汽车工程 ›› 2024, Vol. 46 ›› Issue (11): 1993-2004.doi: 10.19562/j.chinasae.qcgc.2024.11.006
收稿日期:
2024-04-13
修回日期:
2024-05-26
出版日期:
2024-11-25
发布日期:
2024-11-22
通讯作者:
王建强
E-mail:wjqlws@tsinghua.edu.cn
基金资助:
Hailun Zhang,Guangwei Wang,Qingwen Meng,Qing Xu,Jianqiang Wang(),Keqiang Li
Received:
2024-04-13
Revised:
2024-05-26
Online:
2024-11-25
Published:
2024-11-22
Contact:
Jianqiang Wang
E-mail:wjqlws@tsinghua.edu.cn
摘要:
自动驾驶感知系统须对目标车辆运动进行感知,以制定合理交互决策。针对行为感知在时间上的滞后性和数据中可能存在的波动和异常值导致感知准确率差的问题,本文提出一种在线半监督混合方法。首先,采用自回归积分移动平均和在线梯度下降优化器设计基于数据驱动的车辆运动状态在线预测算法。然后,构建基于微簇的初始模型,并以K近邻为基分类器建立集成学习策略,设计错误驱动代表性学习和指数衰减策略实现对初始模型的迭代更新。最后,基于驾驶模拟平台采集了验证所提算法有效性的实验数据。结果表明,所提出的方法对于车辆行为波动具有快速适应性,在线预测算法可准确预测车辆运动趋势,行为感知算法对于不同预测时间下的车辆行为均有较强适应能力。
张海伦,王广玮,孟庆文,许庆,王建强,李克强. 交叉口车辆行为感知在线半监督混合方法[J]. 汽车工程, 2024, 46(11): 1993-2004.
Hailun Zhang,Guangwei Wang,Qingwen Meng,Qing Xu,Jianqiang Wang,Keqiang Li. An Online Semi-supervised Hybrid Approach for Vehicle Behavior Perception at Intersections[J]. Automotive Engineering, 2024, 46(11): 1993-2004.
表1
预测时间0.1 s时准确率对比"
算法 | TL/% | TR/% | GS/% | 平均准确率/% |
---|---|---|---|---|
SVM | 76.2±3.5 | 73.1±2.7 | 74.6±3.2 | 74.8±3.5 |
HMM | 72.5±2.9 | 69.7±2.7 | 70.1±2.4 | 71.7±3.8 |
HMM-BF | 80.4±4.5 | 78.6±3.7 | 78.4±2.4 | 79.2±5.7 |
NB | 78.2±3.3 | 77.2±3.5 | 76.4±4.1 | 77.5±4.5 |
K-NN | 76.6±2.5 | 72.5±3.2 | 73.4±6.2 | 75.0±1.5 |
LSTM-50 | 62.0±1.9 | 59.2±2.9 | 58.4±2.1 | 59.5±3.5 |
LSTM-int | 83.5±4.3 | 81.4±3.1 | 81.9±2.8 | 82.4±4.3 |
SSL-K-NN | 78.6±4.2 | 76.1±3.7 | 76.9±3.5 | 77.5±4.4 |
EL-SSL-10 | 84.1±4.2 | 79.4±5.7 | 82.1±4.6 | 81.2±5.7 |
EL-SSL-30 | 85.8±3.4 | 81.4±5.2 | 82.9±4.3 | 83.8±1.4 |
EL-SSL-50 | 86.8±5.3 | 84.5±2.8 | 85.1±2.7 | 85.9±3.4 |
表2
预测时间0.5 s时准确率对比"
算法 | TL/% | TR/% | GS/% | 平均准确率/% |
---|---|---|---|---|
SVM | 85.7±2.4 | 79.3±2.1 | 80.9±3.2 | 82.1±3.6 |
HMM | 78.8±3.1 | 76.0±3.2 | 75.4±3.2 | 76.8±4.8 |
HMM-BF | 85.5±4.7 | 83.2±4.3 | 82.4±2.4 | 84.1±3.6 |
NB | 85.1±3.1 | 84.4±3.0 | 84.0±3.2 | 84.9±4.0 |
K-NN | 86.0±3.3 | 85.7±3.5 | 84.2±2.1 | 84.9±1.8 |
LSTM-50 | 63.4±5.2 | 61.4±2.7 | 64.1±4.1 | 63.2±2.9 |
LSTM-int | 89.9±2.9 | 87.4±2.7 | 88.0±3.0 | 88.9±2.4 |
SSL-K-NN | 87.3±1.5 | 83.5±1.7 | 83.4±3.6 | 84.9±2.8 |
EL-SSL-10 | 91.2±4.6 | 86.3±3.2 | 86.9±2.2 | 88.6±2.1 |
EL-SSL-30 | 93.2±3.5 | 88.9±4.5 | 89.1±3.6 | 91.2±2.5 |
EL-OSS-50 | 93.9±1.2 | 91.0±2.5 | 90.1±1.1 | 92.1±2.9 |
表3
预测时间1 s时准确率对比"
算法 | TL/% | TR/% | GS/% | 平均准确率/% |
---|---|---|---|---|
SVM | 88.2±2.1 | 86.2±1.9 | 86.0±1.8 | 87.1±4.2 |
HMM | 84.3±2.2 | 82.5±4.1 | 81.3±4.4 | 83.8±3.5 |
