人机共驾智能车驾驶模式决策属性析取研究
|
摘要
为了深入分析驾驶模式决策影响因子,通过实车试验采集了人-车-路多源特征信息。用驾驶人主观经验将驾驶模式划分为人工驾驶、警示辅助、自动驾驶3种状态,并利用采集的驾驶人血流量脉冲(BVP)和皮肤电导(SC)值进行K均值聚类,将驾驶人当前合适的驾驶模式自动聚类为3级。通过融合驾驶人自汇报结果和聚类结果对驾驶模式进行准确标定。采用以信息增益为依据的Ranker算法对多特征进行排序,并在此基础上,根据多分类器分级结果确定最优特征属性集合。研究结果表明:当选取车速、车头时距、车道中心距离、前轮转角标准差、驾驶经验5个指标为特征子集时,支持向量机、朴素贝叶斯及K近邻这3种分类器的识别准确率都超过90%;除警示辅助模式与自动驾驶模式下的车速值和车道中心距之外,其余所有不同模式决策属性值均呈显著性差异;研究结果可为人机共驾智能车驾驶模式决策提供依据。
In order to explore the significant impact factors of intelligent driving mode selection,the multi-source feature information from driver-vehicle-road was collected by dint of on-road experiments.The driving modes were divided into three patterns,namely,manual driving,warning assistant,and automatic driving,and the driver should self-report the selected driving modes.Meanwhile,the method of K-Means clustering was employed to cluster the driver's state into three levels based on the indexes of blood flow pulse(BVP)and skin conductance(SC).The current driving mode suitable to drivers was automatically clustered into three levels,depending on the fusing results of the drivers' self-reported and clustering.Then,the Ranker attributes sorting algorithm based on information gain was employed to select the key features,and threeclassification algorithms(SVM,NB,and KNN)were selected to confirm the irrelevant or redundant feature attributes.The results show that vehicle's speed,time headway,the distance of lane departure,the standard deviation of the front wheel angle,and drivers' experience are significantly influenced the selection of driving modes.The accuracy rates of support vector machine(SVM),Naive Bayes(NB)and K-nearest neighbor(KNN)algorithm are greater than90%,when these five variables are selected as the feature subset.These five selected features are significantly different in different driving modes(p<0.05),except the value of vehicle speed and the distance of lane departure between warning assistant modes and automatic driving modes.The results can provide the theoretical support for the decision-making of driving modes of the intelligent vehicles.
In order to explore the significant impact factors of intelligent driving mode selection,the multi-source feature information from driver-vehicle-road was collected by dint of on-road experiments.The driving modes were divided into three patterns,namely,manual driving,warning assistant,and automatic driving,and the driver should self-report the selected driving modes.Meanwhile,the method of K-Means clustering was employed to cluster the driver's state into three levels based on the indexes of blood flow pulse(BVP)and skin conductance(SC).The current driving mode suitable to drivers was automatically clustered into three levels,depending on the fusing results of the drivers' self-reported and clustering.Then,the Ranker attributes sorting algorithm based on information gain was employed to select the key features,and threeclassification algorithms(SVM,NB,and KNN)were selected to confirm the irrelevant or redundant feature attributes.The results show that vehicle's speed,time headway,the distance of lane departure,the standard deviation of the front wheel angle,and drivers' experience are significantly influenced the selection of driving modes.The accuracy rates of support vector machine(SVM),Naive Bayes(NB)and K-nearest neighbor(KNN)algorithm are greater than90%,when these five variables are selected as the feature subset.These five selected features are significantly different in different driving modes(p<0.05),except the value of vehicle speed and the distance of lane departure between warning assistant modes and automatic driving modes.The results can provide the theoretical support for the decision-making of driving modes of the intelligent vehicles.
引文
[1]王国胤,陈乔松,王进.智能车技术探讨[J].计算机科学,2012,39(5):1-8.WANG Guo-yin,CHEN Qiao-song,WANG Jin.Discussion on the Intelligent Vehicle Technologies[J].Computer Science,2012,39(5):1-8.
[2]BAHRAM M,AEBERHARD M,WOLLHERR D.Please Take Over!An Analysis and Strategy for a Driver Take Over Request During Autonomous Driving[C]//IEEE.Proceedings of the 2015IEEE Intelligent Vehicles Symposium.New York:IEEE,2015:913-919.
[3]SHENG W,OU Y,TRAN D,et al.An Integrated Manual and Autonomous Driving Framework Based on Driver Drowsiness Detection[C]//IEEE.Proceedings of the 2013IEEE/RSJ International Conference on Intelligent Robots and Systems.New York:IEEE,2013:4376-4381.
