基于规则与机器学习融合的换道决策建模方法研究

doi:10.3901/JME.2022.04.212

机械工程学报 ›› 2022, Vol. 58 ›› Issue (4): 212-221.doi: 10.3901/JME.2022.04.212

扫码分享

基于规则与机器学习融合的换道决策建模方法研究

贾寒冰^1,2, 刘鹏^1,2, 张雷^1,2, 王震坡^1,2

1. 北京理工大学电动车辆国家工程实验室北京 100081;
2. 北京电动车辆协同创新中心北京 100081

收稿日期:2021-04-05 修回日期:2021-09-25 出版日期:2022-02-20 发布日期:2022-04-30
通讯作者: 张雷(通信作者),男,1987年出生,博士,北京理工大学特别研究员,博士研究生导师。主要研究方向为智能网联新能源汽车整车动力学控制及储能系统管理技术。E-mail:lei_zhang@bit.edu.cn
作者简介:贾寒冰,男,1995年出生。主要研究方向为智能车辆行车决策与轨迹规划。E-mail:hanbing_jia@bit.edu.cn;刘鹏,男,1983年出生,博士,副教授,硕士研究生导师。主要研究方向为新能源汽车大数据分析。E-mail:bitliupeng@bit.edu.cn;王震坡,男,1976年出生,博士,教授,博士研究生导师。主要研究方向为车辆动力学理论与控制,车用锂离子动力电池成组理论与技术。E-mail:wangzhenpo@bit.edu.cn
基金资助:
科技部重点专项资助项目(2017YFB0103600)。

Lane-changing Decision Model Development by Combining Rules Abstract and Machine Learning Technique

JIA Hanbing^1,2, LIU Peng^1,2, ZHANG Lei^1,2, WANG Zhenpo^1,2

1. National Engineering Laboratory for Electric Vehicles, Beijing Institute of Technology, Beijing 100081;
2. Collaborative Innovation Center of Electric Vehicles in Beijing, Beijing Institute of Technology, Beijing 100081

Received:2021-04-05 Revised:2021-09-25 Online:2022-02-20 Published:2022-04-30

摘要/Abstract

摘要： 自主换道系统是智能车辆技术的重要发展方向，而换道决策是自主换道系统的关键。针对结构化道路下的自由换道场景，提出基于规则与机器学习融合的换道决策模型。针对换道决策过程中存在的多参数与非线性问题，提出基于支持向量机的换道决策模型，并引入贝叶斯优化算法确定决策模型的最优参数。从基于规则的角度出发，分析换道决策过程中的影响因素，包括换道必要性、安全性与换道收益，并将上述规则转化为模型训练数据的新特征与安全约束，对原有训练样本进行增广，以提升支持向量机模型的分类准确率。在NGSIM数据集上进行测试验证，结果表明，仅利用周围车辆基本行驶信息进行模型训练，对换道行为预测的准确率为73.05%，而引入基于换道规则计算得到的新特征后，模型预测准确率提升至83.83%。

关键词: 智能车辆, 换道行为决策, 支持向量机, 贝叶斯优化, 融合建模

Abstract: The autonomous lane-changing system is one of the important research directions of vehicle intelligence at present and lane-changing decision plays a decisive role for the success of lane-changing manoeuvre. An enabling lane-changing decision model is proposed by combing rule abstraction and machine learning model for lane-changing on structured roads. Considering the multi-parameter and nonlinear properties of the lane-changing decision-making process, a lane-changing decision model is first developed based on the support vector machine, and the Bayesian optimization algorithm is introduced to determine its optimal parameters. Then the major influencing factors of the lane-changing decision-making are analysed including the necessity, safety and benefit. These factors are added as the new features into the training datasets so that each original training sample is augmented to improve the training effect. Finally, the prediction accuracy of the developed model is examined based on the NGSIM data. The results show that the prediction accuracies of the trained lane-changing decision models based on the augmented and non-augmented training datasets are 84.22% and 77.19%, respectively. This verifies the effectiveness of the proposed lane-changing decision model and its augmented training method.

Key words: intelligent vehicles, lane-changing decision, support vector machine, Bayesian optimization, fusion modeling

中图分类号:

TP216

贾寒冰, 刘鹏, 张雷, 王震坡. 基于规则与机器学习融合的换道决策建模方法研究[J]. 机械工程学报, 2022, 58(4): 212-221.

JIA Hanbing, LIU Peng, ZHANG Lei, WANG Zhenpo. Lane-changing Decision Model Development by Combining Rules Abstract and Machine Learning Technique[J]. Journal of Mechanical Engineering, 2022, 58(4): 212-221.

