针对自适应巡航的驾驶人风格辨识

车辆进入自适应巡航工况下行驶时,不同风格的驾驶人会对自适应巡航控制系统(Adaptive Cruise Control,ACC)有不同的需求。文章首先通过对不同驾驶人在9种跟随试验下获取的实验数据分析,选取表征驾驶人风格的驾驶特征参数;其次对所有驾驶人驾驶特征参数利用K-mean算法聚类分析,将驾驶人三类,并利用BP神经网络建立辨识模型对驾驶人风格进行辨识。结果表明;文章提出的方法可以较高的准确率对驾驶人风格进行分类,提高自适应巡航系统适应驾驶人的能力。     

Human-Centered Design of an Acc-With-Braking and Forward-Crash-Warning System

This paper addresses the development of driver assistance systems whose functional purposes are to provide both adaptive cruise control (ACC) and forward collision warning (FCW). The purpose of the paper is to combine concepts from human factors psychology, vehicle-dynamics, and control theory, thereby contributing to the body of knowledge and understanding concerning human-centered approaches for designing and evaluating driver assistance systems. Conceptual and experimental results pertaining to driving manually and with the assistance of ACC and FCW are presented. The following human-centered aspects of driver-assistance systems are analyzed and presented: the looming effect; including rule-based and skill-based behavior in the design of ACC systems; using desired dynamics in controlling the driving process; braking rules that trade headway range for deceleration level; and collision-warning rules based on two different stress indicators. Field-test data are examined to justify and verify the parametric values selected for use in human-centered ACC systems. Measured data from on-road driving are used to evaluate the performance of proposed FCW systems in braking situations. The paper concludes with observations concerning the difficulty of developing a clear understanding of when and why drivers brake.     

Human-Centered Design of an Acc-With-Braking and Forward-Crash-Warning System

This paper addresses the development of driver assistance systems whose functional purposes are to provide both adaptive cruise control (ACC) and forward collision warning (FCW). The purpose of the paper is to combine concepts from human factors psychology, vehicle-dynamics, and control theory, thereby contributing to the body of knowledge and understanding concerning human-centered approaches for designing and evaluating driver assistance systems. Conceptual and experimental results pertaining to driving manually and with the assistance of ACC and FCW are presented. The following human-centered aspects of driver-assistance systems are analyzed and presented: the looming effect; including rule-based and skill-based behavior in the design of ACC systems; using desired dynamics in controlling the driving process; braking rules that trade headway range for deceleration level; and collision-warning rules based on two different stress indicators. Field-test data are examined to justify and verify the parametric values selected for use in human-centered ACC systems. Measured data from on-road driving are used to evaluate the performance of proposed FCW systems in braking situations. The paper concludes with observations concerning the difficulty of developing a clear understanding of when and why drivers brake.     

Driver curve speed model and its application to ACC speed control in curved roads

A speed control algorithm for an ACC (Adaptive Cruise Control) system for curved roads is proposed based on driver behavior characteristics. As the foundation of this research, a driver speed model for curved roads is developed using a series of experimental data regarding driver behavior. To adapt the model to each driver’s individual curve speed behavior, the coefficients of the model are identified in real time from the data sequences collected during drivers’ manual operation stage by a self-learning algorithm based on a Recursive Least-Square (RLS) method with a forgetting factor. Using this algorithm, the parameters of the driver model can be identified from the data collected in the manual operation phase, and the identification results are applied during the ACC automatic control phase. Based on the developed model, the ACC speed control algorithm is modified to provide each individual driver with a customized speed profile for the scenario of a curved road with no car ahead. Tests verify the applicability of the modified system.     

