自适应自动驾驶等级的驾驶人状态监测模型研究

doi:10.3901/JME.2023.02.187

摘要/Abstract

摘要： 自动驾驶等级的逐级提升意味着驾驶执行权从驾驶人向车辆自动控制系统逐渐转移，驾驶人所承担的责任也随之发生变化。大量研究表明，自动驾驶车辆驾驶人的注意力跨度与行驶安全性密切相关，且不同等级自动驾驶所要求的驾驶人状态阈值存在差异。提出一种融合长短记忆（Long short term memory，LSTM）网络和驾驶人状态判别机制的驾驶人负荷状态预测模型（long short term memory network driver state prediction model，LSTM-DSDM），实现驾驶人负荷状态的预测及其状态转变阶段的识别，并基于不同自动驾驶等级下驾驶人的任务要求，提出了“低等级识别，高等级预测”的驾驶人负荷状态监测策略。试验结果表明本研究搭建的驾驶员负荷状态预测模型在低自动驾驶等级情况下的负荷识别率可达90%以上；在高自动驾驶等级情况下实现可靠的负荷预测和驾驶人负荷状态过渡阶段的辨识，有效应对不同自动驾驶等级驾驶人负荷状态的监测需求。

关键词: 自动驾驶等级, 驾驶人能力需求, 驾驶人状态监测, 负荷过渡, LSTM

Abstract: The gradual increase in the level of automatic driving means that the power of driving execution is gradually transferred from the driver to the vehicle system, and the responsibilities of the driver also change accordingly. A large number of studies have shown that the attention span of the driver of an autonomous vehicle is closely related to driving safety, and there are differences in the driver state thresholds required for different levels of autonomous driving. This research proposes an long short term memory(LSTM) network driver state prediction model(LSTM-DSDM) that integrates the driver state discrimination mechanism to realize the prediction of the driver's load state and the recognition of the state transition stage, and based on the task requirements of drivers under different levels of automatic driving, a driver's load status monitoring strategy of low-level recognition, high-level prediction is proposed. The experimental results show that the driver's load status monitoring strategy proposed in this study can effectively respond to the driver's load status monitoring needs of different autonomous driving levels. The driver's load state prediction model built in this study has a high recognition rate under the condition of low autopilot level, which can reach more than 90%; under the condition of high autopilot level, the prediction rate of the model can achieve the prediction effect to a certain extent, and it can also be used to study the transition phase of the driver's load state.

Key words: driving automation level, driver capability requirements, driver condition monitoring, load transition, long short term memory(LSTM)

中图分类号:

U469

黄晶, 陈紫琳, 杨梦婷, 彭晓燕. 自适应自动驾驶等级的驾驶人状态监测模型研究[J]. 机械工程学报, 2023, 59(2): 187-198.

HUANG Jing, CHEN Zilin, YANG Mengting, PENG Xiaoyan. Research on Driving Automation Level-adaptive Driver Condition Monitoring Models[J]. Journal of Mechanical Engineering, 2023, 59(2): 187-198.

