面向人机协同共驾的驾驶行为短时预测方法研究
|
摘要
通过实时感知交通场景下的汽车相对运动状态和行车安全信息,对驾驶人的操纵行为进行短时预测,进而为人机协同驾驶中主权切换的模式与方法提供依据。基于线性最优二次型方法建立了典型驾驶意图下的驾驶操纵序贯链优化目标函数,通过求解目标函数得到驾驶人操纵行为对车辆运动状态的改变量,并结合运动学CA模型提出了驾驶操纵行为短时预测模型。运用统计检验分析实车试验和所提出的模型得到的仿真试验驾驶输入之间的差异程度。实车实验的统计检验结果表明,不同驾驶工况下的驾驶输入差值的配对样本T检验的T统计量分别为1.96, 0.1, 1.36,均小于其T临界检验值。所提出的模型能较好的模拟实际驾驶操纵行为特征,并能对驾驶人操纵行为进行准确的短时预测。
By real-time perception of relative motion status of vehicles and traffic safety information, a short-time forecasting of drivers′ behaviors is developed. Basis for a method of man-machine operation switch in cooperative driving is provided. Based on a linear optimal quadratic method, an optimization objective function of expected driving sequential chain is established under typical driving intentions. By solving the target function, expected control input of drivers is obtained. Combined with a traditional CA model, a model of short-time forecasting of operation behaviors of drivers is proposed. A statistical test is used to analyze differences between actual data and results of the model. The results from paired sample T test show that T statistics of different input value under different driving conditions are 1.96, 0.1, and 1.36, respectively, which are all less than critical T test value. The proposed model can adapt to actual characteristics of driving operations, and furthermore accurately forecast operation behaviors of drivers.
By real-time perception of relative motion status of vehicles and traffic safety information, a short-time forecasting of drivers′ behaviors is developed. Basis for a method of man-machine operation switch in cooperative driving is provided. Based on a linear optimal quadratic method, an optimization objective function of expected driving sequential chain is established under typical driving intentions. By solving the target function, expected control input of drivers is obtained. Combined with a traditional CA model, a model of short-time forecasting of operation behaviors of drivers is proposed. A statistical test is used to analyze differences between actual data and results of the model. The results from paired sample T test show that T statistics of different input value under different driving conditions are 1.96, 0.1, and 1.36, respectively, which are all less than critical T test value. The proposed model can adapt to actual characteristics of driving operations, and furthermore accurately forecast operation behaviors of drivers.
引文
[1] 严利鑫,秦伶巧,熊钰冰,等.多模式共驾智能车行驶安全性评估研究[J].交通信息与安全,2018,36(3):1-7,26. YAN Lixin, QIN Lingqiao, XIONG Yubing, et al. A safety evaluation on intelligent vehicles with multi-mode cooperative driving[J]. Journal of Transport Information and Safety, 2018,36(3):1-7,26. (in Chinese)
[2] 马勇,付锐,郭应时,等.基于实车试验的驾驶人换道行为多参数预测[J].长安大学学报(自然科学版),2014,34(5):101-108. MA Yong, FU Rui, GUO Yingshi, et al. Multi-parameter preditction of driver′s lane change behavior or based on real-world driving tests[J]. Journal of Changan University(Natural Science Edition), 2014,34(5):101-108. (in Chinese)
[3] 李亚秋,吴超仲,马晓凤,等.基于EKF学习方法的BP神经网络汽车换道意图识别模型研究[J].武汉理工大学学报(交通科学与工程版),2013,37(4):843-847. LI Yaqiu, WU Chaozhong, HUANG Zhen, et al. A recognition model for lane change intention based on neural network with EKF Algorithm[J]. Journal of Wuhan University of Technology (Transportation Science & Engineering, 2013,37(4):843-847. (in Chinese)
[4] 张良力,祝贺,马天宇.基于贝叶斯网络的机动车驾驶行为状态分析建模[J].交通信息与安全,2014,32(5):77-82.
