北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (5): 1-6.

• 论文 •    下一篇

一种多精度交互的行人轨迹预测

刘绍华1,孙靖凯1,2,王奕苏1,2,刘海波1,2,毛天露2   

  1. 1. 北京邮电大学 电子工程学院
    2. 中国科学院 计算技术研究所
  • 收稿日期:2021-11-11 修回日期:2021-12-29 出版日期:2022-10-28 发布日期:2022-11-01
  • 通讯作者: 毛天露 E-mail:ltm@ ict. ac. cn
  • 基金资助:
    国家自然科学基金项目

Human Trajectory Prediction by Multi-resolution Interaction

LIU Shaohua1, SUN Jingkai1,2, WANG Yisu1,2, LIU Haibo1,2, MAO Tianlu2 #br#   

  • Received:2021-11-11 Revised:2021-12-29 Online:2022-10-28 Published:2022-11-01

摘要: 在机器人导航和自动驾驶等应用中,行人轨迹预测是一项重要且富有挑战性的任务,其中建模行人之间的交互行为是最具挑战性的任务之一现有模型大多采用注意力机制进行成对的交互建模,但是,当场景中行人过多时,这种模型存在交互建模冗余的问题,并且可能忽略不同距离行人的交互差异性为了解决这些问题,提出了一种多精度的全局局部模型,该模型包含一个新颖的多精度全局交互子网络来捕获全局交互,以及一个额外的局部交互子网络来模拟局部的行人交互; 同时,引入了时间域注意力机制,用来融合不同时刻的交互信息实验结果表明,与对比模型相比,所提模型在 2 个公开数据集上取得了更好的性能

关键词: 轨迹预测, 社会模型, 动作规划

Abstract: Human trajectory prediction is an essential and challenging task in robot navigation and autonomous driving applications. One of the most challenging tasks is to model the interaction between pedestrians. Pairwise attention is used by most of the existing models to model the interaction. However, when there are too many pedestrians in the scene, these methods have redundancy in interaction modeling and ignore the interaction differences of pedestrians at different distances. To address these challenges, a multi-resolution global-local model is proposed, which contains a novel multi-region interaction sub-network to capture the global interaction and an additional local interaction sub-network to model pedestrians' interactions in the local neighborhood. In the meantime, the temporal attention mechanism is introduced in the proposed model to fuse the interactive information of different time steps. The experimental results show that compared with previous models, the proposed model achieves better performance on two publicly available datasets.

Key words: trajectory prediction, social model, motion planning

中图分类号: