Trajectory Data-Driven Model for Vehicle Lane Change Intention Recognition

doi:10.12141/j.issn.1000-565X.230258

Abstract

Abstract:

In order to accurately recognize and estimate the lane-changing intentions of vehicles, a vehicle lane change intention recognition model based on TCN-LSTM network is proposed, which combines the temporal processing capability of TCN (Temporal Convolutional Network) with the gate memory mechanism of LSTM (Long Short Term Memory Network). In the investigation, firstly, the driving intentions of the target vehicle are divided into three types, namely going straight, changing lanes to the left, and changing lanes to the right. The running state indicators of the target vehicle and its surrounding neighboring vehicles (including the adjacent front and rear vehicles in the same lane, left lane and right lane) are extracted from the Citysim vehicle trajectory dataset using the median filtering algorithm. Secondly, to overcome the low recognition accuracy, long training time and slow parameter updating existing in statistical theories and traditional machine learning methods, the dilated convolution technique is used to extract the temporal features of time series, and the gate memory units are used to capture the long-term dependency relationships of temporal features. With 54 indicators, including the speed, acceleration, heading angle, heading angle change rate, and relative position information of the target vehicle and surrounding neighboring vehicles, as input parameters, and with the lane change intention of the vehicle as the output indicator, a vehicle lane -change intention recognition model based on the TCN-LSTM network is constructed. Finally, the recognition accuracy of TCN, SVM (Support Vector Machines), LSTM, and TCN-LSTM models under different input time steps are comparatively analyzed. The results show that, when the input time series length is 150 frames, the recognition accuracy of the TCN-LSTM model reaches a maximum of 96.67%; and that, in terms of overall classification accuracy, as compared with LSTM, TCN and SVM models, the TCN-LSTM model improves the classification correctness of lane change intention by 1.34, 0.84 and 2.46 percentage points, respectively, which demonstrates better classification performance.

Key words: transportation engineering, lane change intention, temporal convolutional network, long short term memory neural network, vehicle trajectory, CitySim dataset

CLC Number:

U461.91

YUAN Renteng, WANG Chenzhu, XIANG Qiaojun, et al. Trajectory Data-Driven Model for Vehicle Lane Change Intention Recognition[J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(6): 34-44.

