基于时域卷积网络与注意力机制的车辆换道轨迹预测模型

doi:10.16097/j.cnki.1009-6744.2024.02.012

摘要/Abstract

摘要： 精准的车辆轨迹预测模型可以为自动驾驶车辆提供其周围车辆的准确运动状态信息，进而判断本车与周围车辆短期内是否有发生冲突的可能性。本文提出一种基于时域卷积网络与注意力机制(Temporal Convolutional Networks with Attention mechanism, TCN-Attention)的车辆换道轨迹预测模型。该模型以时域卷积网络作为当前输入的特征提取器，利用时间与空间注意力机制使模型在不同时间和空间位置之间建立动态关联，更准确地捕捉车辆之间的动态时空相关性，实现准确预测车辆换道轨迹。与传统单一车辆轨迹特征输入不同，本文通过对输入特征进行多维扩充与融合，进一步提高了轨迹预测准确率。此外，本文提出一种换道执行起止时刻定义方法更准确地确定数据集中的换道起止时刻。实验表明，本文所提模型能以高准确率预测变换车道轨迹，在整体效果上优于其他深度学习模型，与ConvLSTM(Convolution Long Short-Term Memory)相比，TCN-Attention的平均绝对误差(MeanAbsolute Error, EMAE )降低了69.8%，均方根误差(Root Mean Square Error, ERMSE )降低了 49.15%，平均绝对百分比误差(Mean Absolute Percentage Error, EMAPE )降低了14.24%。

关键词: 交通工程, 轨迹预测, TCN-Attention, 车辆换道

Abstract: An accurate vehicle trajectory prediction model can provide self-driving vehicles with precise information about the motion states of surrounding vehicles in mixed traffic flow environments, allowing it to assess the possibility of conflicts with neighboring vehicles in the short term. This paper proposes a vehicle lane-changing trajectory prediction model based on Temporal Convolutional Networks with Attention Mechanism (TCN-Attention) to improve the accuracy of vehicle lane-changing trajectory prediction. This model uses Temporal Convolutional Networks as the current input's feature extractor and utilizes a temporal and spatial attention mechanism to establish dynamic correlations between different time steps and spatial positions. Specifically, the combination of temporal and spatial attention mechanisms helps the model extract essential semantic features in both the temporal and spatial dimensions before and after lane-changing, enabling it to more accurately capture the dynamic spatiotemporal relationships between vehicles. This enables precise predictions of lane-changing trajectories on highways. Different from the traditional only using a trajectory features as input, our method achieves the multi-dimensional expansion and fusion of the input features, and further improves the accuracy of the trajectory prediction. In addition, this paper proposes a new method to define the start and end time of lane-changing in the dataset more accurately. Experiments show that the proposed model can predict the trajectory of the lane-changing with high accuracy, and the overall effect is better than other deep learning models. Compared with the Convolution Long Short- Term Memory(ConvLSTM), the Mean Absolute Error( EMAE ) of TCN-Attention is reduced by 69.8%, the Root Mean Square Error( ERMSE ) is reduced by 49.15% and the MeanAbsolute Percentage Error( EMAPE ) is reduced by 14.24%.

Key words: traffic engineering, vehicle trajectory prediction, TCN-Attention, vehicle lane-changing

中图分类号:

U491

杨达, 刘家威, 郑斌, 孙峰. 基于时域卷积网络与注意力机制的车辆换道轨迹预测模型[J]. 交通运输系统工程与信息, 2024, 24(2): 114-126.

YANGDa, LIU Jiawei, ZHENG Bin, SUN Feng. AVehicle Lane-changing Trajectory Prediction Model Based on Temporal Convolutional Networks and Attention Mechanism[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(2): 114-126.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.02.012

http://www.tseit.org.cn/CN/Y2024/V24/I2/114

参考文献

[1] SONG R, LI B. Surrounding vehicles' lane change maneuver prediction and detection for intelligent vehicles: A comprehensive review[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(7): 6046 6062.

[2]SHI Q, ZHANG H. An improved learning-based LSTM approach for lane change intention prediction subject to imbalanced data[J]. Transportation Research Part C: Emerging Technologies, 2021, 133: 103414.

[3] WANG J, ZHANG Z, LU G. A Bayesian inference based adaptive lane change prediction model[J]. Transportation Research Part C: Emerging Technologies, 2021, 132: 103363.

[4]GRIESBACH K, BEGGIATO M, HOFFMANN K H. Lane change prediction with an echo state network and recurrent neural network in the urban area[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(7): 6473-6479.

[5]GUO H, KEYVAN-EKBATANI M, XIE K. Lane change detection and prediction using real-world connected vehicle data[J]. Transportation Research Part C: Emerging Technologies, 2022, 142: 103785.

[6]HU J, ZHANG Y, RAKHEJA S. Adaptive lane change trajectory planning scheme for autonomous vehicles under various road frictions and vehicle speeds[J]. IEEE Transactions on Intelligent Vehicles, 2022, 8(2): 1252 1265.