参考文献

[1] 美国汽车工程师学会, 国际标准组织. J3016-2018汽车驾驶自动化分级[S]. 北京:中国标准出版社, 2020. Society of Automotive Engineers, International Standardization Organization. J3016-2018 Automotive driving automation classification[S]. Beijing:China Standard Press, 2020.
[2] 陈枫. 无人驾驶时代正在到来[N]. 北京日报, 2020-04-01(9). CHEN Feng. The era of unmanned driving is coming[N]. Beijing Daily, 2020-04-01(9).
[3] HU L, OU J, HUANG J, et al. A review of research on traffic conflicts based on intelligent vehicles[J]. IEEE Access, 2020, 99(8):24471-24483.
[4] PONTE G, WUNDERSITZ L N. Exploring the prevalence of in-vehicle driver distraction in moving traffic:Apilot study[J]. Centre for Automotive Safety Research, 2019, 4(4):17-19.
[5] NIU J, WANG X, LIU X, et al. Effects of mobile phone use on driving performance in a multiresource workload scenario[J]. Traffic Injury Prevention, 2019, 20(1):1-8.
[6] SCHOETTLE B, SIVAK M. A preliminary analysis of real-world crashes involving self-driving vehicles[R]. Ann Arbor:University of Michigan Transportation Research Insititute, 2015.
[7] 李荣粲, 庄伟超, 殷国栋, 等. 自动驾驶赛车路径与车速协同规划方法[J]. 机械工程学报, 2022, 58(10):200-208. Li Rongcan, Zhuang Weichao, Yin Guodong, et al. Collaborative path and speed planning method for self-driving racing cars[J]. Chinese Journal of Mechanical Engineering, 2022, 58(10):200-208.
[8] 魏凌涛, 王翔宇, 邱彬, 等. 基于自适应预瞄路径的自动驾驶车辆寻迹和避障控制[J]. 机械工程学报, 2022, 58(6):184-193. Wei Lingtao, Wang Xiangyu, Qiu Bin, et al. Adaptive pre-sighted path-based tracing and obstacle avoidance control for self-driving vehicles[J]. Chinese Journal of Mechanical Engineering, 2022, 58(6):184-193.
[9] 李鹏辉, 胡孟夏, 张文会, 等. 分心对驾驶人交通冲突反应时间的影响[J]. 中国公路学报, 2018, 31(4):36-42. LI Penghui, HU Mengxia, ZHANG Wenhui, et al. The influence of distraction on the reaction time of drivers in traffic conflict[J]. China Journal of Highway and Transport, 2018, 31(4):36-42.
[10] 李鹏辉, 廖呈玮, 郑志晓, 等. 认知分心对车辆跟驰过程操控安全性的影响[J]. 中国公路学报, 2018, 31(5):167-173. LI Penghui, LIAO Chengwei, ZHENG Zhixiao, et al. The influence of cognitive distraction on the safety of vehicle following process[J]. China Journal of Highway and Transport, 2018, 31(5):167-173.
[11] ZEEB K, BUCHNER A, SCHRAUF M. Is take-over time all that matters? The impact of visual-cognitive load on driver take-over quality after conditionally automated driving[J]. Accident Analysis & Prevention, 2016, 92(7):230-239.
[12] ERIKSSON A, STANTON N A. Takeover time in highly automated vehicles:Noncritical transitions to and from manual control[J]. Human Factors the Journal of the Human Factors and Ergonomics Society, 2017, 59(4):689-705.
[13] 钮建伟, 张雪梅, 孙一品, 等. 险情中驾驶人接管自动驾驶车辆的驾驶行为研究[J]. 中国公路学报, 2018, 31(6):272-280. NIU Jianwei, ZHANG Xuemei, SUN Yipin, et al. Study on the driving behavior of the driver taking over the autonomous vehicle in a dangerous situation[J]. China Journal of Highway and Transport, 2018, 31(6):272-280.
[14] 杨威, 郑玲, 李以农. 基于高斯混合模型的个性化自动驾驶决策控制研究[J]. 机械工程学报, 2022, 58(16):280-289. Yang Wei, Zheng Ling, Li Yinong. Research on personalised autonomous driving decision control based on Gaussian mixture models[J]. Journal of Mechanical Engineering, 2022, 58(16):280-289.
[15] 林庆峰, 王兆杰, 鲁光泉. 城市道路环境下自动驾驶车辆接管绩效分析[J]. 中国公路学报, 2019, 32(6):240-247. LIN Qingfeng, WANG Zhaojie, LU Guangquan. Analysis of autonomous vehicle takeover performance in urban road environment[J]. China Journal of Highway and Transport, 2019, 32(6):240-247.
[16] HWANG B, YOU J, VAESSEN T, et al. Deep ECGNet:An optimal deep learning framework for monitoring mental stress using ultra short-term ECG signals[J]. Telemedicine and e-Health, 2018, 24(10):753-772.
[17] ZHU B, LIU Z P, ZHAO J, et al. Driver behavior characteristics identification strategies based on bionic intelligent algorithms[J]. IEEE Transactions on Human-Machine Systems, 2018, 48(6):572-581.
[18] 刘明周, 蒋倩男, 扈静. 基于面部几何特征及手部运动特征的驾驶员疲劳检测[J]. 机械工程学报, 2019, 55(2):32-40. LIU Mingzhou, JIANG Qiannan, HU Jing. Driver fatigue detection based on facial geometric features and hand motion features[J]. Journal of Mechanical Engineering, 2019, 55(2):32-40.
[19] SESHADRI K, JUEFEI-XU F, PAL D K, et al. Driver cell phone usage detection on strategic highway research program (shrp2) face view videos[C]//Computer Vision and Pattern Recognition. Proceedings of the IEEE Conference, California:the Computer Vision Foundation, 2015:35-43.