Figures/Tables 15

Fig.1

Fig.2

Table 1

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Table 2

Fig.10

Fig.11

Fig.12

Table 3

References 30

1	CHEN T， SHI X， WONG Y D，et al ．Predicting lane-changing risk level based on vehicles’ space-series features：a pre-emptive learning approach［J］．Transportation Research Part C：Emerging Technologies，2020，116：102646/1-21．
2	HOU Y， EDARA P， SUN C ．Situation assessment and decision making for lane change assistance using ensemble learning methods［J］．Expert Systems with Applications，2015，42：3875-3882．
3	王亚伦．基于驾驶意图识别的人机共驾车道保持控制系统研究［D］．青岛：青岛大学，2022．
4	李亚秋，吴超仲，马晓凤，等．基于EKF学习方法的BP神经网络汽车换道意图识别模型研究［J］．武汉理工大学学报（交通科学与工程版），2013，37（4）：843-847．
	LI Yaqiu， WU Chaozhong， MA Xiaofeng，et al ．A recognition model for lane change intention based on neural network with EKF algorithm［J］．Journal of Wuhan University of Technology （Transportation Science & Engineering），2013，37（4）：843-847．
5	XU G， LIU L，OU Y ．Dynamic modeling of driver control strategy of lane-change behavior and trajectory planning for collision prediction［J］．IEEE Transactions on Intelligent Transportation Systems，2012，13（3）：1138-1155．
6	MCCALL J C， WIPF D P， TRIVEDI M M，et al ．Lane change intent analysis using robust operators and sparse Bayesian learning［J］．IEEE Transactions on Intelligent Transportation Systems，2007，8（3）：431-440．
7	LI K， WANG X， XU Y，et al ．Lane changing intention recognition based on speech recognition models［J］．Transportation Research Part C：Emerging Technologies，2016，69：497-514．
8	彭金栓，付锐，郭应时，等．基于驾驶人视觉特性的换道意图识别方法［J］．武汉理工大学学报，2013，35（3）：73-79．
	PENG Jin-shuan， FU Rui， GUO Ying-shi，et al ．Lane change intent identification based on drivers’ visual characteristics［J］．Journal of Wuhan University of Technology，2013，35（3）：73-79．
9	袁伟，付锐，郭应时，等．基于视觉特性的驾驶人换道意图识别［J］．中国公路学报，2013，26（4）：132-138．
	YUAN Wei， FU Rui， GUO Ying-shi，et al ．Drivers’ lane changing intention identification based on visual characteristics［J］．China Journal of Highway and Transport，2013，26（4）：132-138．
10	商艳，朱守林，戚春华．基于瞳孔变动视觉特征的驾驶人换道意图识别［J］．计算机仿真，2020，37（8）：77-81．
	SHANG Yan， ZHU Shou-lin， QI Chun-hua ．Driver lane change intention recognition based on pupil characteristics［J］．Computer Simulation，2020，37（8）：77-81．
11	彭金栓，付锐，邵毅明，等．基于Logistic模型的驾驶人换道意图识别方法［J］．科技导报，2014，32（14）：69-73．
	PENG Jinshuan， FU Rui， SHAO Yiming，et al ．Lane changing intent identification based on Logistic regression model［J］．Science & Technology Review，2014，32（14）：69-73．
12	宋晓琳，曾艳兵，曹昊天，等．基于长短期记忆网络的换道意图识别方法［J］．中国公路学报，2021，34（11）：236-245．
	SONG Xiao-lin， ZENG Yan-bing， CAO Hao-tian ．Lane change intention recognition method based on LSTM network［J］．China Journal of Highway and Transport，2021，34（11）：236-245．
13	方艺洁，廖祝华，黄浩楷，等．多模型融合的换道意图识别研究［J］．计算机工程与应用，2024，60（2）：344-352．
	FANG Yijie， LIAO Zhuhua， HUANG Haokai，et al ．Lane change intention recognition based on multi-model fusion［J］．Computer Engineering and Applications，2024，60（2）：344-352．
14	张海伦，付锐．高速场景相邻前车驾驶行为识别及意图预测［J］．交通运输系统工程与信息，2020，20（1）：40-46．
	ZHANG Hai-lun， FU Rui ．Driving behavior recognition and intention prediction of adjacent preceding vehicle in highway scene［J］．Journal of Transportation Systems Engineering and Information Technology，2020，20（1）：40-46．
15	张新锋，王万宝，柳欢，等．高速动态交通场景下自动驾驶车辆换道意图识别模型研究［J］．汽车技术，2023（4）：8-15．
	ZHANG Xinfeng， WANG Wanbao， LIU Huan，et al ．Research on lane change intention recognition model of automated vehicle in high-speed dynamic traffic scenario［J］．Automobile Technology，2023（4）：8-15．
