Intention-aware Transformer with Adaptive Social and Temporal Learning for Vehicle Trajectory Prediction

被引:6
作者
Hu, Yu [1 ]
Chen, Xiaobo [2 ]
机构
[1] Jiangsu Univ, Automot Engn Res Inst, Zhenjiang, Jiangsu, Peoples R China
[2] Shandong Technol & Business Univ, Sch Comp Sci & Technol, Yantai, Shandong, Peoples R China
来源
2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) | 2022年
关键词
vehicle trajectory prediction; driving intentions; nudtimodal maneuver; graph attention networks; spatio-temporal learning; LANE CHANGE;
D O I
10.1109/ICPR56361.2022.9956216
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Accurate prediction of the trajectory of surrounding vehicles is crucial to autonomous driving for path planning and collision avoidance. In this paper, we propose a novel transformer-based model with adaptive social and temporal learning for trajectory prediction. In order to model social interaction between vehicles at each historical timestamp, an enhanced graph attention feature aggregation mechanism combing hidden feature and explicit relative spatial relation is developed. Further, the social and temporal dependency across different timestamps is captured by multi-head self-attention with an extra learnable "intention token". To achieve multi-modal trajectory prediction, we implement intention-aware transformer decoder of driving behavior, the intention recognition and trajectory. Experiments on large-scale benchmark datasets verify that our model achieves better performance comparing with some state-of-the-art trajectory prediction models.
引用
收藏
页码:3721 / 3727
页数:7
相关论文
共 29 条
[1]   Social LSTM: Human Trajectory Prediction in Crowded Spaces [J].
Alahi, Alexandre ;
Goel, Kratarth ;
Ramanathan, Vignesh ;
Robicquet, Alexandre ;
Li Fei-Fei ;
Savarese, Silvio .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :961-971
[2]   Environment-Attention Network for Vehicle Trajectory Prediction [J].
Cai, Yingfeng ;
Wang, Zihao ;
Wang, Hai ;
Chen, Long ;
Li, Yicheng ;
Sotelo, Miguel Angel ;
Li, Zhixiong .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (11) :11216-11227
[3]  
Colyar J., 2007, FHWAHRT07030
[4]  
Colyar J., 2007, FHWAHRT07030
[5]  
Deo N, 2018, IEEE INT VEH SYM, P1179, DOI 10.1109/IVS.2018.8500493
[6]   Convolutional Social Pooling for Vehicle Trajectory Prediction [J].
Deo, Nachiket ;
Trivedi, Mohan M. .
PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, :1549-1557
[7]  
Dosovitskiy A., 2020, INT C LEARN REPR
[8]  
Feng XD, 2019, IEEE INT C INTELL TR, P3514, DOI [10.1109/ITSC.2019.8917482, 10.1109/itsc.2019.8917482]
[9]   Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks [J].
Gupta, Agrim ;
Johnson, Justin ;
Li Fei-Fei ;
Savarese, Silvio ;
Alahi, Alexandre .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :2255-2264
[10]  
Haoran Song, 2020, Computer Vision - ECCV 2020. 16th European Conference. Proceedings. Lecture Notes in Computer Science (LNCS 12366), P598, DOI 10.1007/978-3-030-58589-1_36