Advertisement

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12357)

Abstract

Understanding crowd motion dynamics is critical to real-world applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively modeling the socially aware crowd spatial interaction and complex temporal dependencies. We believe attention is the most important factor for trajectory prediction. In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms. STAR models intra-graph crowd interaction by TGConv, a novel Transformer-based graph convolution mechanism. The inter-graph temporal dependencies are modeled by separate temporal Transformers. STAR captures complex spatio-temporal interactions by interleaving between spatial and temporal Transformers. To calibrate the temporal prediction for the long-lasting effect of disappeared pedestrians, we introduce a read-writable external memory module, consistently being updated by the temporal Transformer. We show that with only attention mechanism, STAR achieves the state-of-the-art performance on 5 commonly used real-world pedestrian prediction datasets (code available at https://github.com/Majiker/STAR).

Keywords

Trajectory prediction Transformer Graph neural networks 

Supplementary material

504453_1_En_30_MOESM1_ESM.pdf (769 kb)
Supplementary material 1 (pdf 768 KB)

References

  1. 1.
    Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: Human trajectory prediction in crowded spaces. In: CVPR (2016)Google Scholar
  2. 2.
    Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
  3. 3.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
  4. 4.
    Battaglia, P., Pascanu, R., Lai, M., Rezende, D.J., et al.: Interaction networks for learning about objects, relations and physics. In: Advances in Neural Information Processing Systems (2016)Google Scholar
  5. 5.
    Chen, B., Barzilay, R., Jaakkola, T.: Path-augmented graph transformer network (2019).  https://doi.org/10.26434/chemrxiv.8214422
  6. 6.
    Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (2014)Google Scholar
  7. 7.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)
  8. 8.
    Cui, Z., Henrickson, K., Ke, R., Wang, Y.: Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting. IEEE Trans. Intell. Transp. Syst. (2019)Google Scholar
  9. 9.
    Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems (2016)Google Scholar
  10. 10.
    Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
  11. 11.
    Fan, W., et al.: Graph neural networks for social recommendation. In: WWW (2019)Google Scholar
  12. 12.
    Fang, K., Toshev, A., Fei-Fei, L., Savarese, S.: Scene memory transformer for embodied agents in long-horizon tasks. In: CVPR (2019)Google Scholar
  13. 13.
    Ferrer, G., Garrell, A., Sanfeliu, A.: Robot companion: a social-force based approach with human awareness-navigation in crowded environments. In: IROS (2013)Google Scholar
  14. 14.
    Förster, A., Graves, A., Schmidhuber, J.: RNN-based learning of compact maps for efficient robot localization. In: ESANN (2007)Google Scholar
  15. 15.
    Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: ICML (2017)Google Scholar
  16. 16.
    Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., Alahi, A.: Social Gan: socially acceptable trajectories with generative adversarial networks. In: CVPR (2018)Google Scholar
  17. 17.
    Hajiramezanali, E., Hasanzadeh, A., Narayanan, K., Duffield, N., Zhou, M., Qian, X.: Variational graph recurrent neural networks. In: Advances in Neural Information Processing Systems (2019)Google Scholar
  18. 18.
    Helbing, D., Buzna, L., Johansson, A., Werner, T.: Self-organized pedestrian crowd dynamics: experiments, simulations, and design solutions. Transp. Sci. 39, 1–24 (2005)CrossRefGoogle Scholar
  19. 19.
    Helbing, D., Molnar, P.: Social force model for pedestrian dynamics. Phys. Rev. E 51, 4282 (1995)CrossRefGoogle Scholar
  20. 20.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. (1997)Google Scholar
  21. 21.
    Huang, Y., Bi, H., Li, Z., Mao, T., Wang, Z.: Stgat: modeling spatial-temporal interactions for human trajectory prediction. In: ICCV (2019)Google Scholar
  22. 22.
    Ivanovic, B., Pavone, M.: The trajectron: probabilistic multi-agent trajectory modeling with dynamic spatiotemporal graphs. In: ICCV (2019)Google Scholar
  23. 23.
    Karkus, P., Ma, X., Hsu, D., Kaelbling, L.P., Lee, W.S., Lozano-Pérez, T.: Differentiable algorithm networks for composable robot learning. arXiv preprint arXiv:1905.11602 (2019)
  24. 24.
    Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
