基于ITS技术的汽车驾驶安全辅助系统

基于ITS技术的汽车驾驶安全辅助系统是提高道路交通安全的有效手段,本文介绍了清华大学汽车安全与节能国家重点实验室在此领域的研究与开发工作。在研究行驶环境感知和信息融合、驾驶员特性和安全距离模型、车辆运动控制及系统集成等关键技术的基础上,研制了汽车驾驶安全辅助系统试验平台和试验样车,实现了行车前撞预警、安全车距保持、智能车道保持等功能,并完成了相关试验分析与评价,为进一步开展基于ITS的汽车主动安全辅助技术的研究以及汽车驾驶辅助系统的产业化奠定了基础。     

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Kmeans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A...     

The characteristic velocity stability indicator for passenger cars

Driver assistance systems have received increased attention as market demands have pushed for improved automotive safety. These systems are designed to aid the driver by preventing any unstable or unpredictable vehicle behaviour. One global indicator for stability and driving conditions could help to manage the control algorithms and driver warning subroutines. Another problem which could be solved by a precise driving situation indicator is evaluating new vehicles during test drives. After a short introduction to a linear lateral vehicle model, an analytical approach for an online calculation of different driving conditions (i.e., stability, understeering, oversteering, and neutralsteering) is given. A characteristic velocity stability indicator is defined, which allows online computation of the present driving condition. Results are then checked against real measurements of a test vehicle.     

The characteristic velocity stability indicator for passenger cars

Driver assistance systems have received increased attention as market demands have pushed for improved automotive safety. These systems are designed to aid the driver by preventing any unstable or unpredictable vehicle behaviour. One global indicator for stability and driving conditions could help to manage the control algorithms and driver warning subroutines. Another problem which could be solved by a precise driving situation indicator is evaluating new vehicles during test drives. After a short introduction to a linear lateral vehicle model, an analytical approach for an online calculation of different driving conditions (i.e., stability, understeering, oversteering, and neutralsteering) is given. A characteristic velocity stability indicator is defined, which allows online computation of the present driving condition. Results are then checked against real measurements of a test vehicle.     

可变转向比技术在汽车转向系统的应用

现在人们对汽车驾驶的舒适陛和安全性要求越来越高,汽车传统的转向系统无法满足低速时的灵活性与高速时的稳定性要求,可变转向比技术的应用,有效地解决了这一矛盾。文章介绍了当前应用和开发的可变转向比转向系统,指出该系统使汽车具有一定的智能化,提高了驾驶的安全性和舒适性,可变转向比技术是未来转向系统的主要发展方向之一。     

基于Prescan的自然驾驶场景构建与研究

文章主要描述基于Prescan软件对实车的自然驾驶场景片段转换成虚拟场景,用于ADAS或自动驾驶模拟测试。通过配备毫米波雷达、相机、Mobileye摄像头等传感器采集道路驾驶数据,提取场景片段,转化成虚拟软件中相应的实车场景,用于HIL或MIL测试,可实现重复性测试,降低测试成本,模拟恶劣天气等状况,复现实车测试状态等测试优点。     

汽车智能雨刮系统雨滴检测方法研究进展

在雨雪天气，为了保证驾驶员前方视野清晰，各类车辆均需配备雨刮装置。汽车智能雨刮系统作为汽车高级驾驶辅助系统的重要组成部分，是智能驾驶领域研究重点之一。详细介绍了汽车智能雨刮系统中常用的两种雨滴检测方法，分别基于雨量传感器和视觉传感器来实现。详细阐述了传统的基于雨量传感器的雨滴检测方法的工作原理及其研究现状，分析了各种类型雨量传感器存在的主要问题。针对新兴的基于视觉传感器的智能雨刮系统，分析了雨滴特征及其目标检测方法的发展历程。基于视觉传感器的汽车智能雨刮系统可以和高级驾驶辅助系统的其他组件共用视觉传感器和硬件设备，极大地降低了智能雨刮系统的应用成本，但是在准确性、实时性和适应性等方面仍存在较多问题亟待解决。     

Slope Shift Strategy for Automatic Transmission Vehicles Based on the Road Gradient

Motivated by the development of high-precision digital maps for advanced driver assistance system (ADAS) in recent years, this study provides a new approach to solve the problems of the conventional automatic transmission vehicle travelling on sloping roads. Based on vehicle dynamics, shift problems on hilly roads are analyzed. A novel intelligent shift strategy is proposed, which consists of a dynamic shift schedule for the uphill, a safety shift schedule for the downhill, and a comprehensive economical shift schedule for the gentle slopes. A set of driver-in-loop co-simulation tests was conducted in a driving simulator that is equipped with a MATLAB/Simulink dynamics simulation platform. The test results verified the effectiveness of the new intelligent shift strategy. With the road information provided by a high-precision digital map, busy shifting can be eliminated, and improved dynamic performance can be achieved for a vehicle travelling on the uphill roads; undesired upshift can be prevented, and engine traction resistance can be used to relieve the load of braking system when a vehicle travelling on the downhill roads; also, fuel consumption can be reduced for a vehicle travelling on a gently sloped road. Consequently, this novel intelligent shift strategy offers a reliable and effective solution for improving a vehicle’s driving performance on a hilly road.     

