Research on Vehicle Trajectory Prediction Based on Multifeature Fusion

doi:10.19678/j.issn.1000-3428.0070065

Abstract

Abstract: In response to the problems of insufficient vehicle feature extraction and single prediction scenarios in existing models, this paper proposes a vehicle trajectory prediction model, called MTF-GRU-MTSHMA, that integrates multiple features in multiple scenarios. The proposed model consists of an encoder module, multifeature extraction module, multifeature fusion module, and trajectory prediction module. In the encoder module, the Gated Recurrent Unit (GRU) is used to encode the historical information of the vehicle to obtain its historical status. In the multifeature extraction module, considering the spatial correlation between surrounding vehicles in the target vehicle area, a multidimensional spatial attention mechanism is proposed to mine the deep features of surrounding vehicles. Additionally, a triple attention mechanism is introduced to extract features from the encoded state vector. In the multifeature fusion module, the extracted multiple features are linearly concatenated and input into the multifeature fusion network for fusion. In the trajectory prediction module, improvements are made to the GRU by proposing a Mixed Teaching Force Gated Recurrent Unit (MTF-GRU) as the decoder, which controls the decoding mode by introducing a teaching rate to improve decoding performance. The fused features are input into the decoder to generate future trajectories. The proposed model is experimentally simulated using the NGSIM dataset. The results show that the average Root Mean Square Error (RMSE) of the proposed model for straight road, intersection, and roundabout road scenarios increases by 8.16%, 10.31%, and 8.37%, respectively, compared with the optimal benchmark model, proving the effectiveness of the proposed model.

Key words: trajectory prediction, attention mechanism, multifeature fusion, Mixed Teaching Force Gated Recurrent Unit (MTF-GRU), decoding mode

摘要： 针对现有模型对车辆特征提取不足和预测场景单一的问题,提出了一种在多场景下融合多特征的车辆轨迹预测模型MTF-GRU-MTSHMA。该模型由编码器模块、多特征提取模块、多特征融合模块和轨迹预测模块组成。在编码器模块,利用门控循环单元(GRU)对车辆历史信息进行编码得到车辆的历史状态;在多特征提取模块,考虑目标车辆区域内周围车辆之间的空间关联性,通过多维度空间注意力机制挖掘周围车辆的深层特征,并引入三重注意力机制对编码后的状态向量进行特征提取;在多特征融合模块,将提取到的多种特征进行线性拼接,并输入到多特征融合网络中进行融合;在轨迹预测模块,对GRU进行改进,提出混合示教门控循环单元(MTF-GRU)并作为解码器,通过引入示教率来控制解码模式以提高解码性能,将融合后的特征输入到解码器中生成未来轨迹。在NGSIM数据集上进行的仿真实验结果表明,与最优基准模型相比,所提模型在直线道路、十字路口以及环岛道路场景下的均方根误差(RMSE)分别提高了8.16%、10.31%和8.37%,证明了所提模型的有效性。

关键词: 轨迹预测, 注意力机制, 多特征融合, 混合示教门控循环单元, 解码模式

CLC Number:

TP18

WANG Qingrong, HAO Fule, ZHU Changfeng, WANG Junjie. Research on Vehicle Trajectory Prediction Based on Multifeature Fusion[J]. Computer Engineering, 2026, 52(2): 331-341.

王庆荣, 郝福乐, 朱昌锋, 王俊杰. 基于多特征融合的车辆轨迹预测研究[J]. 计算机工程, 2026, 52(2): 331-341.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070065