HMM-BF | 88.3±2.5 | 86.7±3.2 | 87.4±3.4 | 87.8±3.1 |
NB | 88.1±4.3 | 87.6±4.5 | 86.9±1.5 | 87.5±2.3 |
K-NN | 88.9±2.5 | 87.6±1.7 | 87.7±1.9 | 88.5±3.9 |
LSTM-50 | 71.5±6.1 | 70.2±3.5 | 69.8±4.7 | 69.8±4.5 |
LSTM-int | 94.9±3.2 | 93.4±1.5 | 93.0±3.2 | 94.3±5.1 |
SSL-K-NN | 93.4±2.0 | 90.9±3.8 | 92.7±5.2 | 92.3±3.2 |
EL-SSL-10 | 94.0±2.0 | 92.2±2.5 | 93.1±2.5 | 93.6±2.5 |
EL-SSL-30 | 96.2±2.4 | 93.5±1.9 | 95.1±1.5 | 94.9±1.1 |
EL-SSL-50 | 97.0±2.2 | 94.1±3.5 | 94.8±1.6 | 95.6±2.1 |
1 | FENG S, SUN H, YAN X, et al. Dense reinforcement learning for safety validation of autonomous vehicles[J]. Nature, 2023, 615(7953): 620-627. |
2 | SCHNEIDER J, MEADOWS G, MATHISON S R, et al. Validation and sensitivity studies for SAE J2601, the light duty vehicle hydrogen fueling standard[J]. SAE International Journal of Alternative Powertrains, 2014, 3(2): 257-309. |
3 | 田彦涛, 赵凤凯, 聂光明. 考虑驾驶习惯的驾驶员换道意图识别 [J/OL]. 吉林大学学报(工学版), 2020: 1-9. |
TIAN Y T, ZHAO F K, NIE G M. Driver's lane change intention recognition considering driving habits [J/OL]. Journal of Jilin University (Engineering and Technology Edition), 2020: 1-9. | |
4 | 刘通, 付锐, 马勇, 等. 考虑驾驶人风格的跟车预警规则研究 [J]. 中国公路学报, 2020, 33(2): 170-180. |
LIU T, FU R, MA Y, et al. Car-following warning rules considering driving styles [J]. China Journal of Highway and Transport, 2020, 33(2): 170-180. | |
5 | LI Y, LIU F, XING L, et al. A deep learning framework to explore influences of data noises on lane-changing intention prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2024. |
6 | 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. | |
7 | 郭景华, 李克强, 王进, 等. 基于危险场景聚类分析的前车随机运动状态预测研究 [J]. 汽车工程, 2020, 42(7): 847-853,859. |
GUO J H, LI K Q, WANG J, et al. Study on prediction of preceding vehicle's stochastic motion based on risk scenarios clustering analysis [J]. Automotive Engineering, 2020, 42(7): 847-853,859. | |
8 | 付锐, 张海伦, 刘文晓, 等. 驾驶人意图识别综述[J].长安大学学报(自然科学版),2022,42(1): 33-60. |
FU R, ZHANG H L, LIU W X, et al. Review on driver intention recognition [J]. Journal of Chang’an University (Natural Science Edition), 2022,42(1): 33-60. | |
9 | 张海伦, 付锐, 袁伟, 等. 面向前车的驾驶行为感知与意图识别算法研究 [J]. 中国公路学报, 2022, 35 (6): 299-311. |
ZHANG H L, FU R, YUAN W, et al. Research on algorithms of driving behavior perception and intention recognition oriented to the vehicle front [J]. China Journal of Highway and Transport, 2022, 35 (6): 299-311. | |
10 | BOCKLISCH F, BOCKLISCH S F, BEGGIATO M, et al. Adaptive fuzzy pattern classification for the online detection of driver lane change intention[J]. Neurocomputing, 2017, 262: 148-158. |