Comparison of driving characteristics between drivers in Korea and in the united states of America based on driver-vehicle interaction field database

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.     

Driving environment assessment using fusion of in- and out-of-vehicle vision systems

Because the overall driving environment consists of a complex combination of the traffic Environment, Vehicle, and Driver (EVD), Advanced Driver Assistance Systems (ADAS) must consider not only events from each component of the EVD but also the interactions between them. Although previous researchers focused on the fusion of the states from the EVD (EVD states), they estimated and fused the simple EVD states for a single function system such as the lane change intent analysis. To overcome the current limitations, first, this paper defines the EVD states as driver’s gazing region, time to lane crossing, and time to collision. These states are estimated by enhanced detection and tracking methods from in- and out-of-vehicle vision systems. Second, it proposes a long-term prediction method of the EVD states using a time delayed neural network to fuse these states and a fuzzy inference system to assess the driving situation. When tested with real driving data, our system reduced false environment assessments and provided accurate lane departure, vehicle collision, and visual inattention warning signals.     

Development of advanced driver assistance systems with vehicle hardware-in-the-loop simulations

This paper presents a new method for the design and validation of advanced driver assistance systems (ADASs). With vehicle hardware-in-the-loop (VEHIL) simulations, the development process, and more specifically the validation phase, of intelligent vehicles is carried out safer, cheaper, and is more manageable. In the VEHIL laboratory, a full-scale ADAS-equipped vehicle is set up in a hardware-in-the-loop simulation environment, where a chassis dynamometer is used to emulate the road interaction and robot vehicles to represent other traffic. In this controlled environment, the performance and dependability of an ADAS is tested to great accuracy and reliability. The working principle and the added value of VEHIL are demonstrated with test results of an adaptive cruise control and a forward collision warning system. On the basis of the ‘V’ diagram, the position of VEHIL in the development process of ADASs is illustrated.     

Development of advanced driver assistance systems with vehicle hardware-in-the-loop simulations

This paper presents a new method for the design and validation of advanced driver assistance systems (ADASs). With vehicle hardware-in-the-loop (VEHIL) simulations, the development process, and more specifically the validation phase, of intelligent vehicles is carried out safer, cheaper, and is more manageable. In the VEHIL laboratory, a full-scale ADAS-equipped vehicle is set up in a hardware-in-the-loop simulation environment, where a chassis dynamometer is used to emulate the road interaction and robot vehicles to represent other traffic. In this controlled environment, the performance and dependability of an ADAS is tested to great accuracy and reliability. The working principle and the added value of VEHIL are demonstrated with test results of an adaptive cruise control and a forward collision warning system. On the basis of the 'V' diagram, the position of VEHIL in the development process of ADASs is illustrated.     

基于Prescan 的信号灯路口跟停场景虚拟重构

为满足我国智能驾驶汽车测试场景库的搭建和ADAS(高级驾驶辅助系统)功能研发和验证的需求,设计了一种基于Prescan的交通信号灯路口车辆跟停场景虚拟重构方法,该方法由道路环境建设模块、初始条件设定模块和车辆控制模块组成。道路环境建设模块通过输入道路参数信息构建虚拟道路,初始条件设定模块通过输入本车和目标车的初始位置、初始速度信息确定零时刻车辆和道路的空间位置及状态信息,车辆控制模块依据车辆速度位置等信息,利用训练的神经网络控制本车加速度,实现跟停场景的虚拟重构。仿真结果表明,该方法可以实现交通信号灯路口车辆跟停场景的虚拟重构。     

Test Scenario Design for Intelligent Driving System Ensuring Coverage and Effectiveness

Intelligent vehicle greatly benefits traffic safety, efficiency and driving comfortable. With the development of intelligent driving technology and its application, it is becoming increasingly important to do effective and comprehensive tests before putting on the market. Comprehensively considering the cost of test, an automatic generation method of test scenarios is proposed to ensure both coverage and effectiveness. Based on the analyzed key infuence factors of an intelligent driving system, the analytic hierarchy process (AHP) is used to determine their importance and accordingly an complex index is defined, based on which an improved test case generation algorithm based on the pairwise independent combinatorial testing tool (PICT) is proposed to ensuring both combinational coverage and complexity of test cases. Finally, the test scenario is generated by clustering these discrete test cases considering similarity and complexity. The high complex test cases are preferred to be combined together and conducted preferentially to increase the test efficiency. The effectiveness of this method is validated by applying it on a lane departure warning system (LDW).     

