Please wait a minute...
浙江大学学报(工学版)  2024, Vol. 58 Issue (7): 1377-1386    DOI: 10.3785/j.issn.1008-973X.2024.07.007
交通工程、土木工程     
考虑驾驶风格的车辆避障控制系统
李攀1(),周兵1,柴天1,*(),邓园2,潘倩兮1,吴晓建3
1. 湖南大学 整车先进设计制造技术全国重点实验室,湖南 长沙 410082
2. 舍弗勒智能驾驶科技(长沙)有限公司,湖南 长沙 410036
3. 南昌大学 先进制造学院,江西 南昌 330031
Vehicle obstacle avoidance control system considering driving style
Pan LI1(),Bing ZHOU1,Tian CHAI1,*(),Yuan DENG2,Qianxi PAN1,Xiaojian WU3
1. State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, Hunan University, Changsha 410082, China
2. Schaeffler Intelligent Driving Technology (Changsha) Limited Company, Changsha 410036, China
3. School of Advanced Manufacturing, Nanchang University, Nanchang 330031, China
 全文: PDF(3687 KB)   HTML
摘要:

传统避障控制系统设计未考虑不同驾驶员的偏好,导致驾驶员对系统的接受度不高,为此提出融入驾驶风格量化的避障控制系统. 采集多名熟练驾驶员的驾驶数据进行风格聚类,训练出基于支持向量机的分类器,实现对驾驶风格的在线识别. 设计考虑驾驶风格的避障控制系统,将避障过程分为转向避障和恢复稳定2个阶段. 在转向避障阶段,控制器通过跟踪相应驾驶风格对应的最大侧向加速度进行避障;在恢复稳定阶段,控制器控制车辆进行相邻车道中心线跟踪. 综合考虑车辆的避障安全性和横摆稳定性,将直接横摆力矩控制子系统加入所提系统. 构建系统仿真模型,分析不同驾驶风格下控制器避障操作和车辆状态响应的异同. 开展驾驶员主观感受的问卷调查,结果表明,相较于传统避障控制系统,驾驶员对所提系统的接受度提升了16.58%.

关键词: 驾驶风格机器学习转向避障横向控制主观评价    
Abstract:

An obstacle avoidance control system integrating the quantified driving style was proposed to resolve the problem that the traditional obstacle avoidance control system did not consider the preferences of different drivers, leading to low acceptance of the system by drivers. Firstly, the driving data from several skilled drivers were acquired for style clustering, and a classifier based on support vector machine was obtained to realize the online recognition of driving styles. Then, the obstacle avoidance control system considering driving style was designed, dividing the obstacle avoidance process into an obstacle avoidance by steering stage and a stability restoration stage. In the obstacle avoidance by steering stage, the controller avoided obstacles by tracking the maximum lateral acceleration of the corresponding driving style. In the stability restoration stage, the controller controlled the vehicle to track the center line of the adjacent lane. Moreover, in the whole obstacle avoidance process, a direct yaw-moment control subsystem was added considering the obstacle avoidance safety and yaw stability of the vehicle. Finally, a simulation model of the system was established to analyse the similarities and differences of the obstacle avoidance operation and the vehicle state response under different driving styles. A survey of drivers’ subjective feelings was conducted, and the results showed that drivers’ acceptance of the proposed system increased by 16.58% compared to the traditional obstacle avoidance system.

Key words: driving style    machine learning    obstacle avoidance by steering    lateral control    subjective evaluation
收稿日期: 2023-11-09 出版日期: 2024-07-01
CLC:  U 463.1  
基金资助: 国家自然科学基金资助项目(52002163, 52262054, 52202466);湖南省自然科学基金资助项目(2022JJ40059);湖南大学整车先进设计制造技术全国重点实验室开放基金资助项目(32065008).
通讯作者: 柴天     E-mail: lipan921@hnu.edu.cn;chaitian@hnu.edu.cn
作者简介: 李攀(1998—),男,硕士生,从事车辆动力学与控制研究. orcid.org/0009-0000-2324-740X. E-mail:lipan921@hnu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
李攀
周兵
柴天
邓园
潘倩兮
吴晓建

引用本文:

李攀,周兵,柴天,邓园,潘倩兮,吴晓建. 考虑驾驶风格的车辆避障控制系统[J]. 浙江大学学报(工学版), 2024, 58(7): 1377-1386.