参考文献

[1] LIU Xiao,LIANG Jun,XU Bing. A deep learning method for lane changing situation assessment and decision making[J]. IEEE Access,2019:7:133749-133759.
[2] WANG Mingqiang,WANG Zhenpo,ZHANG Lei,et al. Speed planning for autonomous driving in dynamic urban driving scenarios[C/CD]//2020 IEEE Energy Conversion Congress and Exposition (ECCE),IEEE,2020.
[3] 王慧然,王其东,陈无畏,等.基于车辆行驶安全边界的换道控制[J].机械工程学报,2020,56(18):143-153. WANG Huiran,WANG Qidong,CHEN Wuwei,et al. Lane change control based on vehicle driving safe boundary[J]. Journal of Mechanical Engineering,2020,56(18):143-153.
[4] 章仁燮,熊璐,余卓平,等.基于条件积分算法的无人驾驶车辆轨迹跟踪鲁棒控制方法[J].机械工程学报,2018,54(18):129-139. ZHANG Renxie,XIONG Lu,YU Zhuoping,et al. Robust trajectory tracking control of autonomous vehicles based on conditional integration method[J]. Journal of Mechanical Engineering,2018,54(18):129-139.
[5] GIPPS P G. A model for the structure of lanechanging decisions[J]. Transportation Research,Part B (Methodological),1986,20(5):403-414.
[6] KESTING A,TREIBER M,HELBING D,General lane-changing model MOBIL for car-following models[J]. Transp. Res. Rec.,1999(1):86-94.
[7] 陈慧,王洁新.基于驾驶人不满度的高速公路自动驾驶换道决策[J].中国公路学报,2019,32(12):1-9. CHEN Hui,WANG Jiexin. A decision-making method for lane change of automated vehicles on freeways based on driver's dissatisfaction[J]. China Journal of Highway and Transport,2019,32(12):1-9.
[8] JIN Chengjie,KNOOP V L,LI Dawei. Discretionary lane-changing behavior:Empirical validation for one realistic rule-based model[J]. Transportmetrica A:Transport Science,2018,15(2):244-262.
[9] AHMED K I. Modeling drivers'acceleration and lane changing behavior[D]. Cambridge:Massachusetts Institute of Technology,1999.
[10] SUN D,ELEFTERIADOU L. A driver behavior-based lane-changing model for urban arterial streets[J]. Transportation Science,2014,48(2):184-205.
[11] CHRISTINA N,SUSILAWATI S,MD A,et al. Development of a binary logistic lane change model and its validation using empirical freeway data[J]. Transportmetrica B:Transport Dynamics,2020,8(1):49-71.
[12] XIE Dongfan,FANG Zhezhe,JIA Bin,et al. A data-driven lane-changing model based on deep learning[J]. Transportation Research Part C Emerging Technologies,2019,106:41-60.
[13] 徐兵,刘潇,汪子扬,等.采用梯度提升决策树的车辆换道融合决策模型[J].浙江大学学报,2019,53(6):1171-1181. XU Bing,LIU Xiao,WANG Ziyang,et al. Fusion decision model for vehicle lane change with gradient boosting decision tree[J]. Journal of Zhejiang University,2019,53(6):1171-1181.
[14] GU Xinping,HAN Yunpeng,YU Junfu. A novel lane-changing decision model for autonomous vehicles based on deep autoencoder network and XGBoost[J]. IEEE Access,2020,8(99):9846-9863.
[15] HOU Yi,EDARA P,SUN C. Modeling mandatory lane changing using bayes classifier and decision trees[J]. IEEE Transactions on Intelligent Transportation Systems,2014,15(2):647-655.
[16] LIU Meiyu,SHI Jing. A cellular automata traffic flow model combined with a BP neural network based microscopic lane changing decision model[J]. Journal of Intelligent Transportation Systems,2018:1-34.
[17] VALLON C,ERCAN Z,CARVALHO A,et al. A machine learning approach for personalized autonomous lane change initiation and control[C]//2017 IEEE Intelligent Vehicles Symposium (IV),IEEE 2017.
[18] ZHANG Junyou,LIAO Yaping,WANG Shufeng,et al.Study on driving decision-making mechanism of autonomous vehicle based on an optimized support vector machine regression[J]. Applied Sciences,2018,8(1):13.
[19] 谷新平,韩云鹏,于俊甫.基于决策机理与支持向量机的车辆换道决策模型[J].哈尔滨工业大学学报,2020,52(7):117-127. GU Xinping,HAN Yunpeng,YU Junfu. Vehicle lane-changing decision model based on decision mechanism and support vector machine[J]. Journal of Harbin Institute of Technology,2020,52(7):117-127.
[20] LIU Yonggang,WANG Xiao,LI Liang,et al. A novel lane change decision-making model of autonomous vehicle based on support vector machine[J]. IEEE Access,2019:26543-26550.
[21] WANG E G,SUN Jian,JIANG Shun,et al. Modeling the various merging behaviors at expressway on-ramp bottlenecks using support vector machine models[J]. Transportation Research Procedia,2017,25:1327-1341.
[22] DOU Yangliu,YAN Fengjun,FENG Daiwei. Lane changing prediction at highway lane drops using support vector machine and artificial neural network classifiers[C]//2016 IEEE International Conference on Advanced Intelligent Mechatronics (AIM). IEEE,2016.
[23] 戴望州.一阶逻辑领域知识与机器学习的结合研究[D].南京:南京大学,2019. DAI Wangzhou. Research on integrating first-order logical domain knowledge with machine learning[D]. Nanjing:Nanjing University,2019.

