行人轨迹预测方法综述

被引:10
|
作者
李琳辉 [1 ,2 ]
周彬 [1 ]
任威威 [1 ]
连静 [1 ,2 ]
机构
[1] 大连理工大学汽车工程学院
[2] 大连理工大学工业装备结构分析国家重点实验室
基金
中央高校基本科研业务费专项资金资助;
关键词
轨迹预测; 深度学习; 序列决策;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
随着深度学习技术的突破和大型数据集的提出,行人轨迹预测的准确度已经成为人工智能领域的研究热点之一。主要对行人轨迹预测的技术分类和研究现状进行详细的综述。根据模型建模方式的不同,将现有方法分为基于浅层学习的轨迹预测方法和基于深度学习的轨迹预测方法,分析了每类方法中具有代表性的算法的效果及优缺点,归纳了当前主流的轨迹预测公开数据集,并在数据集中对比了主流轨迹预测方法的性能,最后对轨迹预测技术面临的挑战与发展趋势进行了展望。
引用
收藏
页码:399 / 411
页数:13
相关论文
共 17 条
  • [1] Human motion trajectory prediction: a survey[J] . Andrey Rudenko,Luigi Palmieri,Michael Herman,Kris M Kitani,Dariu M Gavrila,Kai O Arras.The International Journal of Robotics Research . 2020 (8)
  • [2] Stochastic trajectory prediction with social graph network[J] . Lidan Zhang,Qi She,Ping Guo.CoRR . 2019
  • [3] Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs[J] . Javad Amirian,Jean-Bernard Hayet,Julien Pettré.CoRR . 2019
  • [4] Situation-Aware Pedestrian Trajectory Prediction with Spatio-Temporal Attention Model[J] . Sirin Haddad,Meiqing Wu,He Wei,Siew Kei Lam.CoRR . 2019
  • [5] The walking behaviour of pedestrian social groups and its impact on crowd dynamics[J] . Mehdi Moussa?d,Niriaska Perozo,Simon Garnier,Dirk Helbing,Guy Theraulaz.PLoS ONE . 2017 (4)
  • [6] Semi-Supervised Classification with Graph Convolutional Networks[J] . Thomas N. Kipf,Max Welling.CoRR . 2016
  • [7] Variational Graph Auto-Encoders[J] . Thomas N. Kipf,Max Welling.CoRR . 2016
  • [8] A survey on motion prediction and risk assessment for intelligent vehicles
    Lefèvre S.
    Vasquez D.
    Laugier C.
    [J]. ROBOMECH Journal, 2014, 1 (01):
  • [9] Will the Pedestrian Cross? A Study on Pedestrian Path Prediction
    Keller, Christoph G.
    Gavrila, Dariu M.
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2014, 15 (02) : 494 - 506
  • [10] Neural Machine Translation by Jointly Learning to Align and Translate[J] . Dzmitry Bahdanau,Kyunghyun Cho,Yoshua Bengio.CoRR . 2014