https://www.ecice06.com/EN/Y2026/V52/I2/331

References

[1] LIU P, KURT A, OZGUNER U. Trajectory prediction of a lane changing vehicle based on driver behavior estimation and classification[C]//Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems. Washington D. C., USA: IEEE Press, 2014: 942-947.
[2] LEFÈVRE S, VASQUEZ D, LAUGIER C. A survey on motion prediction and risk assessment for intelligent vehicles[J]. ROBOMECH Journal, 2014, 11(1): 1-9.
[3] 毛莺池, 陈杨. 不确定性车辆路口的轨迹预测[J]. 计算机科学, 2018, 45(3): 237-242. MAO Y C, CHEN Y. Ucertain vehicle intersection trajectory prediction[J]. Computer Science, 2018, 45(3): 237-242. (in Chinese)
[4] HOUENOU A, BONNIFAIT P, CHERFAOUI V, et al. Vehicle trajectory prediction based on motion model and maneuver recognition[C]//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems. Washington D. C., USA: IEEE Press, 2013: 4363-4369.
[5] CHOI D, YIM J, BAEK M, et al. Machine learning-based vehicle trajectory prediction using V2V communications and on-board sensors[J]. Electronics, 2021, 10(4): 420.
[6] 吴晓建, 危一华, 王爱春, 等. 基于融合Dropout与注意力机制的LSTM-GRU车辆轨迹预测[J]. 湖南大学学报(自然科学版), 2023, 50(4): 65-75. WU X H, WEI Y H, WANG A C, et al. Vehicle trajectory prediction based on LSTM-GRU integrating dropout and attention mechanism[J]. Journal of Hunan University(Natural Sciences), 2023, 50(4): 65-75. (in Chinese)
[7] 方华珍, 刘立, 肖小凤, 等. 混合示教长短时记忆网络的车辆轨迹预测研究[J]. 交通运输系统工程与信息, 2023, 23(4): 80-87. FANG H Z, LIU L, XIAO X F, et al. Research on vehicle trajectory prediction based on mixed teaching force LSTM[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(4): 80-87. (in Chinese)
[8] CAO Q X, ZHAO Z X, ZENG Q Q, et al. Real-time vehicle trajectory prediction for traffic conflict detection at unsignalized intersections[J]. Journal of Advanced Transportation, 2021, 2021: 8453726.
[9] DEO N, TRIVEDI M M. Convolutional social pooling for vehicle trajectory prediction[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Washington D. C., USA: IEEE Press, 2018: 1468-1476.
[10] MO X Y, XING Y, LV C. Interaction-aware trajectory prediction of connected vehicles using CNN-LSTM networks[C]//Proceedings of the 46th Annual Conference of the IEEE Industrial Electronics Society. Washington D. C., USA: IEEE Press, 2020: 5057-5062.
[11] MUKHERJEE S, WANG S, WALLACE A. Interacting vehicle trajectory prediction with convolutional recurrent neural networks[C]//Proceedings of the IEEE International Conference on Robotics and Automation. Washington D. C., USA: IEEE Press, 2020: 4336-4342.
[12] ZHONG Z R, LI R M, CHAI J, et al. Autonomous vehicle trajectory combined prediction model based on C-LSTM[C]//Proceedings of the International Conference on Fuzzy Theory and Its Applications. Washington D. C., USA: IEEE Press, 2021: 111-120.
[13] SHEN G J, LI P F, CHEN Z Y, et al. Spatio-temporal interactive graph convolution network for vehicle trajectory prediction[J]. Internet of Things, 2023, 24: 100935.
[14] ALAHI A, GOEL K, RAMANATHAN V, et al. Social LSTM: human trajectory prediction in crowded spaces[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2016: 961-971.
[15] DEO N, TRIVEDI M M. Convolutional social pooling for vehicle trajectory prediction[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Washington D. C., USA: IEEE Press, 2018: 1468-1476.