11 | ZHANG M, FU R, MORRIS D D, et al. A framework for turning behavior classification at intersections using 3D LIDAR[J]. IEEE Transactions on Vehicular Technology, 2019, 68(8): 7431-7442. |
12 | ZYNER A, WORRALL S, NEBOT E. Naturalistic driver intention and path prediction using recurrent neural networks[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(4): 1584-1594. |
13 | LEFÈVRE S, VASQUEZ D, LAUGIER C. A survey on motion prediction and risk assessment for intelligent vehicles[J]. ROBOMECH Journal, 2014, 1(1): 1-14. |
14 | ZHANG H, FU R, WANG C, et al. Turning maneuver prediction of connected vehicles at signalized intersections: a dictionary learning-based approach[J]. IEEE Internet of Things Journal, 2022, 9(22): 23142-23159. |
15 | 张一鸣, 周兵, 吴晓建, 等. 基于前车轨迹预测的高速智能车运动规划 [J]. 汽车工程, 2020, 42(5): 574-580,587. |
ZHANG Y M, ZHOU B, WU X J, et al. Motion planning of high-speed intelligent vehicle based on front vehicle trajectory prediction [J]. Automotive Engineering, 2020, 42(5): 574-580,587. | |
16 | TOLEDO-MOREO R, ZAMORA-IZQUIERDO M A. IMM-based lane-change prediction in highways with low-cost GPS/INS[J]. IEEE Transactions on Intelligent Transportation Systems, 2009, 10(1): 180-185. |
17 | WU C, PENG L, HUANG Z, et al. A method of vehicle motion prediction and collision risk assessment with a simulated vehicular cyber physical system [J]. Transportation Research Part C: Emerging Technologies, 2014, 47:179-191. |
18 | 谢枫, 娄静涛, 赵凯, 等. 基于行为识别和曲率约束的车辆轨迹预测方法研究 [J]. 汽车工程, 2019, 41(9): 1036-1042. |
XIE L, LOU J T, ZHAO K, et al. A research on vehicle trajectory prediction method based on behavior recognition and curvature constraints [J]. Automotive Engineering, 2019, 41(9): 1036-1042. | |
19 | 刘创, 梁军. 基于注意力机制的车辆运动轨迹预测 [J]. 浙江大学学报(工学版), 2020, 54(6): 1156-1163. |
LIU C, LIANG J. Vehicle motion trajectory prediction based on attention mechanism [J]. Journal of Zhejiang University (Engineering Science), 2020, 54(6): 1156-1163. | |
20 | 张涛, 邹渊, 张旭东, 等. 网联车辆并线预测与巡航控制的研究 [J]. 汽车工程, 2020, 42(2): 250-256. |
ZHANG T, ZHOU Y, ZHANG X D, et al. Research on merging prediction and cruise control for connected vehicles [J]. Automotive Engineering, 2020, 42(2): 250-256. | |
21 | SUN J, QI X, XU Y, et al. Vehicle turning behavior modeling at conflicting areas of mixed-flow intersections based on deep learning [J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3674-3685. |