Pan LI,Bing ZHOU,Tian CHAI,Yuan DENG,Qianxi PAN,Xiaojian WU. Vehicle obstacle avoidance control system considering driving style. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1377-1386.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2024.07.007        https://www.zjujournals.com/eng/CN/Y2024/V58/I7/1377

图 1  八自由度车辆模型
图 2  驾驶模拟器组成
图 3  不同聚类数量下的数据畸变程度
图 4  驾驶风格聚类结果
图 5  不同驾驶风格的主要特征参数对比图
分类模型Acc/%F1/%AUC/%
最近邻88.0488.0596.75
逻辑回归90.0189.9498.70
决策树88.8088.9591.60
梯度提升94.0794.1699.30
自适应增强75.5273.2486.76
随机森林93.6393.7199.40
高斯朴素贝叶斯64.6565.4383.92
线性判别分析88.0487.8197.97
二次判别分析84.9685.1695.74
支持向量机94.4094.3299.40
表 1  各驾驶风格分类算法结果
图 6  支持向量机分类器测试集混淆矩阵
图 7  避障控制流程
图 8  避障控制系统的整体结构
图 9  避障安全约束示意图
图 10  不同避障算法的避障轨迹对比图(vx =20 m/s)
图 11  不同避障算法的前轮转角对比图(vx =20 m/s)
图 12  不同避障算法的侧向加速度对比图(vx =20 m/s)
图 13  不同避障算法的避障轨迹对比图(vx =24 m/s)
图 14  不同避障算法的前轮转角对比图(vx =24 m/s)
图 15  不同避障算法的侧向加速度对比图(vx=24 m/s)
图 16  激进型驾驶风格避障时的轮胎使用率
图 17  不同避障算法的主观评价得分对比
1 CUI Q, DING R, WU X, et al A new strategy for rear-end collision avoidance via autonomous steering and differential braking in highway driving[J]. Vehicle System Dynamics, 2020, 58 (6): 955- 986
doi: 10.1080/00423114.2019.1602732
2 ZONG X, XU G, YU G, et al Obstacle avoidance for self-driving vehicle with reinforcement learning[J]. SAE International Journal of Passenger Cars-Electronic and Electrical Systems, 2018, 11 (1): 30- 39
3 房亮, 关志伟, 王涛, 等 基于深度学习 LSTM 的智能车辆避撞模型及验证[J]. 汽车安全与节能学报, 2022, 13 (1): 104- 111
FANG Liang, GUAN Zhiwei, WANG Tao, et al Collision avoidance model and its validation for intelligent vehicles based on deep learning LSTM[J]. Journal of Automotive Safety and Energy, 2022, 13 (1): 104- 111
4 WANG H, LIU B Path planning and path tracking for collision avoidance of autonomous ground vehicles[J]. IEEE Systems Journal, 2021, 16 (3): 3658- 3667
5 GUO J, LUO Y, LI K. Adaptive coordinated collision avoidance control of autonomous ground vehicles [J]. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering , 2018, 232(9): 1120–1133.
6 LEE K, KUM D Collision avoidance/mitigation system: motion planning of autonomous vehicle via predictive occupancy map[J]. IEEE Access, 2019, 7: 52846- 52857
doi: 10.1109/ACCESS.2019.2912067
7 BRÜCK Y, NIERMANN D, TRENDE A, et al. Investigation of personality traits and driving styles for individualization of autonomous vehicles [C]// International Conference on Intelligent Human Systems Integration . Palermo: Springer, 2021: 78–83.
8 MA Z, ZHANG Y Drivers trust, acceptance, and takeover behaviors in fully automated vehicles: effects of automated driving styles and driver’s driving styles[J]. Accident Analysis and Prevention, 2021, 159: 106238
doi: 10.1016/j.aap.2021.106238
9 NAVON–EYAL M, TAUBMAN–BEN-ARI O Can emotion regulation explain the association between age and driving styles?[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2020, 74: 439- 445