基于驾驶员行为模拟的ACC控制算法

基于驾驶员最优预瞄加速度模型建立了一种适用于多种典型行驶工况的ACC控制算法。该算法采用基于多目标模糊决策方法的驾驶安全性、工效性、轻便性与合法性评价指标以及基于预瞄跟随理论的微分校正函数，描述了ACC控制系统对自由工况、跟随工况和切入工况等不同行驶条件及汽车动力学系统强非线性特性的考虑。     

基于双模式执行器的商用车自适应巡航控制系统

为实现商用车自适应巡航控制(ACC)系统的功能,开发了双模式制动执行装置和电子油门控制装置,即基于高速开关阀的商用车气压电控辅助制动系统和双模式油门控制系统,可以实现驾驶员和ACC系统的协同切换控制。在此基础上,以某商用车为对象,设计了ACC系统,结合比例-积分控制器和Smith预估补偿器设计了ACC的下位控制算法。结果表明:该ACC系统速度稳态跟踪误差小于1 m.s-1,距离稳态跟踪误差小于1.5 m;同时油门执行器和制动执行器具有安装方便、与原车电子油门及气压制动系统兼容性好的优点。     

基于深度强化学习的车辆跟驰控制

针对自适应巡航控制系统在控制主车跟驰行驶中受前车运动状态的不确定性影响问题，在分析车辆运动特点的基础上，提出一种能够考虑前车运动随机性的跟驰控制策略。搭建驾驶人实车驾驶数据采集平台，招募驾驶人进行实车跟驰道路试验，建立驾驶人真实驾驶数据库。假设车辆未来时刻的加速度决策主要受前方目标车辆运动影响，建立基于双前车跟驰结构的主车纵向控制架构。将驾驶数据库中的驾驶数据分别视作前车和前前车运动变化历程，利用高斯过程算法建立了前车纵向加速度变化随机过程模型，实现对前方目标车运动状态分布的概率性建模。将车辆跟驰问题构建为一定奖励函数下的马尔可夫决策过程，引入深度强化学习研究主车跟驰控制问题。利用近端策略优化算法建立车辆跟驰控制策略，通过与前车运动随机过程模型进行交互式迭代学习，得到具有运动不确定性跟驰环境下的主车纵向控制策略，实现对车辆纵向控制的最优决策。最后基于真实驾驶数据，对控制策略进行测试。研究结果表明：该策略建立了车辆纵向控制与主车和双前车状态之间的映射关系，在迭代学习过程中对前车运动的随机性进行考虑，跟驰控制中不需要对前车运动进行额外的概率预测，能够以较低的计算量实现主车稳定跟随前车行驶。     

Self-tuning control algorithm design for vehicle adaptive cruise control system through real-time estimation of vehicle parameters and road grade

The main purpose of this paper is to design a self-tuning control algorithm for an adaptive cruise control (ACC) system that can adapt its behaviour to variations of vehicle dynamics and uncertain road grade. To this aim, short-time linear quadratic form (STLQF) estimation technique is developed so as to track simultaneously the trend of the time-varying parameters of vehicle longitudinal dynamics with a small delay. These parameters are vehicle mass, road grade and aerodynamic drag-area coefficient. Next, the values of estimated parameters are used to tune the throttle and brake control inputs and to regulate the throttle/brake switching logic that governs the throttle and brake switching. The performance of the designed STLQF-based self-tuning control (STLQF-STC) algorithm for ACC system is compared with the conventional method based on fixed control structure regarding the speed/distance tracking control modes. Simulation results show that the proposed control algorithm improves the performance of throttle and brake controllers, providing more comfort while travelling, enhancing driving safety and giving a satisfactory performance in the presence of different payloads and road grade variations.     

An adaptive lateral preview driver model

Successful modelling and simulation of driver behaviour is important for the current industrial thrust of computer-based vehicle development. The main contribution of this paper is the development of an adaptive lateral preview human driver model. This driver model template has a few parameters that can be adjusted to simulate steering actions of human drivers with different driving styles. In other words, this model template can be used in the design process of vehicles and active safety systems to assess their performance under average drivers as well as atypical drivers. We assume that the drivers, regardless of their style, have driven the vehicle long enough to establish an accurate internal model of the vehicle. The proposed driver model is developed using the adaptive predictive control (APC) framework. Three key features are included in the APC framework: use of preview information, internal model identification and weight adjustment to simulate different driving styles. The driver uses predicted vehicle information in a future window to determine the optimal steering action. A tunable parameter is defined to assign relative importance of lateral displacement and yaw error in the cost function to be optimized. The model is tuned to fit three representative drivers obtained from driving simulator data taken from 22 human drivers.     