16	卢辉遒，赵枫，谢波，等．冰雪环境下基于神经网络的驾驶人换道意图识别［J］．吉林大学学报（工学版），2023，53（1）：273-284．
	LU Huiqiu， ZHAO Feng， XIE Bo，et al ．Driver’s lane change intention recognition in snow and ice environment based on neural network［J］．Journal of Jilin University （Engineering and Technology Edition），2023，53（1）：273-284．
17	DANG R， ZHANG F， WANG J，et al ．Analysis of Chinese driver’s lane change characteristic based on real vehicle tests in highway［C］∥Proceedings of the 16th International IEEE Conference on Intelligent Transportation Systems （ITSC 2013）．The Hague：IEEE，2013：1917-1922．
18	KUMAR P， PERROLLAZ M， LEFEVRE S，et al ．Learning-based approach for online lane change intention prediction［C］∥Proceedings of the 2013 IEEE Intelligent Vehicles Symposium （Ⅳ）．Queensland：IEEE，2013：797-802．
19	GAO J， YI J， MURPHEY Y ．Joint learning of video images and physiological signals for lane-changing behavior prediction［J］．Transportmetrica A：Transport Science，2022，18（3）：1234-1253．
20	王亚伦，陈焕明，赵岩．基于条件随机场的驾驶意图识别研究［J］．青岛大学学报（工程技术版），2021，36（4）：88-94，114．
	WANG Yalun， CHEN Huanming， ZHAO YAN ．Research on driving intention recognition based on conditional random field［J］．Journal of Qingdao University （Engineering & Technology Edition），2021，36（4）：88-94，114．
21	杨志强，朱家伟，穆蕾，等．基于高斯混合隐马尔科夫模型的自由换道识别［J］．计算机系统应用，2022，31（8）：388-394．
	YANG Zhi-Qiang， ZHU Jia-Wei， MU Lei，et al ．Recognition of free lane change based on Gaussian mixture hidden Markov model［J］．Computer Systems & Applications，2022，31（8）：388-394．
22	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 Xue-wu， FEI Cong， HE Xiang-kun，et al ．Intention recognition and trajectory prediction for vehicles using LSTM network［J］．China Journal of Highway and Transport，2019，32（6）：34-42．
23	PARK M， JANG K， LEE J，et al ．Logistic regression model for discretionary lane changing under congested traffic［J］．Transportmetrica A：Transport Science，2015，11（4）：333-344．
24	KOENIG A， REHDER T， HOHMANN S ．Exact inference and learning in hybrid Bayesian Networks for lane change intention classification［C］∥Proceedings of the 2017 IEEE Intelligent Vehicles Symposium （Ⅳ）．Los Angeles：IEEE，2017：1535-1540．
25	陈亮，冯延超，李巧茹．基于Multi-class SVM的车辆换道行为识别模型研究［J］．安全与环境学报，2020，20（1）：193-199．
	CHEN Liang， FENG Yan-chao， LI Qiao-ru ．Probe into the multi-class SVM-based recognition model for the vehicle lane-altering behaviors［J］．Journal of Safety and Environment，2020，20（1）：193-199．
26	BAI S， KOLTER J Z， KOLTUN V ．An empirical evaluation of generic convolutional and recurrent networks for sequence modeling［C］∥Proceedings of the International Conference on Learning Representations （ICLR） Workshop．Vancouver：［s. n.］，2018．
27	ZHENG O， ABDEL A M， YUE L，et al ．CitySim：a drone-based vehicle trajectory dataset for safety oriented research and digital twins［J］．National Academy of Sciences：Transportation Research Board，2024，2678（4）：606-621．
28	HE K， ZHANG X， REN S，et al ．Deep residual learning for image recognition［C］∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition．Las Vegas：IEEE，2016：770-778．
29	COIFMAN B， LI L ．A critical evaluation of the next generation simulation （NGSIM） vehicle trajectory dataset［J］．Transportation Research Part B：Methodological，2017，105：362-377．
30	GU X， ABDEL A M， XIANG Q，et al ．Utilizing UAV video data for in-depth analysis of drivers’ crash risk at interchange merging areas［J］．Accident Analysis & Prevention，2019，123：159-169．

