基于轨迹预测和极限梯度提升的驾驶意图识别

doi:10.13229/j.cnki.jdxbgxb.20230479

Abstract

Abstract:

To achieve accurate identification of the driving intentions of surrounding vehicles by intelligent connected vehicles， a driving intention recognition framework based on trajectory prediction and extreme gradient boosting （XGBoost） algorithm is proposed. Firstly， we attach the driving intention label to the vehicle's historical trajectory sequence and build the offline training dataset. Then， a driving intention recognition framework is constructed. A mixed teacher force long short-term Memory （LSTM） module is used to predict the future trajectory. The XGBoost module concatenates the historical and future trajectory and recognizes driving intention （left lane change， lane keeping， and right lane change）. Finally， the model is verified on the real road datasets Next Generation SIMulation（NGSIM） US101 and I-80 sections. The experimental results show that the proposed model outperforms the other methods in metrics precision， recall， F1 score， and accuracy. The recognition accuracy can reach 97.7% in the prediction of 4 s historical trajectory and 3 s future trajectory， which shows good performance in driving intention recognition. The code can be obtained at：https：∥gitee.com/fanghz-colin/lstm-xgboost.git.

Key words: traffic engineering, long short-term memory, extreme gradient boosting, intelligent connected vehicle, driving intention recognition

CLC Number:

U495

Hua-zhen FANG,Li LIU,Qing GU,Xiao-feng XIAO,Yu MENG. Driving intention recognition based on trajectory prediction and extreme gradient boosting[J].Journal of Jilin University(Engineering and Technology Edition), 2025, 55(2): 623-630.

Figures/Tables 13

Fig.1

Table 1

Table 2

Description of model input feature"

组别	参数	特征描述	数量
TVF	$x t, y t$	目标车辆的横向和纵向位移	2
	$v x t, v y t$	目标车辆的横向和纵向速度，通过相邻轨迹点之间的位移可得： $v x t = 10 x t + 1 - x t, v y t = 10 y t + 1 - y t$	2
	$a x t, a y t$	目标车辆的横向和纵向加速度，通过相邻轨迹点之间的速度可得： $a x t = 10 v x t + 1 - v x t, a y t = 10 v y t + 1 - v y t$	2
SVF	$Δ x t i, Δ y t i$	周围车辆i相对于目标车辆的横向与纵向位移，由公式可得： $Δ x t i = x t i - x t, Δ y t i = y t i - y t$	12
	$v x t i, v y t i$	周围车辆i的横向与纵向绝对速度，通过其位移可得： $v x t i = 10 x t + 1 i - x t i, v y t i = 10 y t + 1 i - y t i$	12
	$a x t, a y t$	周围车辆i的横向与纵向加速度，通过其速度可得： $a x t i = 10 v x t + 1 i - v x t i, a y t i = 10 v y t + 1 i - v y t i$	12
RF	$R l, R r$	$R l 、 R r$ 表示目标车辆左右车道标识位，如果其存在置为1，否则为0	2

Table 2

Fig.2

Fig.3

Fig.4

Fig.5

Table 3

Table 4

Table 5

Fig.6

Table 6

Table 7

References 21

1	Xing Y, Lyu C, Wang H, et al. Driver lane change intention inference for intelligent vehicles: framework, survey, and challenges[J]. IEEE Transactions on Vehicular Technology, 2019, 68(5): 4377-4390.
2	Houenou A, Bonnifait P, Cherfaoui V, et al. Vehicle trajectory prediction based on motion model and maneuver recognition[C]∥ IEEE/RSJ International Conference on Intelligent Robots and Systems, Tokyo, Japan, 2013: 4363-4369.
3	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 Feng, Lou Jing-tao, Zhao Kai, et al. A research on vehicle trajectory prediction method based on behavior recognition and curvature constraints[J]. Automotive Engineering, 2019, 41(9): 1036-1042.
4	Tsogas M, Polychronopoulos A, Floudas N, et al. Situation refinement for vehicle maneuver identification and driver's intention prediction[C]∥ 10th International Conference on Information Fusion, Quebec City, Canada, 2007: No.4408203.
5	Wang X, Guo Y, Bai C, et al. Driver's intention identification with the involvement of emotional factors in two-lane roads[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(11): 6866-6874.
6	祝俪菱, 刘澜, 赵新朋, 等. 基于支持向量机的车辆驾驶行为识别研究[J]. 交通运输系统工程与信息, 2017, 17(1): 91-97.
	Zhu Li-ling, Liu Lan, Zhao Xin-peng, et al. Driver behavior recognition based on support vector machine[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(1): 91-97.
7	Berndt H, Emmert J, Dietmayer K. Continuous driver intention recognition with hidden markov models[C]∥ 11th International IEEE Conference on Intelligent Transportation Systems, Beijing, China, 2008: 1189-1194.
8	Liu Q, Xu S, Lu C, et al. Early recognition of driving intention for lane change based on recurrent hidden semi-Markov model[J]. IEEE Transactions on Vehicular Technology, 2020, 69(10): 10545-10557.
9	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 Zhi-qiang, Wu Xue-gang, Ni Jie, et al. Driving intention recognition based on hmm and svm cascade algorithm[J]. Automotive Engineering, 2018, 40(7): 858-864.
10	Fang H, Liu L, Gu Q, et al. Driving intention recognition of human drivers in mixed traffic flow[C]∥ IEEE 25th International Conference on Intelligent Transportation Systems, Macao, China, 2022: 153-157.
11	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.
12	Chandra R, Guan T, Panuganti S, et al. Forecasting trajectory and behavior of road-agents using spectral clustering in graph-lstms[J]. IEEE Robotics and Automation Letters, 2020, 5(3): 4882-4890.
13	赵健, 宋东鉴, 朱冰, 等. 数据机理混合驱动的交通车意图识别方法[J]. 汽车工程, 2022, 44(7): 997-1008.
	Zhao Jian, Song Dong-jian, Zhu Bing, et al. Traffic vehicles intention recognition method driven by data and mechanism hybrid[J]. Automotive Engineering, 2022, 44(7): 997-1008.
14	赵建东, 赵志敏, 屈云超, 等. 轨迹数据驱动的车辆换道意图识别研究[J]. 交通运输系统工程与信息, 2022, 22(4): 63-71.
	Zhao Jian-dong, Zhao Zhi-min, Qu Yun-chao, et al. Vehicle lane change intention recognition driven by trajectory data[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(4): 63-71.
15	Guo H, Keyvan E M, Xie K. Lane change detection and prediction using real-world connected vehicle data[J]. Transportation Research Part C: Emerging Technologies, 2022, 142: No.103785.
16	Zhang Y, Shi X, Zhang S, et al. A xgboost-based lane change prediction on time series data using feature engineering for autopilot vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 19187-19200.
17	Chen T, Guestrin C. Xgboost: a scalable tree boosting system[C]∥ 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, USA, 2016: 785-794.
18	Hu Y, Zhan W, Tomizuka M. Probabilistic prediction of vehicle semantic intention and motion[C]∥ IEEE Intelligent Vehicles Symposium (IV), Suzhou, China, 2018: 307-313.
19	Ding W, Chen J, Shen S. Predicting vehicle behaviors over an extended horizon using behavior interaction network[C]∥ International Conference on Robotics and Automation, Montreal, Canada, 2019: 8634-8640.
20	Altché F, Fortelle A. An LSTM network for highway trajectory prediction[C]∥ IEEE 20th International Conference on Intelligent Transportation Systems, Yokohama, Japan, 2017: 353-359.
21	田彦涛, 黄兴, 卢辉遒, 等. 基于注意力与深度交互的周围车辆多模态行为轨迹预测[J]. 吉林大学学报: 工学版, 2023, 53(5): 1474-1480.
	Tian Yan-tao, Huang Xing, Lu Hui-qiu, et al. Vehicle multi-modal maneuvers and trajectory prediction based on attention mechanism with deep interaction[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(5): 1474-1480.