[7] LIU Y, ZHOU B, WANG X, et al. Dynamic lane changing trajectory planning for autonomous vehicles based on discrete global trajectory[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(7): 8513 8527.

[8] YE T, HUAXIN P E I, SONG Y A N, et al. Extended driving risk field model for I-VICS and its application[J]. Journal of Tsinghua University (Science and Technology), 2022, 62(3): 447-457.

[9]LIU X, WANG Y, JIANG K, et al. Interactive trajectory prediction using a driving risk map-integrated deep learning method for surrounding vehicles on highways[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 19076-19087.

[10] VALLON C, ERCAN Z, CARVALHO A, et al. A machine learning approach for personalized autonomous lane change initiation and control[C]. Los Angeles, CA, USA : 2017 IEEE Intelligent Vehicles Symposium (IV), IEEE, 2017.

[11] DO Q H, TEHRANI H, MITA S, et al. Human drivers based active-passive model for automated lane change[J]. IEEE Intelligent Transportation Systems Magazine, 2017, 9(1): 42-56.

[12] XUE Q, XING Y, LU J. An integrated lane change prediction model incorporating traffic context based on trajectory data[J]. Transportation Research, Part C. Emerging Technologies, 2022, 132: 103363.

[13] XIN L, WANG P, CHAN C Y, et al. Intention-aware long horizon trajectory prediction of surrounding vehicles using dual LSTM networks[C]. Maui, HI, USA: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), IEEE, 2018.

[14] HOU L, XIN L, LI S E, et al. Interactive trajectory prediction of surrounding road users for autonomous driving using structural-LSTM network[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(11): 4615-4625.

[15] ALTCHE F, D L FORTELLE A. An LSTM network for highway trajectory prediction[C]. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), IEEE, Yokohama, Japan, 2017.

[16] ZHANG Y, ZOU Y, TANG J, et al. Long-term prediction for high-resolution lane-changing data using temporal convolution network[J]. Transportmetrica B: Transport Dynamics, 2022, 10(1): 849-863.

[17] SHI K, WU Y, SHI H, et al. An integrated car-following and lane changing vehicle trajectory prediction algorithm based on a deep neural network[J]. Physica A: Statistical Mechanics and Its Applications, 2022, 599: 127303.

[18] LI Q. TCN-SA: A social attention network based on temporal convolutional network for vehicle trajectory prediction[J/OL]. Journal of Advanced Transportation， (2023-12-09) [2024-03-12]. https://www.hindawi.com/ journals/jat/2023/1286977/.

[19] LIN Z, YUE W, HUANG J, et al. Ship trajectory prediction based on the TTCN-Attention-GRU model[J]. Electronics, 2023, 12(12): 2556.

[20] 连静, 李硕贤, 刘一荻, 等.基于车道目标引导的车辆轨迹预测[J]. 汽车工程,2023, 45(8): 1353-1361. [LIAN J, LI S X, LIU Y D, et al. Goal supervised attention network for vehicle trajectory prediction[J]. Automotive Engineering, 2023, 45(8): 1353-1361.]

[21] LYU N, WEN J, DUAN Z, et al. Vehicle trajectory prediction and cut-in collision warning model in a connected vehicle environment[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 23(2): 966-981.

[22] WANG X, ALONSO-MORA J, WANG M. Probabilistic risk metric for highway driving leveraging multi-modal trajectory predictions[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 19399-19412.

[23] DO J, HAN K, CHOI S B. Lane change intention inference and trajectory prediction of surrounding vehicles on highways[J]. IEEE Transactions on Intelligent Vehicles, 2023, 8(7): 3813-3825.

[24] GAO K, LI X, CHEN B, et al. Dual transformer based prediction for lane change intentions and trajectories in mixed traffic environment[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(6): 6203 6216.

[25] MENG Q, GUO H, LI J, et al. Vehicle trajectory prediction method driven by raw sensing data for intelligent vehicles[J]. IEEE Transactions on Intelligent Vehicles, 2023, 8(7): 3799-3812.

[26] SHANGGUAN Q, FU T, WANG J, et al. A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns[J]. Accident Analysis & Prevention, 2022, 164: 106500.

[27] ZHANG J, LEE J, ABDEL-ATY M, et al. Enhanced index of risk assessment of lane change on expressway weaving segments: A case study of an expressway in China[J]. Accident Analysis & Prevention, 2023, 180: 106909.

[28] TOLEDO T, ZOHAR D. Modeling duration of lane changes[J]. Transportation Research Record, 2007, 1999 (1): 71-78.

[29] THIEMANN C, TREIBER M, KESTING A. Estimating acceleration and lane-changing dynamics from next generation simulation trajectory data[J]. Transportation Research Record, 2008, 2088(1): 90-101.

[30] KRAJEWSKI R, BOCK J, KLOEKER L, et al. The highD dataset: A drone dataset of naturalistic vehicle trajectories on German highways for validation of highly automated driving systems[C]//2018 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2018: 2118-2125