基于MLP-SVM的驾驶员换道行为预测

doi:10.12382/bgxb.2021.0652

摘要/Abstract

摘要： 驾驶员行为的不确定性为高级驾驶辅助系统的应用带来挑战。为更加准确预测驾驶员的换道行为，通过深入研究多层感知机(MLP)深度学习算法与支持向量机(SVM)算法，设计了MLP-SVM预测算法，应用于驾驶员换道行为预测。基于驾驶车辆信息和周围交通环境信息建立驾驶员换道行为预测模型，并采用公开实车驾驶数据集进行验证。研究结果表明，基于MLP-SVM的驾驶员换道行为预测模型，与分别基于MLP或SVM的驾驶员换道行为预测模型对比，取得的最高预测准确率为92.6%，可更早预测出换道行为，提前预测时间可达4.54 s。

关键词: 智能车辆, 换道行为, 多层感知机, 支持向量机, 预测模型

Abstract: The uncertainty of human driver behavior brings challenges to the application of advanced driver assistance systems. In order to more accurately predict the lane-changing behavior of a driver, we studied the multi-layer perceptron (MLP) and the support vector machine (SVM), and designed the hybrid algorithm of MLP-SVM to predict the lane-changing behavior of the driver. Based on the vehicle information and the surrounding traffic environment information, the prediction model of driver's lane changing behavior is built. The real traffic dataset is used to verify the proposed model. The results show that compared with the prediction model of driver's lane changing behavior based on support vector machines or multi-layer perceptrons, the hybrid prediction model of driver's lane changing behavior achieves the highest prediction accuracy of 92.6%, and can predict the lane changing behavior earlier with the advanced prediction time up to 4.54 s.

Key words: intelligencevehicle, lanechangingbehavior, multilayerperceptron, supportvectormachines, predictionmodel

中图分类号:

TP242.6

密俊霞，于会龙，席军强. 基于MLP-SVM的驾驶员换道行为预测[J]. 兵工学报, 2022, 43(12): 3020-3029.

MI Junxia, YU Huilong, XI Junqiang. Prediction of Driver's Lane Changing Behavior Based on MLP-SVM[J]. Acta Armamentarii, 2022, 43(12): 3020-3029.