先进驾驶辅助系统的发展现状和趋势

简要介绍先进驾驶辅助系统的概念和组成架构,详细阐述夜视系统、主动巡航控制系统、电子稳定程序、随动转向前照灯、车道偏离报警、防碰撞技术、盲点辅助技术和泊车辅助技术的组成原理以及目前的应用情况,探讨先进驾驶辅助系统的发展前景。     

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。     

基于整车在环仿真的自动驾驶汽车室内快速测试平台

整车在环仿真测试方法可以安全、高效地验证复杂环境和极端工况等场景下自动驾驶汽车性能的有效性，基于此研发一种基于整车在环仿真的自动驾驶汽车室内快速测试平台，该平台由前轴可旋转式转鼓试验台、试验台测控子系统、虚拟场景自动生成子系统、虚拟传感器模拟子系统、驾驶模拟器、自动驾驶汽车和测试结果自动分析评价子系统组成。通过在试验台滚筒上独立加载转矩模拟车辆行驶阻力，可动态模拟不同的路面附着系数，同时利用坡度、侧倾和转向随动机构可模拟车辆俯仰角、侧倾角和航向角3个自由度；采用虚拟现实技术柔性集成车辆动力学模型、传感器仿真、复杂道路交通环境及测试用例仿真，模拟多种道路交通场景，并通过传感器仿真及数据融合等技术快速测试自动驾驶汽车智能感知与行为决策等性能指标。将自动驾驶汽车、虚拟仿真场景和试验台耦合构建一个闭环系统，完成了多项关键技术研发，包括：多自由度高动态试验台结构设计、虚拟测试场景自动重构方法和传感器数据模拟及注入方法，可满足在各种场景下测试自动驾驶汽车整车性能的需求。此外，为验证快速测试平台的有效性，以U-turn轨迹跟踪控制为研究实例，基于简化的车辆运动学模型和模型预测控制算法，在平台上搭建U-turn场景并对自动驾驶汽车的轨迹跟踪控制算法性能进行大量测试。结果表明：自动驾驶汽车室内快速测试平台可以真实地模拟汽车在道路上的运行工况，自动驾驶汽车在虚拟场景中的轨迹跟踪效果良好，与参考轨迹的偏差小于8%，证明了该测试平台检测方法的有效性。     

汽车驾驶员模型的研究现状及发展趋势

汽车驾驶员模型是汽车交通安全、智能交通系统、汽车自动驾驶和车辆巡航等技术的基础研究内容和关键环节之一。按照汽车驾驶员模型的研究方向及应用,将驾驶员模型分为基于人—车—环境闭环系统汽车操纵稳定性的驾驶员模型、基于智能交通系统的驾驶员行为模型和基于交通安全的驾驶员疲劳模型等类型,综述了上述各类汽车驾驶员模型的研究现状,对各类驾驶员模型存在的不足进行了分析论述,并展望了汽车驾驶员模型的发展方向及趋势。     

基于状态空间采样的高速公路智能网联车辆轨迹动态规划

为实现智能网联车辆在高速公路动态行车环境下的轨迹实时规划，提出一种基于状态空间采样的轨迹动态规划方法。首先，以安全性为原则选取主车当前行驶的理想车道。基于Frenet坐标与笛卡尔坐标的转换关系，建立车辆运动横、纵向解耦的独立积分系统。将高速公路常见的行驶状态分为车道保持与定速巡航、变道以及前车跟随3类，预测主车行驶车道并针对3类行驶状态分别设计轨迹终端的目标配置方法。然后，利用多项式函数生成连接初始配置和目标配置的多条待选轨迹。构建考虑轨迹偏离理想车道程度、始末速度变化、规划周期和轨迹舒适性的综合损失函数，结合速度、加速度、曲率检查来评价各条待选轨迹的成本并进行排序。最后，预测车辆的横、纵向运动轨迹并构建一种胶囊形的车辆虚拟安全边界，通过碰撞检测，确定主车的最优轨迹，设置动态规划触发条件及时更新最优轨迹并避免过度规划浪费资源。研究结果表明：提出的算法能满足高速公路场景的动态规划需求；通过对轨迹规划周期、虚拟安全边界、动态规划时间间隔等关键参数的分析与优化，主车的横摆角速度范围稳定在-0.1~0.15 (°)·s^-1，横向加速度范围稳定在-0.16~0.32 m·s^-2，跟踪参考轨迹的最大误差不超过0.022 m，提出的算法能规划出具有高安全性、稳定性和舒适性的轨迹。