Study on the Take-over Performance of Level 3 Autonomous Vehicles Based on Subjective Driving Tendency Questionnaires and Machine Learning Methods

Level 3 autonomous vehicles require conditional autonomous driving in which autonomous and manual driving are alternately performed; whether the driver can resume manual driving within a limited time should be examined. This study investigates whether the demographics and subjective driving tendencies of drivers affect the take-over performance. We measured and analyzed the reengagement and stabilization time after a take-over request from the autonomous driving system to manual driving using a vehicle simulator that supports the driver's take-over mechanism. We discovered that the driver's reengagement and stabilization time correlated with the speeding and wild driving tendency as well as driving workload questionnaires. To verify the efficiency of subjective questionnaire information, we tested whether the driver with slow or fast reengagement and stabilization time can be detected based on machine learning techniques and obtained results. We expect to apply these results to training programs for autonomous vehicles' users and personalized human–vehicle interfaces for future autonomous vehicles.     

Multimodal Interface Based on Novel HMI UI/UX for In‐Vehicle Infotainment System

We propose a novel HMI UI/UX for an in‐vehicle infotainment system. Our proposed HMI UI comprises multimodal interfaces that allow a driver to safely and intuitively manipulate an infotainment system while driving. Our analysis of a touchscreen interface–based HMI UI/UX reveals that a driver's use of such an interface while driving can cause the driver to be seriously distracted. Our proposed HMI UI/UX is a novel manipulation mechanism for a vehicle infotainment service. It consists of several interfaces that incorporate a variety of modalities, such as speech recognition, a manipulating device, and hand gesture recognition. In addition, we provide an HMI UI framework designed to be manipulated using a simple method based on four directions and one selection motion. Extensive quantitative and qualitative in‐vehicle experiments demonstrate that the proposed HMI UI/UX is an efficient mechanism through which to manipulate an infotainment system while driving.     

In‐Vehicle AR‐HUD System to Provide Driving‐Safety Information

Augmented reality (AR) is currently being applied actively to commercial products, and various types of intelligent AR systems combining both the Global Positioning System and computer‐vision technologies are being developed and commercialized. This paper suggests an in‐vehicle head‐up display (HUD) system that is combined with AR technology. The proposed system recognizes driving‐safety information and offers it to the driver. Unlike existing HUD systems, the system displays information registered to the driver's view and is developed for the robust recognition of obstacles under bad weather conditions. The system is composed of four modules: a ground obstacle detection module, an object decision module, an object recognition module, and a display module. The recognition ratio of the driving‐safety information obtained by the proposed AR‐HUD system is about 73%, and the system has a recognition speed of about 15 fps for both vehicles and pedestrians.     

Driving altitude generation method with pseudo-3D building model for unmanned aerial vehicles

Spatial information is geometrical information combined with the properties of an object. In city areas where unmanned aerial vehicle (UAV) usage demand is high, it is necessary to determine the appropriate driving altitude considering the height of buildings for safe driving. In this study, we propose a data-provision method that generates the driving altitude of UAVs with a pseudo-3D building model. The pseudo-3D building model is developed using high-precision spatial information provided by the National Geographic Information Institute. The proposed method generates the driving altitude of the UAV in terms of tile information, including the UAV's starting and arrival points and a straight line between the two points, and provides the data to users. To evaluate the efficacy of the proposed method, UAV driving altitude information was generated using data of 763 551 pseudo-3D buildings in Seoul. Subsequently, the generated driving altitude data of the UAV was verified in AirSim. In addition, the execution time of the proposed method and the calculated driving altitude were analyzed.     

Co‐Pilot Agent for Vehicle/Driver Cooperative and Autonomous Driving

ETRI's Co‐Pilot project is aimed at the development of an automated vehicle that cooperates with a driver and interacts with other vehicles on the road while obeying traffic rules without collisions. This paper presents a core block within the Co‐Pilot system; the block is named “Co‐Pilot agent” and consists of several main modules, such as road map generation, decision‐making, and trajectory generation. The road map generation builds road map data to provide enhanced and detailed map data. The decision‐making, designed to serve situation assessment and behavior planning, evaluates a collision risk of traffic situations and determines maneuvers to follow a global path as well as to avoid collisions. The trajectory generation generates a trajectory to achieve the given maneuver by the decision‐making module. The system is implemented in an open‐source robot operating system to provide a reusable, hardware‐independent software platform; it is then tested on a closed road with other vehicles in several scenarios similar to real road environments to verify that it works properly for cooperative driving with a driver and automated driving.     

Driver fatigue detection based on deeply-learned facial expression representation

Driver fatigue detection is a significant application in smart cars. In order to improve the accuracy and timeliness of driver fatigue detection, a fatigue detection algorithm based on deeply-learned facial expression analysis is proposed. Specifically, the face key point detection model is first trained by multi block local binary patterns (MB-LBP) and Adaboost classifier. Subsequently, the eyes and mouth state are detected by using the trained model to detect the 24 facial features. Afterwards, we calculate the number of two parameters that can describe the driver's fatigue state and the proportion of the closed eye time within the unit time (PERCLOS) and yawning frequency. Finally, the fuzzy inference system is utilized to deduce the driver's fatigue state (normal, slight fatigue, severe fatigue). Experimental results show that the proposed algorithm can detect driver fatigue degree quickly and accurately.     