参考文献

［1］ HASENJGER M, HECKMANN M, WERSING H. A survey of personalization for advanced driver assistance stems[J].IEEE Transactions on Intelligent Vehicles, 2020, 5(2):335-344.
[2］ SEN B, SMITH J D, NAJM W G. Analysis of lane change crashes:DOT-VNTSC-NHTSA-02-03[R]. Washington, DC, US:National Highway Traffic Safety Administration, 2003.
[3］丁洁云, 党睿娜, 王建强, 等.驾驶人换道决策分析及意图识别算法设计[J].清华大学学报(自然科学版), 2015, 55(7):769-774.
DING J Y, DANG R N, WANG J Q, et al. Driver lane change decision analysis and intention recognition algorithm[J]. Journal of Tsinghua University (Science and Technology), 2015, 55(7):769-774.(in Chinese)
[4］宗长富, 王畅, 何磊, 等.基于双层隐式马尔科夫模型的驾驶意图辨识[J].汽车工程, 2011, 33(8):701-706.
ZONG C F, WANG C, HE L, et al. Driving intention recognition based on double-layer HMM[J]. Automotive Engineering, 2011, 33(8):701-706.(in Chinese)
[5］宋晓琳, 郑亚奇, 曹昊天.基于HMM-SVM的驾驶员换道意图辨识研究[J].电子测量与仪器学报, 2016, 30(1):58-65.
SONG X L, ZHENG Y Q, CAO H T. Research on driver's lane change intention recognition based on HMM and SVM[J]. Journal of Electronic Measurement and Instrument, 2016, 30(1):58-65.(in Chinese)
[6］刘志强, 吴雪刚, 倪捷, 等. 基于HMM和SVM级联算法的驾驶意图识别[J].汽车工程, 2018, 40(7):858-864.
LIU Z Q, WU X G, NI J. Driving intention recognition based on HMM and SVM cascade algorithm[J]. Automotive Engineering, 2018, 40(7):858-864.(in Chinese)
[7］ BUTAKOV V, IOANNOU P. Personalized driver vehicle lane change models for ADAS[J]. IEEE Transactions on Vehicular Technology, 2015, 64(10):4422-4431.
[8］ KASPER D, WEIDL G, DANG T, et al. Object-oriented bayesian networks for detection of lane change maneuvers[C]∥Proceedings of 2011 IEEE Intelligent Vehicles Symposium(IV).Baden-Baden, Germany:IEEE, 2011:673-678.
[9］ MORRIS B, DOSHI A, TRIVEDI M. Lane change intent prediction for driver assistance: on-road design and evaluation[C]∥Proceedings of 2011 IEEE Intelligent Vehicles Symposium(IV). Baden-Baden, Germany：IEEE, 2011:895-901.
[10］ LI J H, LU C, XU Y Z, et al. Manifold learning for lane-changing behavior recognition in urban traffic[C]∥Proceedings of 2019 IEEE Intelligent Transportation Systems Conference. Auckland, New Zealand:IEEE, 2019:3663-3668.
[11］ KUMAR P, PERROLLAZ M, LEFèVRE S, et al. Learning-based approach for online lane change intention prediction[C]∥Proceedings of 2013 IEEE Intelligent Vehicles Symposium(IV).Gold Coast, Australia:IEEE, 2013: 797-802.
[12］ SCHLECTRIEMEN J, WEDEL A, HILLENBRAND J, et al. A lane change detection approach using feature ranking with maximized predictive power[C]∥Proceedings of 2014 IEEE Intelligent Vehicles Symposium. Dearborn, MI, US:IEEE, 2014: 108-114.
[13］ LIU Y K, WANG Z R, HAN K, et al. Vision-cloud data fusion for ADAS:a lane change prediction case study[J]. IEEE Transactions on Intelligent Vehicles, 2021,7(2):210-220.
[14］季学武, 费聪, 何祥坤, 等基于LSTM网络的驾驶意图识别及车辆轨迹预测[J].中国公路学报, 2019, 32(6):34-42.
JI X W, FEI C, HE X K, et al. Intention recognition and trajectory prediction for vehicles using lstm network[J].China Journal of Highway and Transport, 2019, 32(6):34-42.(in Chinese)
[15］宗长富, 杨肖, 王畅, 等.汽车转向时驾驶员驾驶意图辨识与行为预测[J].吉林大学学报(工学版), 2009, 39(增刊1):27- 32.
ZONG C F, XIAO Y, WANG C, et al. Driving intentions identification and behaviors prediction in car lane change[J].Journal of Jilin University(Engineering and Technology Edition), 2009, 39(S1):27-32.(in Chinese)
[16］王庆年, 唐先智, 王鹏宇, 等.基于神经网络的混合动力汽车驾驶意图识别方法[J].农业机械学报, 2012, 43(8):38-42.
WANG Q N, TANG X Z, WANG P Y, et al. Driving intention identification method for hybrid vehicles based on neural network[J]. Transactions of The Chinese Society of Agricultural Machinery, 2012, 43(8):38-42.(in Chinese)
[17］ DANG H Q, FURNKRANZ J, BIEDERMANN A, et al. Time to lane change prediction with deep learning[C]∥Proceedings of the 2017 IEEE 20th International Conference on Intelligent Transportation Systems(ITSC).Yokohama, Japan:IEEE, 2017:1-7.
[18］ LI L, ZHAO W Z, XU C, et al. Lane-change intention inference based on RNN for autonomous driving on highways[J]. IEEE Transactions on Vehicular Technology, 2021:5499-5510.
[19］ OU C, KARRAY F. Deep learning-based driving maneuver prediction system[J].IEEE transactions on vehicular technology, 2019, 69(2):1328-1340.
[20］ KHAIRDOOST N, SHIRPOUR M, BAUER M A, et al.Real-time driver maneuver prediction using LSTM[J].IEEE Transactions on Intelligent Vehicles, 2020, 5(4):714-724.
[21］ LETHAUS F, RATAJ J. Do eye movements reflect driving manoeuvres[J]. Iet Intelligent Transport Systems, 2007, 1(3):199-204.
[22］ DOSHI A, TRIVEDI M M. On the roles of eye gaze and head dynamics in predicting driver's intent to change lanes[J].IEEE Transactions on Intelligent Transportation Systems, 2009, 10(3): 453-462.
[23］ LETHAUS F, BAUMANN M, KOESTER F, et al. A comparison of selected simple supervised learning algorithms to predict driver intent based on gaze data[J]. Neurocomputing, 2013, 121(12): 108-130.
[24］张立军, 唐鑫, 孟德建.面向驾驶意图识别的驾驶员头、面部视觉特征提取[J]. 汽车技术, 2019, 521(2):18-24.
ZHANG L J, TANG X, MENG D J, et al. Driver's head and face visual feature extraction for driving intention recognition[J]. Automobile Technology, 2019, 521(2):18-24.(in Chinese)
[25］ DENG Q, WANG J, HILLEBRAND K, et al. Prediction performance of lane changing behaviors:a study of combining environmental and eye-tracking data in a driving simulator[J].IEEE Transactions on Intelligent Transportation Systems, 2019, 21(8):3561-3570.
[26］ YANG S, WANG W S, LU C, et al. A time-efficient approach for decision-making style recognition in lane changing behavior[J]. IEEE Transactions on Human-Machine Systems, 2019, 49(6): 579-588.
[27］ LI X H, WANG W S, ROETTING M. Estimating driver's lane-change intent considering driving style and contextual traffic[J].IEEE Transactions on Intelligent Transportation Systems, 2018:1-14.
[28］ LU C, HU F Q, WANG W S, et al. Transfer learning for driver model adaptation via modified local procrustes analysis[C]∥Proceedings of 2018 IEEE Intelligent Vehicles Symposium. New York, NY, US:IEEE, 2018:73-78.
[29］ LU C, HU F Q, CAO D P, et al. Transfer learning for driver model adaptation in lane-changing scenarios using manifold alignment[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 99:1-13.
[30］ LU C, HU F Q, CAO D P, et al. Virtual-to-real knowledge transfer for driving behavior recognition: framework and a case study[J］.IEEE Transactions on Vehicular Technology, 2019, 68(7): 6391-6402.
[31］ KRAJEWSKI R, BOCK J, KLOEKER L, et al. The highD dataset:a drone dataset of naturalistic vehicle trajectories on german highways for validation of highly automated driving systems[C]∥Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems. New York, NY, US:IEEE, 2018:2118-2125.