自适应巡航及协同式巡航对交通流的影响分析

自适应巡航（ACC）和协同式自适应巡航（CACC）等自动驾驶技术正逐渐进入市场，未来一段时间内道路交通流将由人工驾驶车辆与不同等级、不同形式的自动驾驶车辆混合构成。为分析ACC和CACC对交通流的影响，利用实测交通数据NGSim建立人工驾驶车辆跟驰模型，并在综合已有ACC和CACC模型的基础上，提出基于安全间距的自动驾驶跟驰行为模型，进而得出不同ACC，CACC车辆渗透率下交通流的基本图模型。研究结果表明：自动驾驶可以提升交通容量；与ACC车辆比例r_a相比，CACC车辆比例r_c对交通容量的影响更为显著；当r_c>0.5时，饱和流量快速增加，当r_c=1时，饱和流量约为纯人工驾驶时的2倍。进一步，通过仿真考察车辆在车队中的跟驰响应和交通流在瓶颈处的运行情况。研究结果表明：自动驾驶改善了交通流的动态特性，对存在跟驰关系的连续车流来说，自动驾驶使得后车可以更加及时地响应前车的行为，车流会在更短的时间内进入稳态；在交通瓶颈处，自动驾驶降低了拥堵程度，提高了阻塞发生的临界流量。总体来看，自动驾驶对交通流静态和动态性能均有所提升，特别是在协同式自动驾驶场景下，车辆行为更加协调一致，交通流表现出良好的抗扰性，进一步验证了车路协同对自动驾驶的意义。     

Development of a Driving Behavior-Based Collision Warning System Using a Neural Network

An advanced driver assistance system (ADAS) uses radar, visual information, and laser sensors to calculate variables representing driving conditions, such as time-to-collision (TTC) and time headway (THW), and to determine collision risk using empirically set thresholds. However, the empirically set threshold can generate differences in performance that are detected by the driver. It is appropriate to quickly relay collision risk to drivers whose response speed to dangerous situations is relatively slow and who drive defensively. However, for drivers whose response speed is relatively fast and who drive actively, it may be better not to provide a warning if they are aware of the collision risk in advance, because giving collision warnings too frequently can lower the reliability of the warnings and cause dissatisfaction in the driver, or promote disregard. To solve this problem, this study proposes a collision warning system (CWS) based on an individual driver’s driving behavior. In particular, a driver behavior model was created using an artificial neural network learning algorithm so that the collision risk could be determined according to the driving characteristics of the driver. Finally, the driver behavior model was learned using actual vehicle driving data and the applicability of the proposed CWS was verified through simulation.     

面向人因的车路协同系统综合测试及影响评估

面向冬奥主干通道兴延高速，以驾驶人适应性为导向，构建一种面向人因的车路协同系统硬件在环效能测试平台，针对多种道路条件、交通状态、特殊事件等面向高速公路设计13种交通情境，从主、客观2个维度实现车路协同系统包括主观感受、高效性、安全性、生态性、舒适性、有效性6个方面的驾驶人适应性评价，分析车路协同驾驶状态下的综合评估指标及影响机理。主观评估结果显示，车路协同技术对驾驶人有积极作用，52%的被试认为车载预警信息可以使行车过程更安全。客观运行结果表明：由于车路协同状态下驾驶人对于前方道路危险状况的可预知性，导致驾驶人提前降速，运行速度降低，效率有所下降；车路协同条件下的加速度和换道次数明显减小，其安全性显著提升；由于车路协同系统避免了驾驶人对于突发危险状况的紧急制动，因此车辆的油耗、排放均明显降低，其生态性改善效果显著；归因于驾驶人对于车路协同系统熟悉程度不足，导致舒适度各系统存在不一致的结论，也表明驾驶人对于车路协同系统的接受度和信任度均有待进一步提高；驾驶人在车路协同条件下可获取不同路段的限速值和超速提示，其有效性表现出明显的优势，速度跟随比有显著提升。所构建的测试平台和指标体系为进一步深层次挖掘车路协同的作用机理奠定了基础。     