[5] ZHANG Liangli, ZHU He, MA Tianyu. Model for vehicle driver′s behavior analysis based on bayesian network[J]. Journal of Transport Information and Safety, 2014,32(5):77-82. (in Chinese)
[6] ZHAO C, GAO Y, HE J, et al. Recognition of driving postures by multiwavelet transform and multilayer perceptron classifier[J]. Engineering Applications of Artificial Intelligence, 2012,25(8):1677-1686.
[7] KLINGELSCHMITT S, PLATHO M, GROSS H M, et al. Combining behavior and situation information for reliably estimating multiple intentions[C]. 2014 IEEE Intelligent Vehicles Symposium, Dearborn, MI, USA: IEEE,2014.
[8] KUMAR P, PERROLLAZ M, LEFEVRE S, et al. Learning-based approach for online lane change intention prediction[C]. 2013 IEEE Intelligent Vehicles Symposium (IV), Gold Coast City, Australia: IEEE, 2013.
[9] LEE C, YI K. Modeling and control of an electronic-vacuum booster for vehicle cruise control[J]. Ksme International Journal, 2002,16(10):1314-1319.
[10] THORSLUND B, AHLSTR?M C, PETERS B, et al. Cognitive workload and visual behavior in elderly drivers with hearing loss[J]. European Transport Research Review, 2014,6(4):377-385.
[11] LI G, LI S E, CHENG B, et al. Estimation of driving style in naturalistic highway traffic using maneuver transition probabilities[J]. Transportation Research Part C, 2017,74:113-125. [12] 解少博,林程.基于无迹卡尔曼滤波的车辆状态与参数估计[J].农业机械学报,2011,42(12):6-12. XIE Shaobo, LIN Cheng. State and parameters estimation of vehicle based on UKF[J]. Transactions of the Chinese Society for Agricultural Machinery, 2011,42(12):6-12. (in Chinese)
[13] LI X R, JILKOV V P. Survey of maneuvering target tracking: Part I. Dynamic models[J]. IEEE Transactions on Aerospace & Electronic Systems, 2004,39(4):1333-1364.
[14] PENG Liqun, WU Chaozhong, HUANG Zhen, et al. Novel vehicle motion model considering driver behavior for trajectory prediction and driving risk detection[J]. Journal of the Transportation Research Board, 2014(2434):123-134.
[15] Lee C, YI K. Modeling and control of an electronic-vacuum booster for vehicle cruise control[J]. Ksme International Journal, 2002,16(10):1314-1319.
[16] 徐杰,杜文,孙宏.跟随车安全距离的分析[J].交通运输工程学报,2002,2(1):101-104. XU Jie, DU Wen, SUN Hong. Safety distance about car-following[J]. Journal of Traffic and Transportation Engineering, 2002,2(1):101-104. (in Chinese)
[17] GUO B, YUAN Y. A comparative review of methods for comparing means using partially paired data[J]. Statistical Methods in Medical Research, 2017,26(3):1323-1340.
[18] FU Y, ZHU J, WANG S, et al. Reduced complexity SNR estimation via Kolmogorov-Smirnov Test[J]. IEEE Communications Letters, 2015,19(9):1568-1571.
[19] OLIVERA R, OLIVERA R, VITE O, et al. Application of the three state kalman filtering for moving vehicle tracking[J]. IEEE Latin America Transactions, 2016,14(5):2072-2076.