字段	单位	说明
CarId		车辆编号，每辆车分别对应唯一的车辆编号
FrameNum		数据帧号，每1 s采集30帧数据
CarCenterX	像素	车辆边界框中心像素点的x坐标值
CarCenterY	像素	车辆边界框中心像素点的y坐标值
BoundingBox1X	英尺	车辆边界框顶点1的x坐标值
BoundingBox1Y	英尺	车辆边界框顶点1的y坐标值
︙	︙	︙
BoundingBox4X	英尺	车辆边界框顶点4的x坐标值
BoundingBox4Y	英尺	车辆边界框顶点4的y坐标值
CarCenterLat	（°）	车辆边界框中心像素点的纬度
CarCenterLon	（°）	车辆边界框中心像素点的经度
︙	︙	︙
LaneId		车道编号，即车辆当前所处车道编号

输入指标	变量描述
E-，P-，F-，LP-，LF-，RP-，RF-v_x	目标车辆和周边车辆的纵向速度，km/h
E-，P-，F-，LP-，LF-，RP-，RF-v_y	目标车辆和周边车辆的侧向速度，km/h
E-，P-，F-，LP-，LF-，RP-，RF-a_x	目标车辆和周边车辆的纵向加速度，m/s²
E-，P-，F-，LP-，LF-，RP-，RF-a_y	目标车辆和周边车辆的侧向加速度，m/s²
E-，P-，F-，LP-，LF -，RP-，RF-θ	目标车辆和周边车辆的航向角，（°）
E-，P-，F-，LP-，LF -，RP-，RF-Δθ	目标车辆和周边车辆的航向角变化率，（°）/s
dw₀，dw₁，dw₂，dw₃，dw₄，dw₅	目标车辆和周边车辆的车头间距，m
P-，F-，LP-，LF -，RP-，RF-val	1表示对应车辆轨迹未被记录或不存在，0表示对应车辆轨迹被记录

模型	类别	精确率/%	召回率/%	准确率/%
TCN	LK	90.47	97.36	95.83
	RLC	98.17	95.77
	LLC	98.81	94.28
LSTM	LK	90.10	96.40	95.33
	RLC	97.83	95.56
	LLC	97.93	93.73
SVM	LK	88.31	97.29	94.21
	RLC	97.23	93.46
	LLC	96.88	92.10
TCN-LSTM	LK	94.19	95.70	96.67
	RLC	98.99	97.13
	LLC	96.37	97.16

[1]	LONG Xueqin, WANG Han, WANG Ruixuan. Taxi Trajectory Characteristics Analysis Based on Frequent Sequence Mining [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(6): 24-33.
[2]	LEI Cailin, ZHAO Cong, LOU Ren, JI Yuxiong, DU Yuchuan. Quality Assessment Method of Vehicle Trajectory Data from Roadside Perception [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(6): 56-72.
[3]	ZHANG Wenhui, LIU Tuo, SONG Yajing, et al. Identification of Hazardous Driving Hotspots of Conventional Urban Bus Based on Spatial Autocorrelation [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(4): 138-150.
[4]	ZHAO Xiaomei, ZHU Xiangyuan, WANG Qin, et al. Operational Reliability Optimization Strategies of Multi-type Bus Lines [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(8): 32-39.
[5]	LIN Yongjie, CHEN Ning, LU Kai. Vehicle Trajectory Tracking at Intersections Based on Millimeter Wave Radar Point Cloud [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(10): 110-125.
[6]	WENG Jiancheng, WANG Maolin, LIN Pengfei, et al. Cross-line Combined Bus Scheduling Optimization Method Based on Passenger Flow Characteristic Identification [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(9): 39-48.
[7]	QIN Yaqin, QIAN Zhengfu, XIE Jiming, et al. Cooperative Lane Change Decision-Making Model of Bottleneck Emergency Section in Weaving Area Based on Social Force [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(7): 66-75.
[8]	YUAN Hua CHEN Zehao. Short-term Traffic Flow Prediction Based on Temporal Convolutional Networks [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(11): 107-113,122.
[9]	ZHANG Nian LUO Xia ZHANG Ke. Bus Travel Choice Reversals Based on the Equate-to-Differentiate Theory [J]. Journal of South China University of Technology(Natural Science Edition), 2019, 47(9): 61-67.
[10]	CHAI Linguo CAI Baigen SHANGGUAN Wei WANG Jian WANG Huashen. A Construction Approach Based on Kinematic Simulation Environment for Networked Intelligent Vehicles [J]. Journal of South China University of Technology (Natural Science Edition), 2018, 46(1): 66-77.
[11]	Xu Hong-feng He Long Zhang Kun. Coordinated Signal Timing Optimization at Closely-Spaced Split Midblock Crosswalks [J]. Journal of South China University of Technology (Natural Science Edition), 2015, 43(12): 106-113.
[12]	Yang Zhao-sheng Qu Xin Lin Ci-yun Bing Qi-chun Gong Bo-wen. Traffic Signal Optimization Method Considering Low Emissions and Short Delay [J]. Journal of South China University of Technology (Natural Science Edition), 2015, 43(10): 29-34,41.
[13]	Yang Qing- fang Mei Duo Zheng Li- li Ma Ming- hui Wang Wei. Cloud Computing- Based Genetic Algorithm to Solve the Shortest Path in Urban Rood Networks [J]. Journal of South China University of Technology (Natural Science Edition), 2014, 42(3): 47-51,58.