GSM模块TC35在汽车信息记录仪中的应用

TC35是Siemens公司推出的无线通信GSM模块,可以快速安全可靠地实现数据、语音传输、短消息服务和传真。详细地分析了TC35的结构、特点和工作原理,介绍其与4串口ARM处理器配合在汽车信息记录仪中的使用,实现汽车行驶里程、超速纪录、当前位置等信息的记录功能,并可以根据需求情况把相关信息传送到公司总部,系统地给出了相关硬件电路和软件的设计方法。     

可重构信息安全系统研究综述

传统安全计算提供固定的安全服务能力,无法根据环境和安全需求的变化灵活配置,导致安全管理复杂,软硬件资源重复利用率低.可重构安全计算为提升系统灵活性、适应性和可扩展性提供了新的手段.本文阐述了可重构安全计算的发展历程,初步研究了其内涵与意义,提出了可重构安全计算的概念模型,并详细论述了其中的关键技术及其研究现状,最后分析了可重构安全计算的发展趋势.可重构信息安全系统是新型计算与信息安全技术融合的必然产物,必将为信息安全技术提供更广阔的应用空间.     

对于驾驶机器人性能综合评价的研究

为了综合评价驾驶机器人的驾驶性能,在单纯指标评价的基础上,提出一种新的综合评价方法.经过对驾驶机器人的实测验证,获得的数据证明此方法能时驾驶机嚣人驾驶性能进行定性的、直观的综合评价.     

Model Reference Adaptive Control Based on Adjustable Reference Model during Mode Transition for Hybrid Electric Vehicles

Hybrid elective vehicles (HEVs) operate in multiple driving modes, e.g., motor driving mode, engine driving mode, and combined driving mode, under various different scenarios. Therefore, mode transition between different driving modes is necessary to ensure high-efficiency operation of HEVs under various running conditions. This paper proposes adjustable reference model (ARM)-based model reference adaptive control (MRAC) to solve the problems of deviation from driver's intention and lack of adaptability to parameter changes. The driveline dynamics model during mode transition is built and validated. The dynamics in the mode before the mode transition is taken as the reference model whose parameters are estimated online. Thereafter, the adaptive law is derived. Simulation and hardware-in-loop experiments are carried out. The results show that the mode transition performance under varying driver's demand torque is satisfactory in terms of not only vehicle jerk, but also clutch slipping time and frictional loss. And, the controller has good adaptability to different vehicle masses and road slopes. The ability to deal with the disturbance in clutch torque with low frequency is also validated.     

基于SVM的疲劳驾驶人脸图像特征检测算法

针对传统图像识别算法对疲劳驾驶检测精度差、准确率低的缺陷,提出了一种利用人脸图像特征提取的疲劳驾驶检测方法。首先将实时采集到的车辆驾驶员面部图像进行预处理,借助Dlib检测出图像中的人脸区域并进行人脸图像特征点的标注,然后使用基于眼睛纵横比(Eye Aspect Ratio,EAR)的方法进行图像中人眼疲劳特征的识别,基于嘴唇纵横比(Mouth Aspect Ratio,MAR)的方法进行图像中嘴部疲劳特征的识别,最后利用支持向量机(SVM)的方法将两种特征融合起来进行疲劳驾驶检测。实验表明,该方法可以准确地定位出特征点,疲劳检测的识别率达84.29%,可以有效地识别出疲劳状态。     

From destination prediction to route prediction

A prediction of a vehicle's route would be useful for giving the driver advance warnings and alerts about upcoming situations and opportunities. This paper presents a new algorithm for predicting a driver's route based on a probabilistic prediction of the driver's destination. For each candidate destination, our route prediction algorithm plans a route to that destination. Roads on these routes accumulate the probabilities of their respective destinations, giving higher probabilities to roads along the way to higher probability destinations. The algorithm is based on a single parameter that characterises how efficiently a driver drives. Once this parameter is computed, it does not require storing a history of trips, and it works in places a driver has never visited. We test the algorithm on 100 routes recorded with the Global Positioning System (GPS) and show that the route prediction quickly narrows down the future route to a small fraction of the road network. We also compare our algorithm to two other algorithms to show how it performs better.     