Nonlinear ACC in Simulation and Measurement

In this paper an adaptive cruise control (ACC) of a convoy consisting of two passenger cars is designed and tested. For the ACC only on board sensors in the following vehicle are used, communication within the convoy or between the controlled vehicle and electronic systems on the roadside is not assumed. A laser scanner is applied for range measurements, derived from the complete vision data of the area in front of the car. Since the scanner provides the range only, a Kalman Filter is used to estimate the velocity and acceleration of the car. For controller design the concept of flat outputs in connection with the exact state linearization is applied. Moreover, the exact state linearization is combined with a sliding mode control. The control parameters are obtained by an optimization algorithm using optimal tracking formulation. The optimization also guarantees individual vehicle stability as well as string stability of the convoy. It is shown how the convoy is responding to disturbances resulting from initial errors or from velocity steps by the leading vehicle at lower speed in simulation and experiment.     

Nonlinear ACC in Simulation and Measurement

In this paper an adaptive cruise control (ACC) of a convoy consisting of two passenger cars is designed and tested. For the ACC only on board sensors in the following vehicle are used, communication within the convoy or between the controlled vehicle and electronic systems on the roadside is not assumed. A laser scanner is applied for range measurements, derived from the complete vision data of the area in front of the car. Since the scanner provides the range only, a Kalman Filter is used to estimate the velocity and acceleration of the car. For controller design the concept of flat outputs in connection with the exact state linearization is applied. Moreover, the exact state linearization is combined with a sliding mode control. The control parameters are obtained by an optimization algorithm using optimal tracking formulation. The optimization also guarantees individual vehicle stability as well as string stability of the convoy. It is shown how the convoy is responding to disturbances resulting from initial errors or from velocity steps by the leading vehicle at lower speed in simulation and experiment.     

The perspectives of research for enhancing active safety based on advanced control technology

This paper considers the scope and the methodologies for enhancing active safety of road vehicles by sensing and control technologies. The first part of this paper introduces statistical data of traffic accidents in Japan, and describes the development of the drive recorder for accident/incident survey and analysis. Based on vehicle dynamics data, the algorithm of the drive recorder for capturing near-miss incident data is introduced. The second part of this paper reviews control problems of vehicle dynamics on micro-scale electric vehicles for enhancing vehicle dynamics and driving assistance function. In particular, the direct yaw moment control using in-wheel-motors and the active front steering control algorithm are described. The third part of the paper introduces the advanced driver assistance system adapted to driver characteristics and traffic situations. This part mainly describes an adaptive system, which adjusts the assisting manoeuvre depending on individual driver behaviour and situation, and some experimental investigations using the active interface vehicle and driving simulator. Finally, some perspectives and new challenges for future research on vehicle control technology are mentioned.     

Comparing and validating models of driver steering behaviour in collision avoidance and vehicle stabilisation

A number of driver models were fitted to a large data set of human truck driving, from a simulated near-crash, low-friction scenario, yielding two main insights: steering to avoid a collision was best described as an open-loop manoeuvre of predetermined duration, but with situation-adapted amplitude, and subsequent vehicle stabilisation could to a large extent be accounted for by a simple yaw rate nulling control law. These two phenomena, which could be hypothesised to generalise to passenger car driving, were found to determine the ability of four driver models adopted from the literature to fit the human data. Based on the obtained results, it is argued that the concept of internal vehicle models may be less valuable when modelling driver behaviour in non-routine situations such as near-crashes, where behaviour may be better described as direct responses to salient perceptual cues. Some methodological issues in comparing and validating driver models are also discussed.     

