Goal-driven Long-Term Trajectory Prediction

被引:23
|
作者
Tran, Hung [1 ]
Le, Vuong [1 ]
Tran, Truyen [1 ]
机构
[1] Deakin Univ, Appl AI Inst, Geelong, Vic, Australia
关键词
ATTENTION;
D O I
10.1109/WACV48630.2021.00084
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The prediction of humans' short-term trajectories has advanced significantly with the use of powerful sequential modeling and rich environment feature extraction. However, long-term prediction is still a major challenge for the current methods as the errors could accumulate along the way. Indeed, consistent and stable prediction far to the end of a trajectory inherently requires deeper analysis into the overall structure of that trajectory, which is related to the pedestrian's intention on the destination of the journey. In this work, we propose to model a hypothetical process that determines pedestrians' goals and the impact of such process on long-term future trajectories. We design Goal-driven Trajectory Prediction model - a dual-channel neural network that realizes such intuition. The two channels of the network take their dedicated roles and collaborate to generate future trajectories. Different than conventional goal-conditioned, planning-based methods, the model architecture is designed to generalize the patterns and work across different scenes with arbitrary geometrical and semantic structures. The model is shown to outperform the state-of-the-art in various settings, especially in large prediction horizons. This result is another evidence for the effectiveness of adaptive structured representation of visual and geometrical features in human behavior analysis.
引用
收藏
页码:796 / 805
页数:10
相关论文
共 50 条
  • [1] Goal-driven long-term marine vessel trajectory prediction with a memory-enhanced network
    Zhang, Xiliang
    Liu, Jin
    Chen, Chengcheng
    Wei, Lai
    Wu, Zhongdai
    Dai, Wenjuan
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 263
  • [2] Stepwise Goal-Driven Networks for Trajectory Prediction
    Wang, Chuhua
    Wang, Yuchen
    Xu, Mingze
    Crandall, David J.
    arXiv, 2021,
  • [3] Stepwise Goal-Driven Networks for Trajectory Prediction
    Wang, Chuhua
    Wang, Yuchen
    Xu, Mingze
    Crandall, David J.
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02): : 2716 - 2723
  • [4] Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction
    Chiara, Luigi Filippo
    Coscia, Pasquale
    Das, Sourav
    Calderara, Simone
    Cucchiara, Rita
    Ballan, Lamberto
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 2517 - 2526
  • [5] Pedestrian trajectory prediction using goal-driven and dynamics-based deep learning framework
    Wang, Honghui
    Zhi, Weiming
    Batista, Gustavo
    Chandra, Rohitash
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 271
  • [6] Goal-driven modeling
    Bock, C
    JOOP-JOURNAL OF OBJECT-ORIENTED PROGRAMMING, 2000, 13 (05): : 48 - +
  • [7] Goal-Driven Optimization
    Chen, Wenqing
    Sim, Melvyn
    OPERATIONS RESEARCH, 2009, 57 (02) : 342 - 357
  • [8] Goal-driven modeling
    Bock, Conrad
    JOOP - Journal of Object-Oriented Programming, 2000, 13 (05): : 48 - 56
  • [9] Learning a Memory-Enhanced Multi-Stage Goal-Driven Network for Egocentric Trajectory Prediction
    Wu, Xiuen
    Li, Sien
    Wang, Tao
    Xu, Ge
    Papageorgiou, George
    BIOMIMETICS, 2024, 9 (08)
  • [10] Long-term trajectory and signal behaviour prediction
    Castellanos, J.
    Leiva, S.
    Mingo, L.F.
    Rios, J.
    1996, IDG, Prague, Czech Republic (06)