基于Transformer模型的车辆轨迹预测

doi:10.16088/j.issn.1001-6600.2023061203

摘要/Abstract

摘要： 准确预测车辆轨迹可以保障自动驾驶车辆行驶安全,针对已有方法对长序列轨迹建模预测能力有限的问题,本文提出一种基于Transformer网络的车辆轨迹预测模型。将车辆的运动数据与交互数据输入驾驶意图预测模块生成概率意图向量,通过Concatenate函数与轨迹信息拼接后输入轨迹预测编码器,利用多头注意力机制充分提取轨迹特征,经解码器得到未来时刻的车辆轨迹分布。在车辆轨迹真实数据集NGSIM上进行验证,结果表明:在2 s预判时间下,驾驶意图预测模块准确率可达到85%以上;在4 s的预测时域下,轨迹预测模型相较于已有模型,其RMSE降低均达到10%以上。本文提出方法为自动驾驶车辆准确预测轨迹提供技术支持。

关键词: 自动驾驶, 车辆轨迹预测, 驾驶意图, 特征提取, 多头注意力机制

Abstract: Accurately predicting the trajectory of vehicle is crucial to ensure the safety of autonomous vehicles. However, traditional methods have limited modeling and predictive capabilities when dealing with long sequence trajectories. To address this issue, a vehicle trajectory prediction model was proposed based on the Transformer network. The approach involves inputting the motion and interaction data of the vehicle into a driving intention prediction module to generate a probability intention vector. The trajectory prediction encoder is obtained after the Concatenate function is spliced with the trajectory information, and the trajectory features are fully extracted by using the multi-head attention mechanism. Through the decoder, a distribution of future vehicle trajectories is obtained. Validation on the NGSIM real vehicle trajectory dataset indicates that the accuracy of the driving intention prediction module can reach more than 85% under a prediction time of 2 seconds. Furthermore, the RMSE of the trajectory prediction model is reduced by more than 10% compared with the existing models under a prediction time of 4 seconds. The method provides technical support for accurately predicting the trajectory of autonomous vehicles.

Key words: autonomous driving, vehicle trajectory prediction, driving intention, feature extraction, multi-head attention mechanism

中图分类号: U495

田晟, 胡啸. 基于Transformer模型的车辆轨迹预测[J]. 广西师范大学学报（自然科学版）, 2024, 42(3): 47-58.

TIAN Sheng, HU Xiao. Vehicle Trajectory Prediction Based on Transformer Model[J]. Journal of Guangxi Normal University(Natural Science Edition), 2024, 42(3): 47-58.

参考文献

[1] 肖凯文,胡伟琪,谢树辉,等.行人过街预警方法[J].汽车实用技术,2022,47(14):12-16. DOI: 10.16638/j.cnki.1671-7988.2022.014.004.
[2] 卢许孟,南新元,夏斯博.无模型坐标补偿积分滑模约束的自动驾驶汽车轨迹跟踪控制[J].广西师范大学学报(自然科学版),2023,41(2):36-48. DOI: 10.16088/j.issn.1001-6600.2022042004.
[3] LI X L, XIA J, CHEN X Y, et al. SIT: a spatial interaction-aware transformer-based model for freeway trajectory prediction[J]. ISPRS International Journal of Geo-Information, 2022, 11(2): 79. DOI: 10.3390/ijgi11020079.
[4] HOUENOU A, BONNIFAIT P, CHERFAOUI V, et al. Vehicle trajectory prediction based on motion model and maneuver recognition[C]// 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. Los Alamitos, CA: IEEE Computer Society, 2013: 4363-4369. DOI: 10.1109/IROS.2013.6696982.
[5] 裴玉龙,张银.车道变换期望运行轨迹仿真[J].交通与计算机,2008,26(4):68-71. DOI: 10.3963/j.issn.1674-4861.2008.04.019.
[6] 王畅,付锐,郭应时,等.换道预警系统中越线时间的预测方法[J].汽车工程,2014,36(4):509-514. DOI: 10.3969/j.issn.1000-680X.2014.04.023.
[7] ELMAN J L. Finding structure in time[J]. Cognitive Science, 1990, 14(2): 179-211. DOI: 10.1207/s15516709cog1402_1.
[8] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. DOI: 10.1162/neco.1997.9.8.1735.
[9] XIAO H P, WANG C Q, LI Z X, et al. UB-LSTM: a trajectory prediction method combined with vehicle behavior recognition[J]. Journal of Advanced Transportation, 2020, 2020: 8859689. DOI: 10.1155/2020/8859689.
[10] 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. DOI: 10.19721/j.cnki.1001-7372.2019.06.003.
[11] PARK S H, KIM B D, KANG C M, et al. Sequence-to-sequence prediction of vehicle trajectory via LSTM Encoder-Decoder architecture[C]// 2018 IEEE Intelligent Vehicles Symposium (IV). Los Alamitos, CA: IEEE Computer Society, 2018: 1672-1678. DOI: 10.1109/IVS.2018.8500658.
[12] LI R M, ZHONG Z R, CHAI J, et al. Autonomous vehicle trajectory combined prediction model based on CC-LSTM)[J]. International Journal of Fuzzy Systems, 2022, 24(8): 3798-3811. DOI: 10.1007/s40815-022-01288-x.
[13] 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. DOI: 10.3785/j.issn.1008-973X.2020.06.012.
[14] 温惠英,张伟罡,赵胜.基于生成对抗网络的车辆换道轨迹预测模型[J].华南理工大学学报(自然科学版),2020,48(5):32-40. DOI: 10.12141/j.issn.1000-565X.190182.
[15] GAO K, LI X H, 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. DOI: 10.1109/TITS.2023.3248842.
[16] 胡启洲,张晓亮,吴翊恺,等.车路协同下高速公路运行态势监测方法[J].东南大学学报(自然科学版),2020,50(6):1143-1147. DOI: 10.3969/j.issn.1001-0505.2020.06.022.
[17] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2017: 6000-6010.
[18] 高镇海,鲍明喜,高菲,等.基于LSTM概率多模态预期轨迹预测方法[J].汽车工程,2023,45(7):1145-1152,1162. DOI: 10.19562/j.chinasae.qcgc.2023.07.005.
[19] PENG J K, ZHANG S Y, ZHOU Y, et al. An integrated model for autonomous speed and lane change Decision-Making based on deep reinforcement learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 21848-21860. DOI: 10.1109/TITS.2022.3185255.
[20] HASAN F, HUANG H L. MALS-Net: a multi-head attention-based LSTM sequence-to-sequence network for socio-temporal interaction modelling and trajectory prediction[J]. Sensors, 2023, 23(1): 530. DOI: 10.3390/s23010530.
[21] 翁小雄,谢志鹏.基于多层复杂网络的高速公路节点重要性研究[J].广西师范大学学报(自然科学版),2021,39(5):78-88. DOI: 10.16088/j.issn.1001-6600.2020080801.
[22] DOROUDGAR S, CHUANG H M, PERRY P J, et al. Driving performance comparing older versus younger drivers[J]. Traffic Injury Prevention, 2017, 18(1): 41-46. DOI: 10.1080/15389588.2016.1194980.
[23] TIJERINA L, GARROTT W R, STOLTZFUS D, et al. Eye glance behavior of van and passenger car drivers during lane change decision phase[J]. Transportation Research Record, 2005, 1937(1): 37-43. DOI: 10.1177/0361198105193700106.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed