four-wheel model and the equivalent two-wheel model are shown for comparison, and the vehicle trajectories with time are discussed.     

基于注意力Seq2Seq网络的高速公路交织区车辆变道轨迹预测

针对交通状态复杂的高速公路交织区域,经验丰富的驾驶人能够通过正确地推断周围车辆的未来运动进行及时的车道变换,这对于实现安全高效的自动驾驶至关重要,然而目前的自动驾驶车辆往往缺乏这种预测能力。为此,基于深度学习理论,提出了一种结合注意力机制和编-解码器结构的交织区车辆强制性变道轨迹预测方法,利用Next Generation Simulation（NGSIM）数据集提取车辆变道过程中的关键特征,并引入碰撞时间（Time to Collision,TTC）和避免碰撞减速度（Deceleration Rate to Avoid a Crash,DRAC）2种风险指标,将变道车辆及其周围车辆视为一个整体状态单元,同时补全状态单元内部不同车辆在横向和纵向上的时空状态特征,从而更有效地刻画车辆间的动态交互行为;然后将不同观测车辆的连续窗口序列输入基于长短期记忆网络（Long Short-term Memory,LSTM）的编-解码器,预测交织区车辆变道的未来运动轨迹,通过添加软注意力模块,使模型能够集中聚焦于影响车辆在不同时刻下位置变化的关键信息,再现了真实交通场景下车辆的变道行为。试验验证表明：基于注意力机制的编-解码器模型与当前流行的卷积长短期记忆网络、极限梯度提升树等模型相比具有更高的轨迹预测精度,在长时域的变道轨迹拟合上有显著的优越性,为辅助和自动驾驶领域的发展提供了新思路。     

城市平面交叉口左转车辆规避效应特性

城市道路交叉口交通隔离栏侵入内侧车道建筑限界,导致车辆横向偏移,增加行车风险。为了解城市平面交叉口交通隔离栏对左转车辆规避行为的影响,通过无人机采集3个设有交通隔离栏的平面交叉口车辆视频,提取车辆轨迹、速度、加速度等参数。分析交叉口出口不同车道车辆偏移和速度的分布特性,研究左转车辆规避特性。结果表明：①两侧车道上行驶的车辆更倾向于向中间车道偏移,中间车道行驶轨迹则较为稳定;②20 m的行程可供驾驶人稳定行驶方向,保持与交通隔离栏的安全横向距离;③左侧车道上85%以上车辆远离交通隔离栏行驶,平均偏移距离为0.278 m;右侧车道上60%左右车辆远离右侧行驶,平均偏移距离为0.116 m。④左转车辆在出口不同车道的速度分布存在显著差异,其中左侧车道和右侧车道上左转车辆速度分布峰值、横向加速度均值、纵向加速度均值均小于中间车道。以此提出城市道路交叉口的改善方法：①增加中分带宽度,提升路侧净距,实现左侧车道名义路权宽度与实际路权宽度一致;②增大硬质设施与驾驶人的横向距离;③开口段硬质设施优化为柔性,减弱设施心理冲击,降低驾驶负荷;④增设路面导流线和反光设施,保证诱导设施的连续性和一致性,提升方向感和速度感,从而减少规避效应过度或不足所带来的安全隐患。     

Intelligent Electronic Systems in Commercial Vehicles for Enhanced Traffic Safety

Looking at the future trends of the road traffic, one will recognize that the commercial vehicle participation will not decrease, although it is required from the environmental and social viewpoints. The reason is that the other means of freight transport (water, railway, air) do not provide the same flexibility as the road transport, and direct business interest of those companies, who are using this transport form is larger than the eventual loss caused by the penalties to be paid (taxes, compensation of higher axle load). This conflict is hard to solve, but the effect can be minimized. The commercial vehicle industry attempts to introduce systems to the vehicles, which are targeting on reduction of the environmental impacts caused by heavy vehicles. These systems, which are named generally as “intelligent chassis systems”, electronically control the operation of the chassis subsystems (engine, transmission, brake, suspension) and co-ordinate their operation on a higher level (vehicle controller, intelligent control systems, such as adaptive cruise control, video camera based lane change recognition system, etc.). This paper reviews the state-of-the-art of the commercial vehicle chassis systems, and tries to project their future development.     

Intelligent Electronic Systems in Commercial Vehicles for Enhanced Traffic Safety

Looking at the future trends of the road traffic, one will recognize that the commercial vehicle participation will not decrease, although it is required from the environmental and social viewpoints. The reason is that the other means of freight transport (water, railway, air) do not provide the same flexibility as the road transport, and direct business interest of those companies, who are using this transport form is larger than the eventual loss caused by the penalties to be paid (taxes, compensation of higher axle load). This conflict is hard to solve, but the effect can be minimized. The commercial vehicle industry attempts to introduce systems to the vehicles, which are targeting on reduction of the environmental impacts caused by heavy vehicles. These systems, which are named generally as “intelligent chassis systems”, electronically control the operation of the chassis subsystems (engine, transmission, brake, suspension) and co-ordinate their operation on a higher level (vehicle controller, intelligent control systems, such as adaptive cruise control, video camera based lane change recognition system, etc.). This paper reviews the state-of-the-art of the commercial vehicle chassis systems, and tries to project their future development.     

无人驾驶车辆解耦混合运动规划方法研究

高速公路无人驾驶车辆运动规划要充分考虑车辆的动力学特性和道路环境构成的复杂约束,优先确保车辆的无碰撞行驶轨迹,同时算法实时性比常速情况下要求更高,要充分考虑计算的复杂性。提出一种可生成横纵向最优解逼近群的解耦增强混合运动规划方法,引入Frent坐标系将运动规划问题进行横纵向解耦,在横向偏移规划中融合数值优化和多项式规划算法,在纵向速度规划中融合围绕速度和围绕避障规划算法,解耦规划完成后使用代价函数和碰撞检测方法对生成的轨迹群进行评估和选择。搭建Apollo-LGsvl无人驾驶联合仿真测试平台,对所提出的运动规划方法进行仿真验证。结果表明,提出的横纵向解耦增强混合运动规划算法在高速公路各工况中所生成的运动轨迹能够有效避免车辆发生碰撞,其横向偏移和纵向速度均能满足二阶平滑,最大横向加速度、最大纵向加速度、最大纵向jerk等满足动力学约束。该方法有效减少了最优解逼近群内的轨迹数量,使轨迹评估阶段计算复杂度降低了46%,证明提出的方法具备一定的应用价值。     

An Emergency Obstacle Avoidance Control Strategy for Automated Highway Vehicles

Summary This paper presents an emergency obstacle avoidance control strategy that may be used in automated highway vehicles. In the proposed control strategy, an inverse vehicle dynamics problem is solved on the selected emergency lane-change path to find out the nominal feedforward control inputs such as the steering wheel angle and the braking force. Then the overall vehicle lateral and yaw motion is controlled additionally in the feedback path by an active yaw moment for stability augmentation as well as a corrective steering angle that is added to the nominal steering angle in order to compensate for uncertainties involved in the nominal control input computation. The proposed control strategy has been tested by an ABS Hardware-In-the-Loop Simulation (HILS) system for rapid and safe control prototyping in a lab. Simulation results with a sample emergency avoidance distance (45 m) show that the proposed control strategy may be used as a feasible obstacle avoidance strategy for automated highway vehicles.     

An Emergency Obstacle Avoidance Control Strategy for Automated Highway Vehicles

Summary This paper presents an emergency obstacle avoidance control strategy that may be used in automated highway vehicles. In the proposed control strategy, an inverse vehicle dynamics problem is solved on the selected emergency lane-change path to find out the nominal feedforward control inputs such as the steering wheel angle and the braking force. Then the overall vehicle lateral and yaw motion is controlled additionally in the feedback path by an active yaw moment for stability augmentation as well as a corrective steering angle that is added to the nominal steering angle in order to compensate for uncertainties involved in the nominal control input computation. The proposed control strategy has been tested by an ABS Hardware-In-the-Loop Simulation (HILS) system for rapid and safe control prototyping in a lab. Simulation results with a sample emergency avoidance distance (45 m) show that the proposed control strategy may be used as a feasible obstacle avoidance strategy for automated highway vehicles.     

Effects of Model Complexity on the Performance of Automated Vehicle Steering Controllers: Model Development,Validation and Comparison

SUMMARY

Recent research on autonomous highway vehicles has begun to focus on lateral control strategies. The initial work has focused on vehicle control during low-g maneuvers at constant vehicle speed, typical of lane merging and normal highway driving. In this paper, and its companion paper, to follow, the lateral control of vehicles during high-g emergency maneuvers is addressed. Models of the vehicle dynamics are developed, showing the accuracy of the different models under low and high-g conditions. Specifically, body roll, tire and drive-train dynamics, tire force saturation, and tire side force lag are shown to be important effects to include in models for emergency maneuvers. Current controllers, designed for low-g maneuvers only, neglect these effects. The follow on paper demonstrates the performance of lateral controllers during high-g lateral emergency maneuvers using these vehicle models.     

Effects of Model Complexity on the Performance of Automated Vehicle Steering Controllers: Model Development, Validation and Comparison

Recent research on autonomous highway vehicles has begun to focus on lateral control strategies. The initial work has focused on vehicle control during low-g maneuvers at constant vehicle speed, typical of lane merging and normal highway driving. In this paper, and its companion paper, to follow, the lateral control of vehicles during high-g emergency maneuvers is addressed. Models of the vehicle dynamics are developed, showing the accuracy of the different models under low and high-g conditions. Specifically, body roll, tire and drive-train dynamics, tire force saturation, and tire side force lag are shown to be important effects to include in models for emergency maneuvers. Current controllers, designed for low-g maneuvers only, neglect these effects. The follow on paper demonstrates the performance of lateral controllers during high-g lateral emergency maneuvers using these vehicle models.     

智能汽车横纵向运动控制方法综述

在我国随着人民生活水平的提高,车辆保有量也在呈倍速增长,进而引起了大量的交通安全问题,其中由驾驶员操作不当引起的交通事故约占所有交通事故的75%。而汽车的智能化发展可以很好地解决此类交通安全问题。智能汽车的核心技术主要包括环境感知、行为决策及运动控制三方面。其中运动控制作为智能汽车核心技术之一,有着重要的研究意义。智能汽车的运动控制包括横向控制和纵向控制两部分,对汽车横、纵向运动控制中的多种方法进行了分析介绍,包括模型预测控制、模糊逻辑控制、神经网络的自适应滑膜控制、直接式控制和分层式控制;同时介绍了横纵向耦合实现运动控制的重要性,并分析了其研究现状;最后,对智能汽车运动控制的后续发展方向进行了展望,有助于智能汽车运动控制的进一步优化发展。     

考虑道路因素的智能车辆纵向运动决策与控制研究

针对智能车辆纵向运动时的交通道路适应性问题,考虑路面附着系数和前车运动速度等因素,研究了智能车辆纵向运动决策与控制方法。论文研究了基于车头时距的纵向运动决策方法并建立不同驾驶行为的目标车速模型,运用变论域模糊推理算法设计了目标加速度模型。基于纵向动力学模型,运用自适应反演滑模控制算法建立了驱动控制器和制动控制器。对高附着系数路面和低附着系数路面的行驶工况进行仿真试验验证,结果表明,在不同的附着系数路面和前车变速行驶条件下,智能车辆能实时、合理地决策目标车速、目标加速度,实现安全、高效、稳定的跟驰。     

Connected variable speed limits control and car-following control with vehicle-infrastructure communication to resolve stop-and-go waves

The vision of intelligent vehicles traveling in road networks has prompted numerous concepts to control future traffic flow, one of which is the in-vehicle actuation of traffic control commands. The key of this concept is using intelligent vehicles as actuators for traffic control systems. Under this concept, we design and test a control system that connects a traffic controller with in-vehicle controllers via vehicle-to-infrastructure communication. The link-level traffic controller regulates traffic speeds through variable speed limits (VSL) gantries to resolve stop-and-go waves, while intelligent vehicles control accelerations through vehicle propulsion and brake systems to optimize their local situations. It is assumed that each intelligent vehicle receives VSL commands from the traffic controller and uses them as variable parameters for the local vehicle controller. Feasibility and effectiveness of the connected control paradigm are tested with simulation on a two-lane freeway stretch with intelligent vehicles randomly distributed among human-driven vehicles. Simulation shows that the connected VSL and vehicle control system improves traffic efficiency and sustainability; that is, total time spent in the network and average fuel consumption rate are reduced compared to (uncontrolled and controlled) scenarios with 100% human drivers and to uncontrolled scenarios with the same intelligent vehicle penetration rates.     

换道操作对智能车辆乘客舒适性的影响研究

乘坐舒适性是决定乘客对智能车辆接受度的重要因素之一。为了提升智能车辆的舒适性,服务智能驾驶控制算法的设计和优化,开展了基于乘客主观感知的实车乘坐舒适性试验,试验中驾驶人驾驶传统车辆执行多次换道操作,获取了60名被试乘客对换道操作的舒适性评价数据,并采集了车辆的运动数据。选取换道时横向最大加速度、回正时横向最大加速度、横向最大加加速度、横向加速度转换幅值以及横向加速度转换频率这5个车辆运动参数作为研究对象。采用二元Logistic回归单因素分析法分析了这5个车辆运动参数对乘坐舒适性的影响,采用接收者操作特征(ROC)曲线分析法为不同晕车易感性的乘客分别确立了这5个车辆运动参数的舒适性阈值,并根据岭回归分析法确定了不同参数对乘坐舒适性的影响权重。结果表明：所选取的5个车辆运动参数对乘坐舒适性具有显著影响,易晕乘客的舒适性阈值小于不易晕乘客的舒适性阈值,在换道过程中,换道时横向最大加速度、回正时横向最大加速度和横向加速度转换幅值是影响乘坐舒适性的主要因素。最后根据车辆运动参数和乘客生理特征参数建立了基于动态时间归整(DTW)和K最近邻(KNN)算法的乘坐舒适性预测模型,该模型对乘坐舒适性的预测准确率为84%,可用于智能车辆控制算法的舒适性判断。     

基于动态风险饱和度的高速公路交通安全分析

为了反映高速公路运营安全状况,提出了动态风险饱和度理论,构建了动态风险饱和度模型和计算方法。依据路段不同交通饱和度下车辆的驾驶行为,以路段交通安全为约束,研究了跟车行驶和换道行驶2种驾驶状态下,考虑车速变化及雾天等特殊天气条件影响的路段平均最小安全车头时距计算方法,利用建立的安全车头时距与安全流量之间的转换关系,得到不同驾驶状态下的路段安全流量。在不同车辆驾驶状态切换阈值下,计算路段实际交通流量与路段安全流量的比值得到高速公路路段动态风险饱和度值。以G3高速公路某改扩建路段所在路网为例进行验证,计算得到了路网中各路段不同切换阈值下的动态风险饱和度值。动态风险饱和度随着交通饱和度的增大,呈现稳定的先增大后减小的规律,且在换道行驶状态时达到最大,在跟车行驶状态时开始下降,与现有交通安全状态分析相吻合。相较于交通饱和度,动态风险饱和度更能够反应出高速公路路段交通安全动态变化的规律。      

基于交通流元胞自动机模型的车辆当量换算

将一维元胞自动机模型用于模拟周期性边界条件下高速公路的车流运动,用随机慢化FI模型对一定交通环境下车流的车速与密度之间的关系进行仿真分析。探讨了不同车型和车速对道路最大流量(最大通行能力)的影响。依据不同车型在同一道路上的不同通行能力,提出了一种不同车型车辆之间当量换算系数的确定方法。在模拟仿真过程中,考虑不同类型车辆的最大行驶速度及所占空间不同,仿真模型具有不同的参数。通过计算机模拟,得到不同车型的交通流基本图,根据相同道路条件下的最大流量值,给出了以通行能力作为基准时当量换算系数的计算公式。     

Implementation of active steering on longer combination vehicles for enhanced lateral performance

A steering-based controller for improving lateral performance of longer combination vehicles (LCVs) is proposed. The controller steers the axles of the towed units to regulate the time span between the driver steering and generation of tyre lateral forces at the towed units and consequently reduces the yaw rate rearward amplification (RWA) and offtracking. The open-loop effectiveness of the controller is evaluated with simulations and its closed loop or driver in the loop effectiveness is verified on a test track with a truck–dolly–semitrailer test vehicle in a series of single- and double-lane change manoeuvres. The developed controller reduces the yaw rate RWA and offtracking considerably without diminishing the manoeuvrability. Furthermore, as a byproduct, it decreases the lateral acceleration RWA moderately. The obtained safety improvements by the proposed controller can promote the use of LCVs in traffic which will result in the reduction of congestion problem as well as environmental and economic benefits.