  25. 25.
    Kuderer, M., Kretzschmar, H., Sprunk, C., Burgard, W.: Feature-based prediction of trajectories for socially compliant navigation. In: RSS (2012)Google Scholar
  26. 26.
    Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)
  27. 27.
    Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015)
  28. 28.
    Li, Y., Wu, J., Tedrake, R., Tenenbaum, J.B., Torralba, A.: Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids. arXiv preprint arXiv:1810.01566 (2018)
  29. 29.
    Lim, B., Arik, S.O., Loeff, N., Pfister, T.: Temporal fusion transformers for interpretable multi-horizon time series forecasting. arXiv preprint arXiv:1912.09363 (2019)
  30. 30.
    Liu, J., et al.: Transformer-based capsule network for stock movement prediction. In: Proceedings of the First Workshop on Financial Technology and Natural Language Processing (2019)Google Scholar
  31. 31.
    Liu, K., et al.: Chemi-Net: a molecular graph convolutional network for accurate drug property prediction. Int. J. Mol. Sci. 20, 3389 (2019)CrossRefGoogle Scholar
  32. 32.
    Löhner, R.: On the modeling of pedestrian motion. Appl. Math. Model. 34, 366–382 (2010)MathSciNetCrossRefGoogle Scholar
  33. 33.
    Luo, Y., Cai, P.: Gamma: A general agent motion prediction model for autonomous driving. arXiv preprint arXiv:1906.01566 (2019)
  34. 34.
    Luo, Y., Cai, P., Bera, A., Hsu, D., Lee, W.S., Manocha, D.: Porca: modeling and planning for autonomous driving among many pedestrians. IEEE Robot. Autom. Lett. 3, 3418–3425 (2018)CrossRefGoogle Scholar
  35. 35.
    Ma, X., Gao, X., Chen, G.: Beep: a Bayesian perspective early stage event prediction model for online social networks. In: ICDM (2017)Google Scholar
  36. 36.
    Ma, X., Karkus, P., Hsu, D., Lee, W.S.: Particle filter recurrent neural networks. arXiv preprint arXiv:1905.12885 (2019)
  37. 37.
    Ma, X., Karkus, P., Hsu, D., Lee, W.S., Ye, N.: Discriminative particle filter reinforcement learning for complex partial observations. arXiv preprint arXiv:2002.09884 (2020)
  38. 38.
    Ma, Y., Zhu, X., Zhang, S., Yang, R., Wang, W., Manocha, D.: Trafficpredict: trajectory prediction for heterogeneous traffic-agents. In: AAAI (2019)Google Scholar
  39. 39.
    Miao, Y., Gowayyed, M., Metze, F.: EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding. In: ASRU (2015)Google Scholar
  40. 40.
    Sadeghian, A., Kosaraju, V., Sadeghian, A., Hirose, N., Rezatofighi, H., Savarese, S.: Sophie: an attentive Gan for predicting paths compliant to social and physical constraints. In: CVPR (2019)Google Scholar
  41. 41.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems (2014)Google Scholar
  42. 42.
    Van Den Berg, J., Guy, S.J., Lin, M., Manocha, D.: Reciprocal n-body collision avoidance. In: Pradalier, C., Siegwart, R., Hirzinger, G. (eds.) Robotics Research. Springer Tracts in Advanced Robotics, vol. 70, pp. 3–19. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-19457-3_1CrossRefGoogle Scholar
  43. 43.
    Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)Google Scholar
  44. 44.
    Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
  45. 45.
    Vemula, A., Muelling, K., Oh, J.: Social attention: modeling attention in human crowds. In: ICRA (2018)Google Scholar
  46. 46.
    Xiong, W., Wu, L., Alleva, F., Droppo, J., Huang, X., Stolcke, A.: The Microsoft 2017 conversational speech recognition system. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (2018)Google Scholar
  47. 47.
    Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018)
  48. 48.
    Xu, Y., Piao, Z., Gao, S.: Encoding crowd interaction with deep neural network for pedestrian trajectory prediction. In: CVPR (2018)Google Scholar
  49. 49.
    Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems (2019)Google Scholar
  50. 50.
    Yi, S., Li, H., Wang, X.: Pedestrian behavior understanding and prediction with deep neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 263–279. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_16CrossRefGoogle Scholar
  51. 51.
    Young, T., Hazarika, D., Poria, S., Cambria, E.: Recent trends in deep learning based natural language processing. IEEE Comput. Intel. Mag. 13, 55–75 (2018)CrossRefGoogle Scholar
  52. 52.
    Zhang, P., Ouyang, W., Zhang, P., Xue, J., Zheng, N.: SR-LSTM: state refinement for LSTM towards pedestrian trajectory prediction. In: CVPR (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.SenseTime ResearchBeijingChina
  2. 2.National University of SingaporeSingaporeSingapore

Personalised recommendations