Graph Convolution Networks for Probabilistic Modeling of Driving Acceleration

被引:6
作者
Su, Jianyu [1 ]
Beling, Peter A. [1 ]
Guo, Rui [2 ]
Han, Kyungtae [2 ]
机构
[1] Univ Virginia, Dept Engn Syst & Environm, 151 Engineers Way, Charlottesville, VA 22904 USA
[2] Toyota InfoTech Labs, 465 N Bernardo Ave, Mountain View, CA USA
来源
2020 IEEE 23RD INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC) | 2020年
关键词
D O I
10.1109/itsc45102.2020.9294294
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The ability to model and predict ego-vehicle's surrounding traffic is crucial for autonomous pilots and intelligent driver-assistance systems. Acceleration prediction is important as one of the major components of traffic prediction. This paper proposes novel approaches to the acceleration prediction problem. By representing spatial relationships between vehicles with a graph model, we build a generalized acceleration prediction framework. This paper studies the effectiveness of proposed Graph Convolution Networks, which operate on graphs predicting the acceleration distribution for vehicles driving on highways. We further investigate prediction improvement through integrating of Recurrent Neural Networks to disentangle the temporal complexity inherent in the traffic data. Results from simulation with comprehensive performance metrics support that our proposed networks outperform state-of-the-art methods in generating realistic trajectories over a prediction horizon.
引用
收藏
页数:8
相关论文
共 28 条
  • [1] Abadi M, 2016, ACM SIGPLAN NOTICES, V51, P1, DOI [10.1145/2951913.2976746, 10.1145/3022670.2976746]
  • [2] Altché F, 2017, IEEE INT C INTELL TR
  • [3] [Anonymous], 1996, Automatic Speech and Speaker Recognition
  • [4] Bahdanau D, 2016, Arxiv, DOI [arXiv:1409.0473, 10.48550/arXiv.1409.0473, DOI 10.48550/ARXIV.1409.0473]
  • [5] Bengio Y, 2013, INT CONF ACOUST SPEE, P8624, DOI 10.1109/ICASSP.2013.6639349
  • [6] Bishop Christopher M, 1994, MIXTURE DENSITY NETW
  • [7] TRAFFIC DYNAMICS - STUDIES IN CAR FOLLOWING
    CHANDLER, RE
    HERMAN, R
    MONTROLL, EW
    [J]. OPERATIONS RESEARCH, 1958, 6 (02) : 165 - 184
  • [8] Colyar J., 2006, U.s. highway 80 dataset
  • [9] Diehl F, 2019, IEEE INT VEH SYM, P695, DOI 10.1109/IVS.2019.8814066
  • [10] Fout A, 2017, ADV NEUR IN, V30