[20] RAHMAN H, AHMED M U, BARUA S, et al. Non-contact-based driver's cognitive load classification using physiological and vehicular parameters[J]. Biomedical Signal Processing and Control, 2020, 55(10):1-13.
[21] 郭孜政, 潘雨帆, 潘毅润, 等. 驾驶员脑力负荷的SVM识别模型[J]. 哈尔滨工业大学学报, 2016, 48(3):154-158. GUO Zizheng, PAN Yufan, PAN Yirun, et al. SVM recognition model of driver's mental workload[J]. Journal of Harbin Institute of Technology, 2016, 48(3):154-158.
[22] Chiang HS. ECG-based mental stress assessment using fuzzy computing and associative petrinet[J]. Journal of Medical&Biological Engineering, 2015, 35(6):833-844.
[23] AMIR T, KIHYO J, et al. Classification of a driver's cognitive workload levels using artificial neural network on ECG signals[J]. Applied Ergonomics, 2017, 59(Pt A):326-332.
[24] HUANG J, LUO X, PENG X Y. A novel classification method for a driver's cognitive stress level by transferring interbeat intervals of the ECG signal to pictures[J]. Sensors, 2020, 20(5):1340-1352.
[25] 扈静, 钱佩伦, 刘明周, 等. 基于肌肉生理信号的操纵舒适性评价[J]. 中国机械工程, 2018, 29(2):200-204. HU Jing, QIAN Peilun, LIU Mingzhou, et al. Manipulation comfort evaluation based on muscle physiological signals[J]. China Mechanical Engineering, 2018, 29(2):200-204.
[26] YANG C, BAABAK A. Predicting the volatility of highway construction cost index using long short-term memory[J]. Journal of Management in Engineering, 2020, 36(4):1-12.
[27] 孙博华, 邓伟文, 吴坚, 等. 虚拟随机车路场下驾驶人驾驶能力机理分析[J]. 机械工程学报, 2020, 56(16):166-180. SUN Bohua, DENG Weiwen, WU Jian, et al. Analysis of the driving ability mechanism of drivers under virtual random vehicles[J]. Journal of Mechanical Engineering, 2020, 56(16):166-180.
[28] COLLET C, MUSICANT O. Associating vehicles automation with drivers functional state assessment systems:a challenge for road safety in the future[J]. Frontiers in Human Neuroscience, 2019, 13(131):1-12.
[29] GOLD C, BERISHA I, BENGLER K. Utilization of drivetime-performing non-driving related tasks while driving highly automated[J]. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 2015, 59(1):1666-1670.
[30] 任秉韬, 邓伟文, 白雪松, 等. 面向智能驾驶测试的仿真场景构建技术综述[J]. 中国图象图形学报, 2021, 26(1):1-12. REN Bingtao, DENG Weiwen, BAI Xuesong, et al. Overview of simulation scene construction technology for intelligent driving test[J]. Journal of Image and Graphics, 2021, 26(1):1-12.
[31] Ranney T A, Garrott W R, Goodman M J. NHTSA driverdistractionresearch:past, present, andfuture[C]//National Highway Traffic Safety Administration, 2001:1-7.
[32] 许力, 胡杰, 孟武强. 个性化驾驶员模型及其在车辆测试中应用[J]. 机械工程学报, 2015, 51(18):136-142. XU Li, HU Jie, MENG Wuqiang. Personalized driver model and its application in vehicle testing[J]. Journal of Mechanical Engineering, 2015, 51(18):136-142.
[33] PAVAN G M, MALAYA K H. A review on ECG filtering techniques for rhythm analysis[J]. Research on Biomedical Engineering, 2020, 36(2):171-186.
[34] 张振慧, 张正江, 胡桂廷, 等. 基于拉依达准则与线性拟合的改进型无迹卡尔曼滤波粗大误差补偿算法[J]. 计算机测量与控制, 2019, 27(11):153-156, 162. ZHANG Zhenhui, ZHANG Zhengjiang, HU Guiting, et al. Improved unscented Kalman filter coarse error compensation algorithm based on Laida criterion and linear fitting[J]. Computer Measurement and Control, 2019, 27(11):153-156, 162.
[35] 刘振宇, 周思杭, 谭建荣, 等. 基于多准则修正的产品性能多参数关联分析与预测方法[J]. 机械工程学报, 2013, 49(15):105-114. LIU Zhenyu, ZHOU Sihang, TAN Jianrong, et al. Multi-parameter correlation analysis and prediction method of product performance based on multi-criteria modification[J]. Journal of Mechanical Engineering, 2013, 49(15):105-114.
[36] 黄晶, 杨梦婷. 考虑初始情绪的个性化驾驶负荷状态评价[J]. 中国公路学报, 2021, 34(1):167-176. HUANG Jing, YANG Mengting. Personalized driving load state evaluation considering initial emotions[J]. China Journal of Highway and Transport, 2021, 34(1):167-176.
[37] KARTHIKEYAN P, MURUGAPPAN M, YAACOB S. Detection of human stress using short-term ECG and HRV signals[J]. Journal of Mechanics in Medicine and Biology, 2013, 13(2):1-29.
[38] KATJA P, BENEDICT H, CHRISTIAN S, et al. Stress load of emergency service:effects on the car and HRV of HEMS emergency physicians on different working days (N=20)[J]. International Archives of Occupational and Environmental Health, 2019, 92(2):155-164.