doi: 10.1016/j.trf.2020.09.008
10 FAN X, PAN G, MAO Y, et al Investigating the effect of personality on left-turn behaviors in various scenarios to understand the dynamics of driving styles[J]. Traffic Injury Prevention, 2019, 20 (8): 801- 806
doi: 10.1080/15389588.2019.1673893
11 SUN B, DENG W, WU J, et al An intention-aware and online driving style estimation based personalized autonomous driving strategy[J]. International Journal of Automotive Technology, 2020, 21: 1431- 1446
doi: 10.1007/s12239-020-0135-3
12 LI H, WU C, CHU D, et al Combined trajectory planning and tracking for autonomous vehicle considering driving styles[J]. IEEE Access, 2021, 9: 9453- 9463
doi: 10.1109/ACCESS.2021.3050005
13 董俊一. 考虑驾驶风格的智能驾驶换道决策模型研究[D]. 长春: 吉林大学, 2022.
DONG Junyi. Research on lane changing decision model for the intelligent vehicle considering driving style [D]. Changchun: Jilin University, 2022.
14 LI G, YANG Y, ZHANG T, et al Risk assessment based collision avoidance decision-making for autonomous vehicles in multi-scenarios[J]. Transportation Research Part C: Emerging Technologies, 2021, 122: 102820
doi: 10.1016/j.trc.2020.102820
15 崔庆佳. 面向高速紧急工况的车辆避撞多目标协调控制研究[D]. 长沙: 湖南大学, 2020.
CUI Qingjia. Research on multi-objective coordinated control strategies for vehicle collision-avoidance in highway driving [D]. Changsha: Hunan University, 2020.
16 PACEJKA H B, BAKKER E The magic formula tyre model[J]. Vehicle System Dynamics, 1992, 21 (Suppl.1): 1- 18
17 EBOLI L, MAZZULLA G, PUNGILLO G The influence of physical and emotional factors on driving style of car drivers: a survey design[J]. Travel Behaviour and Society, 2017, 7: 43- 51
doi: 10.1016/j.tbs.2017.02.001
18 蓟仲勋. 考虑驾驶员风格的车辆换道轨迹规划及跟踪控制研究[D]. 长沙: 湖南大学, 2019.
JI Zhongxun. Research of vehicle lane-changing trajectory planning and tracking control considering driving style [D]. Changsha: Hunan University, 2019.
19 中华人民共和国公安部交通管理局. 2021年全国机动车保有量达3.95亿 新能源汽车同比增59.25%. (2022-01-11)[2023-03-23]. https://www.mps.gov.cn/n2254314/n6409334/c8322353/content.html.
20 ZHU B, YAN S, ZHAO J, et al Personalized lane-change assistance system with driver behavior identification[J]. IEEE Transactions on Vehicular Technology, 2018, 67 (11): 10293- 10306
doi: 10.1109/TVT.2018.2867541
21 DENG Z, CHU D, WU C, et al. A probabilistic model for driving-style-recognition-enabled driver steering behaviors [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2022, 52(3): 1838–1851.
22 SAGBERG F, SELPI, BIANCHI PICCININI G F, et al A review of research on driving styles and road safety[J]. Human Factors, 2015, 57 (7): 1248- 1275
doi: 10.1177/0018720815591313
23 马依宁, 姜为, 吴靖宇, 等 基于不同风格行驶模型的自动驾驶仿真测试自演绎场景研究[J]. 中国公路学报, 2023, 36 (2): 216- 228