EEG-based prediction of driver's cognitive performance by deep convolutional neural network

We considered the prediction of driver's cognitive states related to driving performance using EEG signals. We proposed a novel channel-wise convolutional neural network (CCNN) whose architecture considers the unique characteristics of EEG data. We also discussed CCNN-R, a CCNN variation that uses Restricted Boltzmann Machine to replace the convolutional filter, and derived the detailed algorithm. To test the performance of CCNN and CCNN-R, we assembled a large EEG dataset from 3 studies of driver fatigue that includes samples from 37 subjects. Using this dataset, we investigated the new CCNN and CCNN-R on raw EEG data and also Independent Component Analysis (ICA) decomposition. We tested both within-subject and cross-subject predictions and the results showed CCNN and CCNN-R achieved robust and improved performance over conventional DNN and CNN as well as other non-DL algorithms.     

特种车辆驾驶员任务终端的设计

针对特种车辆信息化、数字化的提升,为驾驶员实时提供各种行驶与实验数据、同时提高精度和可靠性,设计实现了基于嵌入式操作系统VxWorks及其图形开发工具Zinc的特种车辆任务终端。论述了系统总体方案,以及系统的硬件、软件设计流程。设计实现了基于CAN总线的集车辆信息显示、视频辅助驾驶、定位导航于一体的驾驶员终端,并在样机上进行试验。结果显示,该系统运行稳定、可靠,能很好地满足特种车辆的设计要求。     

基于驾驶数据的主动安全预警系统设计

随着人们生活水平的提高,车辆的安全性越来越成为人们共同追求和关注的焦点。在“人-车-路-环境”的交通系统中以信息技术为主导的车辆主动安全预警系统是解决车辆驾驶安全问题的最佳方法。文章基于驾驶数据得到驾驶人驾驶风险评估,依据峰值触发系统报警,有效保障了车辆全过程安全行驶,避免交通事故发生。     

ETC收费系统在高速公路收费站的应用

ETC收费系统为自动收费系统,驾驶员无需停车,收费系统就可以将驾驶员所需要交纳费用计算出来.ETC收费系统运用计算机网络完成全程收费,其具有自动识别技术,能够对驶入高速公路的车辆进行识别.运用计算机网络建立高速公路与银行的联系,实现后台信息交换.目前,ETC收费系统已经在全国各地普及,面对车流量呈增长趋势,多数收费站都改用ETC收费系统.本论文针对ETC收费系统在高速公路收费站的应用进行探究.     

Design and implementation of a real-time eye tracking system

Driver fatigue severely affects driver's alertness and ability to drive safely. There are vital problems related to drivers fatigue on driving of trains, vehicles and airplanes. Therefore, the driver fatigue research is important. In this paper, we first study the impact of eye locations on face recognition accuracy, with Haar-like feature and AdaBoost classifier, face and eye area can be detected quickly and accurately. In the part of eye tracking, cam-shift based mean-shift algorithm is used to track the eyes. This method could automatically adjust the size of tracking window according to the different posture of driver. The performance of our eye detection method is validated by using image database with more than 6000 pictures. In addition, our real-time eye tracking system has been tested on railway line segment (China). There are 5 train drivers involved in the experiment. The validation shows that our eye detector has an overall 93% eye detection rate.     

一种压电材料的新型线性高电压驱动器

提出一种压电材料的新型线性高电压驱动器的研制方案,驱动器包括两大部分,即大功率、可对压电作动器进行正负向电压加载的闭环倍压放大式线性高电压驱动器;基于固态继电器的ON/OFF驱动器,内含压电作动器的电压加载控制模块和快速放电控制模块。该驱动器线性输出电压为直流电压(-220～+220V),输出频率可达3kHz。     

Novel TFT-Based emission driver in high performance AMOLED display applications

A novel integrated row driver for emission control with n-type thin-film transistors (TFTs) was proposed. A single stage of the proposed driving circuit consists of charge supplement unit, improved inverter, and power conservation unit besides input TFT and driving TFTs. Simulations were carried out with fabricated LTPS TFT. The results show the driving circuit achieves leakage prevention with no floating state and high reliability even under the V_th shift of 3 V. What's more, further measurement results show a 3 μs pulse width can be generated by the circuit, supporting 8k4k resolution with high refresh rate of 120 Hz. And the capability of low refresh rate (1 Hz) driving also can be achieved without degradation. In addition, only three control signals (two non-overlap clocks and one input signal) are used in the proposed circuit, where input signal of present stage is connected with the output of its previous stage. That means the row driver can work under independent control and be not susceptible, which contributes to generating adjustable pulse width for pulse width modulation (PWM) in active matrix organic light-emitting diode (AMOLED) displays.     

应用于等离子体显示器的自适应子场编码驱动方法

为解决交流等离子体显示器(AC PDP)中传统"单纯累积"发光模式产生的灰度显示不足的问题,本文提出了一种自适应子场编码驱动方法(ASC).该方法中子场编码根据每一场输入图像的归一化灰度直方图进行自适应地计算,将子场编码权值选取在输入图像灰度信息最丰富的区间.同时根据计算出的子场编码,驱动电路调整各个子场的维持脉冲个数.仿真结果表明,该方法不仅能够消除AC PDP中的动态假轮廓现象,而且弥补了传统"单纯累积"发光模式造成的灰度显示不足的问题,具有良好的灰度显示效果.