基于规则与机器学习融合的换道决策建模方法研究

Lane-changing Decision Model Development by Combining Rules Abstract and Machine Learning Technique

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	关海杰, 王博洋, 龚建伟, 陈慧岩. 面向异构车辆的统一运动规划方法[J]. 机械工程学报, 2024, 60(18): 288-298.
[2]	褚端峰, 彭赛骞, 胡海洋, 皮大伟. 预见性驾驶风险场模型[J]. 机械工程学报, 2024, 60(10): 160-170.
[3]	赵林峰, 丰肖, 方婷, 王宁, 陈无畏, 王慧然. 基于前车轨迹预测的智能车辆高速主动避撞方法[J]. 机械工程学报, 2024, 60(10): 289-301.
[4]	林亮行, 马国政, 孙建芳, 韩翠红, 雍青松, 苏峰华, 王海斗. 基于VMD-EEMD-LSTM的涂层型关节轴承剩余使用寿命预测方法[J]. 机械工程学报, 2023, 59(9): 125-136.
[5]	李华, 朱一民, 马海军, 丁继波, 楚恬歆, 张文海. 基于最小二乘支持向量机的小电流接地系统早期故障识别算法研究[J]. 电气工程学报, 2023, 18(3): 297-306.
[6]	刘春蕾, 庞鹏飞, 石纹赫, 孔令号, 黄洵, 戚军. 非侵入式负荷动态识别方法的研究及工程应用[J]. 电气工程学报, 2023, 18(3): 307-314.
[7]	陈诺, 吕干云, 叶加星. 基于SVM级联决策树的复合电能质量扰动识别^*[J]. 电气工程学报, 2023, 18(2): 149-156.
[8]	郭锐, 张印浩, 牛雯雯, 骆雄帅, 蔡伟, 王建伟, 王岳峰, 赵静一. 基于GLCT及CPA-SVM的变转速齿轮泵健康状态分类研究[J]. 机械工程学报, 2023, 59(14): 310-319.
[9]	周策, 白斌, 叶楠. 自适应粒子群优化支持向量回归的工程系统可靠性预测[J]. 机械工程学报, 2023, 59(14): 328-338.
[10]	周凯, 曹林, 胡志坚, 严利雄, 毕如玉, 邓科, 李煜磊. 基于决策树和支持向量机的智能变电站二次系统防误方法^*[J]. 电气工程学报, 2023, 18(1): 118-125.
[11]	吴西涛, 魏超, 翟建坤, 苑士华. 考虑横摆稳定性的无人车轨迹跟踪控制优化研究[J]. 机械工程学报, 2022, 58(6): 130-142.
[12]	徐彬翔, 郑林锋, 黄乙恒, 肖志能, 王新月. 基于改进最小二乘支持向量机的锂离子电池健康状态快速估计方法^*[J]. 电气工程学报, 2022, 17(4): 11-19.
[13]	曾德政, 吕继亮, 屈盛官, 尹鹏, 李小强. 基于SVMBP的下肢外骨骼步态检测及识别研究[J]. 机械工程学报, 2022, 58(12): 29-38.
[14]	宋立业, 范抑伶, 王燚增. 基于KPCA与IHHO-LSSVM的电力变压器故障诊断方法研究^*[J]. 电气工程学报, 2022, 17(1): 95-103.
[15]	刘检华, 黄浩, 金鹏, 刘少丽. 基于自适应基元的导管测量方法[J]. 机械工程学报, 2021, 57(22): 71-79.