MA Yining, JIANG Wei, WU Jingyu, et al Self-evolution scenarios for simulation tests of autonomous vehicles based on different models of driving styles[J]. China Journal of Highway and Transport, 2023, 36 (2): 216- 228
24 马跃, 郭烈, 秦增科, 等 考虑驾驶风格的路径跟踪控制方法[J]. 重庆理工大学学报: 自然科学, 2022, 36 (11): 20- 30
MA Yue, GUO Lie, QIN Zengke, et al Path tracking control method considering driving styles[J]. Journal of Chongqing University of Technology: Natural Science, 2022, 36 (11): 20- 30
25 SILVA I, EUGENIO NARANJO J A systematic methodology to evaluate prediction models for driving style classification[J]. Sensors, 2020, 20 (6): 1692
doi: 10.3390/s20061692
26 李升波, 王建强, 李克强 软约束线性模型预测控制系统的稳定性方法[J]. 清华大学学报: 自然科学版, 2010, 50 (11): 1848- 1852
LI Shengbo, WANG Jianqiang, LI Keqiang Stabilization of linear predictive control systems with softening constraints[J]. Journal of Tsinghua University: Science and Technology, 2010, 50 (11): 1848- 1852
27 NILSSON J, FALCONE P, ALI M, et al Receding horizon maneuver generation for automated highway driving[J]. Control Engineering Practice, 2015, 41: 124- 133
doi: 10.1016/j.conengprac.2015.04.006
28 CUI Q, DING R, WEI C, et al A hierarchical framework of emergency collision avoidance amid surrounding vehicles in highway driving[J]. Control Engineering Practice, 2021, 109: 104751
doi: 10.1016/j.conengprac.2021.104751
29 DING S, LIU L, ZHENG W X Sliding mode direct yaw-moment control design for in-wheel electric vehicles[J]. IEEE Transactions on Industrial Electronics, 2017, 64 (8): 6752- 6762
doi: 10.1109/TIE.2017.2682024
[1] 霍育福,金蓓弘,廖肇翊. 多模态信息增强的短视频推荐模型[J]. 浙江大学学报(工学版), 2024, 58(6): 1142-1152.
[2] 李素,陈泽,宋宝燕,张浩林. 营商环境评估的企业级复合区块链构建方法[J]. 浙江大学学报(工学版), 2024, 58(5): 891-899.
[3] 黄龙森,房俊,周云亮,郭志城. 基于变分自编码器的近似聚合查询优化方法[J]. 浙江大学学报(工学版), 2024, 58(5): 931-940.
[4] 高一聪,王彦坤,费少梅,林琼. 基于迁移学习的机械制图智能评阅方法[J]. 浙江大学学报(工学版), 2022, 56(5): 856-863, 889.
[5] 张鹏,田子都,王浩. 基于改进生成对抗网络的飞参数据异常检测方法[J]. 浙江大学学报(工学版), 2022, 56(10): 1967-1976.
[6] 黄发明,潘李含,姚池,周创兵,姜清辉,常志璐. 基于半监督机器学习的滑坡易发性预测建模[J]. 浙江大学学报(工学版), 2021, 55(9): 1705-1713.
[7] 任嘉豪,王海鸥,邢江宽,罗坤,樊建人. 湍流火焰切向应变率的低维近似模型[J]. 浙江大学学报(工学版), 2021, 55(6): 1128-1134.
[8] 战友,李强,马啸天,王郴平,邱延峻. 基于宏微观纹理特征融合的路面摩擦性能预测[J]. 浙江大学学报(工学版), 2021, 55(4): 684-694.
[9] 于勇,薛静远,戴晟,鲍强伟,赵罡. 机加零件质量预测与工艺参数优化方法[J]. 浙江大学学报(工学版), 2021, 55(3): 441-447.
[10] 陈巧红,陈翊,李文书,贾宇波. 多尺度SE-Xception服装图像分类[J]. 浙江大学学报(工学版), 2020, 54(9): 1727-1735.
[11] 王慧芳,张晨宇. 采用极限梯度提升算法的电力系统电压稳定裕度预测[J]. 浙江大学学报(工学版), 2020, 54(3): 606-613.
[12] 谢乐,衡熙丹,刘洋,蒋启龙,刘东. 基于线性判别分析和分步机器学习的变压器故障诊断[J]. 浙江大学学报(工学版), 2020, 54(11): 2266-2272.
[13] 万志远,陶嘉恒,梁家坤,才振功,苌程,乔林,周巧妮. Stack Overflow上机器学习相关问题的大规模实证研究[J]. 浙江大学学报(工学版), 2019, 53(5): 819-828.
[14] 柯懂湘,潘丽敏,罗森林,张寒青. 基于随机森林算法的Android恶意行为识别与分类方法[J]. 浙江大学学报(工学版), 2019, 53(10): 2013-2023.
[15] 忽丽莎, 王素贞, 陈益强, 高晨龙, 胡春雨, 蒋鑫龙, 陈振宇, 高兴宇. 基于可穿戴设备的跌倒检测算法综述[J]. 浙江大学学报(工学版), 2018, 52(9): 1717-1728.