[4]BRANDENBURG S,SKOTTKE E M.Switching From Manual to Automated Driving and Reverse:Are Drivers Behaving More Risky After Highly Automated Driving?[C]//IEEE.Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems.New York:IEEE,2014:2978-2983.
[5]王殿海,金盛.车辆跟驰行为建模的回顾与展望[J].中国公路学报,2012,25(1):115-127.WANG Dian-hai,JIN Sheng.Review and Outlook of Modeling of Car Following Behavior[J].China Journal of Highway and Transport,2012,25(1):115-127.
[6]ZEEB K,BUCHNER A,SCHRAUF M.What Determines the Take-over Time?An Integrated Model Approach of Driver Take-over After Automated Driving[J].Accident Analysis&Prevention,2015,78:212-221.
[7]WILKE M,DE HAAN B D,JUENGER H,et al.Manual Semi-automated,and Automated Delineation of Chronic Brain Lesions:A Comparison of Methods[J].Neuroimage,2011,56(4):2038-2046.
[8]HEALEY J A,PICARD R W.Detecting Stress During Real-world Driving Tasks Using Physiological Sensors[J].IEEE Transactions on Intelligent Transportation Systems,2005,6(2):156-166.
[9]MILANS V,LLORCA D F,VILLAGRA J,et al.Intelligent Automatic Overtaking System Using Vision for Vehicle Detection[J].Expert Systems with Applications,2012,39(3):3362-3373.
[10]彭理群,吴超仲,黄珍.基于变精度粗糙集的汽车碰撞危险态势评估[J].交通运输系统工程与信息,2013,13(5):120-126.PENG Li-qun,WU Chao-zhong,HUANG Zhen.Situation Assessment of Vehicle Collision Risk Based on Variable Precision Rough Set[J].Journal of Transportation System Engineering and Information Technology,2013,13(5):120-126.
[11]DY J G,BRODLEY C E.Feature Selection for Unsupervised Learning[J].Journal of Machine Learning Research,2004,5(4):845-889.
[12]CHEN Z,WU C,ZHANG Y,et al.Feature Selection with Redundancy-complementariness Dispersion[J].Knowledge-based Systems,2015,89:203-217.
[13]YANG S.On Feature Selection for Traffic Congestion Prediction[J].Transportation Research Part C,2013,26:160-169.
[14]张轮,杨文臣,刘拓,等.基于朴素贝叶斯分类的高速公路交通事件检测[J].同济大学学报:自然科学版,2014,42(4):558-595.ZHANG Lun,YANG Wen-chen,LIU Tuo,et al.A Naive Bayesian Classifier-based Algorithm for Freeway Traffic Incident Detection[J].Journal of Tongji University:Natural Science,2014,42(4):558-595.
[15]YEO M V M,LI X,SHEN K,et al.Can SVM be Used for Automatic EEG Detection of Drowsiness During Car Driving?[J].Safety Science,2009,47(1):115-124.
[16]于滨,邬珊华,王明华,等.K近邻短时交通流预测模型[J].交通运输工程学报,2012,12(2):105-111.YU Bin,WU Shan-hua,WANG Ming-hua,et al.Knearest Neighbor Model of Short-term Traffic Flow Forecast[J].Journal of Traffic and Transportation Engineering,2012,12(2):105-111.
[17]袁伟.城市道路环境中汽车驾驶员动态视觉特性试验研究[D].西安:长安大学,2008.YUAN Wei.Study on Car Driver’s Dynamic Visual Characters Test on City Road[D].Xi’an:Chang’an University,2008.
[18]严利鑫,吴超仲,高嵩,等.驾驶人个体因素对驾驶愤怒情绪影响关系研究[J].交通信息与安全,2013,31(6):119-124.YAN Li-xin,WU Chao-zhong,GAO Song,et al.Relationship Between Driver’s Temperament and Driving Anger[J].Journal of Transport Information and Safety,2013,31(6):119-124.
[19]GUO F,FANG Y.Individual Driver Risk Assessment Using Naturalistic Driving Data[J].Accident Analysis&Prevention,2013,61:3-9.
[20]FAYYAD U,IRANI K.Multi-interval Discretization of Continuous-valued Attributes for Classification Learning[C]//IJCAI.Proceedings of the International Joint Conference on Uncertainty in AI.Chambery:IJCAI,1993:1022-1027.
[2]BAHRAM M,AEBERHARD M,WOLLHERR D.Please Take Over!An Analysis and Strategy for a Driver Take Over Request During Autonomous Driving[C]//IEEE.Proceedings of the 2015IEEE Intelligent Vehicles Symposium.New York:IEEE,2015:913-919.