[1]	刘子昌, 李思雨, 裴模超, 刘洁, 孟硕, 吴巍屹. 基于纹理分析的柴油发动机故障诊断方法[J]. 兵工学报, 2024, 45(2): 684-694.
[2]	方秋雨, 张蕴霖, 麻壮壮, 邵晋梁. 未知环境下基于控制障碍函数的无人车轨迹规划[J]. 兵工学报, 2023, 44(S2): 90-102.
[3]	蒋岩, 丁语嫣, 张兴龙, 徐昕. 基于模型预测与策略学习的智能车辆人机协同控制算法[J]. 兵工学报, 2023, 44(11): 3465-3477.
[4]	丁伟, 明振军, 王国新, 阎艳. 基于多层次LSTM网络的多智能体攻防效能动态预测模型[J]. 兵工学报, 2023, 44(1): 176-192.
[5]	裘镓荣, 曾鹏飞, 邵伟平, 赵丽俊, 郝永平. 基于PSO-LSSVM弹药装配质量预测方法[J]. 兵工学报, 2022, 43(9): 2379-2387.
[6]	段浩，陈晖，翟兆阳，韩雨，马凡华，崔亚辉. 基于支持向量机的氢混天然气发动机性能预测[J]. 兵工学报, 2022, 43(5): 1002-1011.
[7]	杨建新，兰小平，冯亚东，杨一铭，郭志明. 基于改进樽海鞘群和最小二乘支持向量机算法的新型弹药质量评估方法[J]. 兵工学报, 2022, 43(5): 1012-1022.
[8]	辛大钧，薛琨. 基于人工神经网络的非球形破片阻力系数预测模型[J]. 兵工学报, 2022, 43(5): 1083-1092.
[9]	李良钰，苏铁熊，马富康，吴小军，徐春龙. 基于集合经验模态分解-支持向量机的高压共轨系统故障诊断方法[J]. 兵工学报, 2022, 43(5): 992-1001.
[10]	徐雨芯，顾楚梅，曹建军，许金勇，魏志虎. 基于蚁群特征选择并行分类集成学习的孪生辐射源个体识别[J]. 兵工学报, 2022, 43(12): 3132-3141.
[11]	陆瑶敏, 龚建伟, 王博洋, 关海杰. 基于多重示范的智能车辆运动基元表征与序列生成[J]. 兵工学报, 2021, 42(4): 851-861.
[12]	马润波，董丽虹，王海斗. 基于支持向量机的热喷涂层接触疲劳寿命预测[J]. 兵工学报, 2021, 42(12): 2743-2752.
[13]	雷震烁，刘松涛，温镇铭，葛杨. 复杂电磁环境下末制导雷达工作状态实时判别方法[J]. 兵工学报, 2021, 42(1): 83-90.
[14]	王成，吴岩，杨廷飞. 利用改进单分类支持向量机提升舰船尾流目标的检测准确率[J]. 兵工学报, 2020, 41(9): 1887-1893.
[15]	吕国俊，曹建军，郑奇斌，常宸，翁年凤，彭琮. 基于多目标蚁群优化的单类支持向量机相似重复记录检测[J]. 兵工学报, 2020, 41(2): 324-331.