[2] 马勇,付锐,郭应时,等.基于实车试验的驾驶人换道行为多参数预测[J].长安大学学报(自然科学版),2014,34(5):101-108. MA Yong, FU Rui, GUO Yingshi, et al. Multi-parameter preditction of driver′s lane change behavior or based on real-world driving tests[J]. Journal of Changan University(Natural Science Edition), 2014,34(5):101-108. (in Chinese)
[3] 李亚秋,吴超仲,马晓凤,等.基于EKF学习方法的BP神经网络汽车换道意图识别模型研究[J].武汉理工大学学报(交通科学与工程版),2013,37(4):843-847. LI Yaqiu, WU Chaozhong, HUANG Zhen, et al. A recognition model for lane change intention based on neural network with EKF Algorithm[J]. Journal of Wuhan University of Technology (Transportation Science & Engineering, 2013,37(4):843-847. (in Chinese)
[4] 张良力,祝贺,马天宇.基于贝叶斯网络的机动车驾驶行为状态分析建模[J].交通信息与安全,2014,32(5):77-82.
[5] ZHANG Liangli, ZHU He, MA Tianyu. Model for vehicle driver′s behavior analysis based on bayesian network[J]. Journal of Transport Information and Safety, 2014,32(5):77-82. (in Chinese)
[6] ZHAO C, GAO Y, HE J, et al. Recognition of driving postures by multiwavelet transform and multilayer perceptron classifier[J]. Engineering Applications of Artificial Intelligence, 2012,25(8):1677-1686.
[7] KLINGELSCHMITT S, PLATHO M, GROSS H M, et al. Combining behavior and situation information for reliably estimating multiple intentions[C]. 2014 IEEE Intelligent Vehicles Symposium, Dearborn, MI, USA: IEEE,2014.
[8] KUMAR P, PERROLLAZ M, LEFEVRE S, et al. Learning-based approach for online lane change intention prediction[C]. 2013 IEEE Intelligent Vehicles Symposium (IV), Gold Coast City, Australia: IEEE, 2013.
[9] LEE C, YI K. Modeling and control of an electronic-vacuum booster for vehicle cruise control[J]. Ksme International Journal, 2002,16(10):1314-1319.
[10] THORSLUND B, AHLSTR?M C, PETERS B, et al. Cognitive workload and visual behavior in elderly drivers with hearing loss[J]. European Transport Research Review, 2014,6(4):377-385.
[11] LI G, LI S E, CHENG B, et al. Estimation of driving style in naturalistic highway traffic using maneuver transition probabilities[J]. Transportation Research Part C, 2017,74:113-125. [12] 解少博,林程.基于无迹卡尔曼滤波的车辆状态与参数估计[J].农业机械学报,2011,42(12):6-12. XIE Shaobo, LIN Cheng. State and parameters estimation of vehicle based on UKF[J]. Transactions of the Chinese Society for Agricultural Machinery, 2011,42(12):6-12. (in Chinese)
[13] LI X R, JILKOV V P. Survey of maneuvering target tracking: Part I. Dynamic models[J]. IEEE Transactions on Aerospace & Electronic Systems, 2004,39(4):1333-1364.
[14] PENG Liqun, WU Chaozhong, HUANG Zhen, et al. Novel vehicle motion model considering driver behavior for trajectory prediction and driving risk detection[J]. Journal of the Transportation Research Board, 2014(2434):123-134.
[15] Lee C, YI K. Modeling and control of an electronic-vacuum booster for vehicle cruise control[J]. Ksme International Journal, 2002,16(10):1314-1319.
[16] 徐杰,杜文,孙宏.跟随车安全距离的分析[J].交通运输工程学报,2002,2(1):101-104. XU Jie, DU Wen, SUN Hong. Safety distance about car-following[J]. Journal of Traffic and Transportation Engineering, 2002,2(1):101-104. (in Chinese)
[17] GUO B, YUAN Y. A comparative review of methods for comparing means using partially paired data[J]. Statistical Methods in Medical Research, 2017,26(3):1323-1340.
[18] FU Y, ZHU J, WANG S, et al. Reduced complexity SNR estimation via Kolmogorov-Smirnov Test[J]. IEEE Communications Letters, 2015,19(9):1568-1571.
[19] OLIVERA R, OLIVERA R, VITE O, et al. Application of the three state kalman filtering for moving vehicle tracking[J]. IEEE Latin America Transactions, 2016,14(5):2072-2076.