[3]SHENG W,OU Y,TRAN D,et al.An Integrated Manual and Autonomous Driving Framework Based on Driver Drowsiness Detection[C]//IEEE.Proceedings of the 2013IEEE/RSJ International Conference on Intelligent Robots and Systems.New York:IEEE,2013:4376-4381.
[4]BRANDENBURG S,SKOTTKE E M.Switching From Manual to Automated Driving and Reverse:Are Drivers Behaving More Risky After Highly Automated Driving?[C]//IEEE.Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems.New York:IEEE,2014:2978-2983.
[5]王殿海,金盛.车辆跟驰行为建模的回顾与展望[J].中国公路学报,2012,25(1):115-127.WANG Dian-hai,JIN Sheng.Review and Outlook of Modeling of Car Following Behavior[J].China Journal of Highway and Transport,2012,25(1):115-127.
[6]ZEEB K,BUCHNER A,SCHRAUF M.What Determines the Take-over Time?An Integrated Model Approach of Driver Take-over After Automated Driving[J].Accident Analysis&Prevention,2015,78:212-221.
[7]WILKE M,DE HAAN B D,JUENGER H,et al.Manual Semi-automated,and Automated Delineation of Chronic Brain Lesions:A Comparison of Methods[J].Neuroimage,2011,56(4):2038-2046.
[8]HEALEY J A,PICARD R W.Detecting Stress During Real-world Driving Tasks Using Physiological Sensors[J].IEEE Transactions on Intelligent Transportation Systems,2005,6(2):156-166.
[9]MILANS V,LLORCA D F,VILLAGRA J,et al.Intelligent Automatic Overtaking System Using Vision for Vehicle Detection[J].Expert Systems with Applications,2012,39(3):3362-3373.
[10]彭理群,吴超仲,黄珍.基于变精度粗糙集的汽车碰撞危险态势评估[J].交通运输系统工程与信息,2013,13(5):120-126.PENG Li-qun,WU Chao-zhong,HUANG Zhen.Situation Assessment of Vehicle Collision Risk Based on Variable Precision Rough Set[J].Journal of Transportation System Engineering and Information Technology,2013,13(5):120-126.
[11]DY J G,BRODLEY C E.Feature Selection for Unsupervised Learning[J].Journal of Machine Learning Research,2004,5(4):845-889.
[12]CHEN Z,WU C,ZHANG Y,et al.Feature Selection with Redundancy-complementariness Dispersion[J].Knowledge-based Systems,2015,89:203-217.
[13]YANG S.On Feature Selection for Traffic Congestion Prediction[J].Transportation Research Part C,2013,26:160-169.
[14]张轮,杨文臣,刘拓,等.基于朴素贝叶斯分类的高速公路交通事件检测[J].同济大学学报:自然科学版,2014,42(4):558-595.ZHANG Lun,YANG Wen-chen,LIU Tuo,et al.A Naive Bayesian Classifier-based Algorithm for Freeway Traffic Incident Detection[J].Journal of Tongji University:Natural Science,2014,42(4):558-595.
[15]YEO M V M,LI X,SHEN K,et al.Can SVM be Used for Automatic EEG Detection of Drowsiness During Car Driving?[J].Safety Science,2009,47(1):115-124.
[16]于滨,邬珊华,王明华,等.K近邻短时交通流预测模型[J].交通运输工程学报,2012,12(2):105-111.YU Bin,WU Shan-hua,WANG Ming-hua,et al.Knearest Neighbor Model of Short-term Traffic Flow Forecast[J].Journal of Traffic and Transportation Engineering,2012,12(2):105-111.
[17]袁伟.城市道路环境中汽车驾驶员动态视觉特性试验研究[D].西安:长安大学,2008.YUAN Wei.Study on Car Driver’s Dynamic Visual Characters Test on City Road[D].Xi’an:Chang’an University,2008.
[18]严利鑫,吴超仲,高嵩,等.驾驶人个体因素对驾驶愤怒情绪影响关系研究[J].交通信息与安全,2013,31(6):119-124.YAN Li-xin,WU Chao-zhong,GAO Song,et al.Relationship Between Driver’s Temperament and Driving Anger[J].Journal of Transport Information and Safety,2013,31(6):119-124.
[19]GUO F,FANG Y.Individual Driver Risk Assessment Using Naturalistic Driving Data[J].Accident Analysis&Prevention,2013,61:3-9.
[20]FAYYAD U,IRANI K.Multi-interval Discretization of Continuous-valued Attributes for Classification Learning[C]//IJCAI.Proceedings of the International Joint Conference on Uncertainty in AI.Chambery:IJCAI,1993:1022-1027.