Comparative study between Korea and UK: relationship between driving style and real-world fuel consumption

It is known that differences in driving styles have a significant impact on fuel efficiency and driving styles are affected by various factors such as driver characteristics, street environment, traffic situation, vehicle performance, and weather conditions. However, existing knowledge about the relationship between driving style and fuel consumption is limited. Thus, the aim of this study was to analyze the relationship beteen driving style and fuel consumption. The analysis presented in this paper used data from three on-road experiments were conducted independently in two different countries, i.e. South Korea and the United Kingdom. In this study, 91 participants, consisting 44 UK drivers and 47 Korean drivers, were asked to drive approximately 28 km of UK road and 21 km of Korean road, respectively. Driving data, including real-time fuel consumption, vehicle speed, and acceleration pedal usage were collected. The results suggested that driving styles including average vehicle speed and average throttle position were highly correlated with the real-world fuel consumption, and the cultural factors, e.g. road environment, traffic design, and driver’s characteristics affected the driving styles and, consequently, fuel efficiency.     

Haptic steering support for driving near the vehicle’s handling limits; skid-pad case

Current vehicle dynamic control systems from simple yaw control to high-end active steering support systems are designed to primarily actuate on the vehicle itself, rather than stimulate the driver to adapt his/her inputs for better vehicle control. The driver though dictates the vehicle’s motion, and centralizing him/her in the control loop is hypothesized to promote safety and driving pleasure. Exploring the above statement, the goal of this study is to develop and evaluate a haptic steering support when driving near the vehicle’s handling limits (Haptic Support Near the Limits; HSNL). The support aims to promote the driver’s perception of the vehicle’s behaviour and handling capacity (the vehicle’s internal model) by providing haptic (torque) cues on the steering wheel. The HSNL has been evaluated in (a) driving simulator tests and (b) tests with a vehicle (Opel Astra G/B) equipped with a variable steering feedback torque system. Drivers attempted to achieve maximum velocity while trying to retain control in a circular skid-pad. In the simulator (a) 25 subjects drove a vehicle model parameterised as the Astra on a dry skid-pad while in (b) 17 subjects drove the real Astra on a wet skid-pad. Both the driving simulator and the real vehicle tests led to the conclusion that the HSNL assisted subjects to drive closer to the designated path while achieving effectively the same speed. With the HSNL the drivers operated the tires in smaller slip angles and hence avoided saturation of the front wheels’ lateral forces and excessive understeer. Finally, the HSNL reduced their mental and physical demand.     

Role of steering wheel feedback on driver performance: driving simulator and modeling analysis

When driving in curves, how do drivers use the force appearing on the steering wheel? As it carries information related to lateral acceleration, this force could be necessary for drivers to tune their internal model of vehicle dynamics; alternatively, being opposed to the drivers' efforts, it could just help them stabilize the steering wheel position. To assess these two hypotheses, we designed an experiment on a motion-based driving simulator. The steering characteristics of the vehicle were modified in the course of driving, unknown to drivers. Results obtained with standard drivers showed a surprisingly wide range of adaptation, except for exaggerated modifications of the steering force feedback. A two-level driver model, combining a preview of vehicle dynamics and a neuromuscular steering control, reproduces these experimental results qualitatively and indicates that adaptation occurs at the haptic level rather than in the internal model of vehicle dynamics. This effect is related to other theories on the manual control of dynamics systems, wherein force feedback characteristics are abstracted at the position control level. This research also illustrates the use of driving simulation for the study of driver behavior and future intelligent steering assistance systems.     

Study on driver model for hybrid truck based on driving simulator experimental results

In this paper, a proposed car-following driver model taking into account some features of both the compensatory and anticipatory model representing the human pedal operation has been verified by driving simulator experiments with several real drivers. The comparison between computer simulations performed by determined model parameters with the experimental results confirm the correctness of this mathematical driver model and identified model parameters. Then the driver model is joined to a hybrid vehicle dynamics model and the moderate car following maneuver simulations with various driver parameters are conducted to investigate influences of driver parameters on vehicle dynamics response and fuel economy. Finally, major driver parameters involved in the longitudinal control of drivers are clarified.