Related Articles 15

[1]	Fei WU,Peng-cheng WANG,Kang YANG. Drivability evaluation model based on PCA-SSA-XGBoost [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(1): 105-115.
[2]	Huai-xin LI,Chang-gen YAN,Bin LIN,Yu-ling SHI. Strength and statistical damage model in whole process of clay-concrete combined body [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(1): 245-255.
[3]	Rong-han YAO,Wen-yan QI,Hong-yu HU,Xiao-jing DU,Yan-feng QIAO,Li-bing WANG. Multi-lane cellular automata model considering bus-high occupancy vehicle lane [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(1): 162-174.
[4]	Rong-gui ZHOU,Pei GAO,Yu-xuan LI,Jian ZHOU. Abnormal driving behavior thresholds of highway minibuses based on trajectory data [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(9): 2581-2587.
[5]	Ping YU,Kang ZHAO,Jie CAO. Rolling bearing fault diagnosis based on optimized A-BiLSTM [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2156-2166.
[6]	Qiu-zhan ZHOU,Ze-yu JI,Cong WANG,Jing RONG. Non-intrusive load monitoring via online compression and reconstruction [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(6): 1796-1806.
[7]	Qing-lu MA,Hao YAN,Zhen-yu NIE,Yang-mei LI. Cooperative control method for intelligent networked vehicles in ramp confluence area [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1332-1346.
[8]	Yun PU,Yin XU,Hai-xu LIU,Yi-fan TAN. An improved car⁃following model for connected and automated vehicles considering impact of multiple vehicles [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1285-1292.
[9]	Ling HUANG,Zuan CUI,Feng YOU,Pei-xin HONG,Hao-chuan ZHONG,Yi-xuan ZENG. Vehicle trajectory prediction model for multi-vehicle interaction scenario [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1188-1195.
[10]	Qian CAO,Zhi-hui LI,Peng-fei TAO,Hai-tao LI,Yong-jian MA. Deployment of heterogeneous sensors for traffic accident detection and prevention [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(4): 969-978.
[11]	Xin ZHANG,Qi-zhou HU,Jun HE,Xiao-yu WU. Traffic condition diagnosis of confluence areas considering traffic infarction [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(2): 478-484.
[12]	Wei-hua ZHANG,Jia-ming LIU,Li-peng XIE,Heng DING. Lane⁃changing model of autonomous vehicle in weaving area of expressway in intelligent and connected mixed environment [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(2): 469-477.
[13]	Hui-ying WEN,Zi-qi HE,Qiu-ling LI,Sheng ZHAO. Traffic conflict prediction and influencing factors analysis of truck lane change on expressway [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(10): 2827-2836.
[14]	Yi-yong PAN,Jing-ting WU,Xuan-ye Miao. Temporal instability analysis of factors affecting injury severities of elderly drivers [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(10): 2819-2826.
[15]	Xiao-jing DU,Rong-han YAO. Evolutionary game mechanism of mandatory lane changing for exiting for intelligent connected bus [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(1): 124-135.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

编号	特征名	特征描述	单位
1	Vehicle_ID	车辆编号	-
2	Frame_ID	帧数编号	-
3	Total_Frames	车辆在数据集中总帧数	-
4	Global_Time	全局时间（毫秒数）	ms
5	Local_X	横向相对位移	feet
6	Local_Y	纵向相对位移	feet
7	Lane_ID	车道编号	-

模型	未来轨迹/s
模型	1	2	3
MHA-LSTM	0.41	1.01	1.74
MTF-LSTM	0.48	0.89	1.47

历史轨迹长度/s	预测轨迹长度/s
历史轨迹长度/s	1	2	3
1	0.961	0.966	0.969
2	0.965	0.970	0.972
3	0.968	0.972	0.975
4	0.971	0.974	0.977
5	0.971	0.973	0.977

指标	模型	驾驶意图
指标	模型	左换道	车道保持	右换道
精确率	XGBoost	0.973	0.960	0.975
	S-XGBoost	0.950	0.963	0.948
	LSTM-XGBoost	0.984	0.965	0.983
召回率	XGBoost	0.971	0.959	0.978
	S-XGBoost	0.953	0.943	0.963
	LSTM-XGBoost	0.976	0.976	0.980
F₁ Score	XGBoost	0.972	0.959	0.977
	S-XGBoost	0.952	0.953	0.955
	LSTM-XGBoost	0.980	0.971	0.981
准确率	XGBoost	0.969
	S-XGBoost	0.953
	LSTM-XGBoost	0.977

Driving intention recognition based on trajectory prediction and extreme gradient boosting

RICH HTML

PDF (PC)