22 | XING Y, LV C, CAO D. Personalized vehicle trajectory prediction based on joint time-series modeling for connected vehicles [J]. IEEE Transactions on Vehicular Technology, 2020, 69(2): 1341-1352. |
23 | ZHANG M, FU R, MORRIS D D, et al. A framework for turning behavior classification at intersections using 3D LIDAR [J]. IEEE Transactions on Vehicular Technology, 2019, 68(8): 7431-7442. |
24 | GADEPALLY V, KRISHNAMURTHY A, OZGUNER U. A framework for estimating driver decisions near intersections [J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(2): 637-646. |
25 | 易丹辉, 王燕. 应用时间序列分析 [M]. 5版.北京:中国人民大学出版社, 2019. |
YI D H, WANG Y. Applied time series analysis[M]. 5 th ed. Beijing: China Renmin University Press, 2019. | |
26 | HAZAN E, AGARWAL A, KALE S. Logarithmic regret algorithms for online convex optimization[J]. Machine Learning, 2007, 69(2-3): 169-192. |
27 | ZINKEVICH M. Online convex programming and generalized infinitesimal gradient ascent [C]. Proceedings of the 20th International Conference on Machine Learning (ICML-03),2003: 928-936. |
28 | ANAVA O, HAZAN E, MANNOR S, et al. Online learning for time series prediction[C].Conference on Learning Theory, 2013: 172-184. |
29 | SHAO J, TAN Y, GAO L, et al. Synchronization-based clustering on evolving data stream [J]. Information Sciences, 2019, 501: 573-587. |
[1] | 李道飞,潘豪. 场景复杂度评估在轨迹预测和驾驶决策中的应用[J]. 汽车工程, 2024, 46(9): 1556-1563. |
[2] | 朱冰,范天昕,赵健,张培兴,宋东鉴,薛越,赵文博. 自动驾驶拟人连续交互测试场景生成方法[J]. 汽车工程, 2024, 46(9): 1600-1607. |
[3] | 张国娟,胡宏宇,李浩淼,王明剑,高菲,高镇海. 自动驾驶车辆乘坐舒适性评价研究综述[J]. 汽车工程, 2024, 46(9): 1617-1627. |
[4] | 张佳楠,胡钊政,孟杰,胡华桦,左洁. 面向车-路-图协同的分布式自动驾驶仿真平台架构及应用[J]. 汽车工程, 2024, 46(8): 1335-1345. |
[5] | 颜伏伍,向博文,胡杰,陈锐鹏,张志豪,刘昊岩,高宠智. 基于改进LPV模型的自动驾驶轻型货车横向控制[J]. 汽车工程, 2024, 46(8): 1403-1413. |
[6] | 陶乐,王海,蔡英凤,陈龙. 面向自动驾驶场景的多目标点云检测算法[J]. 汽车工程, 2024, 46(7): 1208-1218. |
[7] | 李琳辉,付一帆,王霆,王雪成,连静. 引入自监督预训练的轨迹预测方法[J]. 汽车工程, 2024, 46(7): 1219-1227. |
[8] | 王海,张桂荣,罗彤,邱梦,蔡英凤,陈龙. 面向自动驾驶道路场景中异常案例的多模态数据挖掘算法[J]. 汽车工程, 2024, 46(7): 1239-1248. |
[9] | 王海,丁玉轩,罗彤,邱梦,蔡英凤,陈龙. 驾驶场景下结合运动速度以及外观特征的多类多目标跟踪方法[J]. 汽车工程, 2024, 46(6): 956-964. |
[10] | 黄晶,刘祥臻,邓潇阳,陈然. 基于多模态轨迹预测的智能车轨迹规划研究[J]. 汽车工程, 2024, 46(6): 965-974. |
[11] | 王国栋,刘立,孟宇,杜海平,白国星,顾青. 自动驾驶汽车避撞极限研究[J]. 汽车工程, 2024, 46(6): 985-994. |
[12] | 姚福星,孙超,兰云港,卢兵,王博,于海洋. 基于混合专家模型的智能网联汽车换道决策方法[J]. 汽车工程, 2024, 46(5): 882-892. |
[13] | 李梦凡,冯忠祥,张卫华,李靖宇. 面向人机共驾模式下驾驶人接管过程的视觉转移特性研究[J]. 汽车工程, 2024, 46(5): 795-804. |
[14] | 杜国栋,邹渊,张旭东,孙文景,孙巍. 基于双估计强化学习结合前向预测控制的自动驾驶运动控制研究[J]. 汽车工程, 2024, 46(4): 564-576. |
[15] | 丁志杰,王亚飞,章翼辰,邬明宇,王亦乐. 基于复合动态采样的自动驾驶矿车节能路径规划方法[J]. 汽车工程, 2024, 46(4): 588-595. |
|