[16] 黄玲, 崔躜, 游峰, 等. 适用于多车交互场景的车辆轨迹预测模型[J]. 吉林大学学报(工学版), 2024, 54(5): 1188-1185. HUANG L, CUI Z, YOU F, et al. Vehicle trajectory prediction model for multi-vehicle interaction scenario[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1188-1185. (in Chinese)
[17] 蔡国庆, 刘玲, 张冲等. 基于GNN-LSTM-CNN网络的6G车辆轨迹预测算法[J]. 西安电子科技大学学报, 2023, 50(3): 50-60. CAI G Q, LIU L, ZHANG C, et al. Algorithm for prediction of the 6G vehicle trajectory based on the GNN-LSTM-CNN network[J]. Journal of Xidian University, 2023, 50(3): 50-60. (in Chinese)
[18] GAN N F, JIANG Z W, ZHOU B, et al. Research on vehicle trajectory prediction method for intersections without signal lights[J]. SAE International Journal of Connected and Automated Vehicles, 2021, 4(3): 124-131.
[19] CHOI S, KIM J, YEO H. Attention-based recurrent neural network for urban vehicle trajectory prediction[J]. Procedia Computer Science, 2019, 151: 327-334.
[20] 田彦涛, 许富强, 王凯歌, 等. 考虑周车信息的自车期望轨迹预测[J]. 吉林大学学报(工学版), 2023, 53(3): 674-681. TIAN Y T, XU F Q, WANG K G, et al. Expected trajectory prediction of vehicle considering surrounding vehicle information[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(3): 674-681. (in Chinese)
[21] 闫建红, 刘芝妍, 王震. 融合时空注意力机制的多尺度卷积车辆轨迹预测[J]. 计算机工程, 2025, 51(8): 406-414. YAN J H, LIU Z Y, WANG X. Vehicle trajectory prediction based on spatial-temporal attention mechanisms and multi-scale convolutional social pooling[J]. Computer Engineering, 2025, 51(8): 406-414. (in Chinese)
[22] 吴翊恺, 胡启洲, 吴啸宇. 车联网背景下的机动车辆轨迹预测模型[J]. 东南大学学报(自然科学版), 2022, 52(6): 1199-1208. WU Y K, HU Q Z, WU X Y. Vehicle trajectory prediction model in the context of Internet of vehicles[J]. Journal of Southeast University(Natural Science Edition), 2022, 52(6): 1199-1208. (in Chinese)
[23] 金立生, 高铭, 郭柏苍, 等. 基于时空融合LSTM网络的驾驶视角轨迹预测[J]. 中国公路学报, 2022, 35(4): 325-332. JIN L S, GAO M, GUO B C, et al. Driver perspective trajectory prediction based on spatiotemporal fusion LSTM network[J]. China Journal of Highway and Transport, 2022, 35(4): 325-332. (in Chinese)
[24] GENG M S, CHEN Y, XIA Y J, et al. Dynamic-learning spatial-temporal Transformer network for vehicular trajectory prediction at urban intersections[J]. Transportation Research Part C: Emerging Technologies, 2023, 156: 104330.
[25] 温惠英, 张昕怡, 黄俊达, 等. 考虑动态交互作用的智能车辆轨迹预测研究[J]. 交通运输系统工程与信息, 2024, 24(4): 60-68. WEN H Y, ZHANG X Y, HUANG J D, et al. Research on intelligent vehicle trajectory prediction considering dynamic interaction[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(4): 60-68. (in Chinese)
[26] 刘占文, 李文倩, 林杉, 等. 基于稀疏权重共享的多模态轨迹预测[J].中国公路学报, 2023, 36(9): 244-256. LIU Z W, LI W Q, LIN B, et al. Multimodal trajectory prediction based on sparse weight sharing[J]. China Journal of Highway and Transport, 2023, 36(9): 244-256. (in Chinese)
[27] 宋秀兰, 董兆航, 单杭冠, 等. 基于时空融合的多头注意力车辆轨迹预测[J]. 浙江大学学报(工学版), 2023, 57(8): 1636-1643. SONG X L, DONG Z H, SHAN H G, et al. Vehicle trajectory prediction based on temporal-spatial multi-head attention mechanism[J]. Journal of Zhejiang University (Engineering Science), 2023, 57(8): 1636-1643. (in Chinese)

Please choose a citation manager

Content to export