Let's Connect
Follow Us
Watch Us
(+385) 1 2380 262
journal.prometfpz.unizg.hr
Promet - Traffic&Transportation journal

Accelerating Discoveries in Traffic Science

Accelerating Discoveries in Traffic Science

PUBLISHED
31.10.2024
LICENSE
Copyright (c) 2024 Xuelong ZHENG, Xuemei CHEN, Yaohan JIA

Vehicle Trajectory Prediction Based on GAT and LSTM Networks in Urban Environments

Authors:Xuelong ZHENG, Xuemei CHEN, Yaohan JIA

Abstract

Vehicle trajectory prediction plays a critical role before the decision planning of autonomous vehicles in complex and dynamic traffic environments. It helps autonomous vehicles better understand the traffic environments and ensure safe and efficient tasks. In this study, a hierarchical trajectory prediction method is proposed. The graph attention network (GAT) model was selected to estimate the interactions of surrounding vehicles. Considering the behaviour of surrounding agents, the future trajectory of the target vehicle is predicted based on the long short-term memory network (LSTM). The model has been validated in real traffic environments. By comparing the accuracy and real-time performance of target vehicle trajectory prediction, the proposed model is superior to the traditional single trajectory prediction model. The results of this study will provide new modelling ideas and a theoretical basis for the vehicle trajectory prediction in urban traffic environments.

Keywords:autonomous vehicle, trajectory prediction, hierarchical, long short-term memory network, graph attention network

References

  1. [1] Jiang Y, et al. Vehicle trajectory prediction considering driver uncertainty and vehicle dynamics based on dynamic Bayesian network. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2023;53:689–703. DOI: 10.1109/TSMC.2022.3186639.
  2. [2] Wang K, et al. LSTM-based prediction method of surrounding vehicle trajectory. 2022 International Conference on Artificial Intelligence in Everything (AIE), Lefkosa, Cyprus. 2022. p. 100-105. DOI: 10.1109/AIE57029.2022.00026.
  3. [3] Huang B, Li K, Wang J. Vehicle trajectory prediction by integrating physics-and maneuver-based approaches using interactive multiple models. IEEE Transactions on Industrial Electronics. 2017;65(7):5999–6008. DOI: 10.1109/TIE.2017.2782236.
  4. [4] Wang Y, et al. Trajectory planning and safety assessment of autonomous vehicles based on motion prediction and model predictive control. IEEE Transactions on Vehicular Technology. 2019;68(9):8546–8556. DOI: 10.1109/TVT.2019.2930684.
  5. [5] Wang Y, Wang C, Zhao W, Xu C. Decision-making and planning method for autonomous vehicles based on motivation and risk assessment. IEEE Transactions on Vehicular Technology. 2021;70(1):107–120. DOI: 10.1109/TVT.2021.3049794.
  6. [6] Zhang S, Zhi Y, He R, Li J. Research on traffic vehicle behavior prediction method based on game theory and HMM. IEEE Access. 2020;8:30210–30222. DOI: 10.1109/ACCESS.2020.2971705.
  7. [7] Mercat J, et al. Multi-head attention for multi-modal joint vehicle motion forecasting. In 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE. 2020. p. 9638–9644.
  8. [8] Hasan F, Huang H. Mals-net: A multi-head attention-based lstm sequence-to-sequence network for socio-temporal interaction modelling and trajectory prediction. Sensors. 2023;23(1):530. DOI: 10.3390/s23010530.
  9. [9] Barth A, Franke U. Where will the oncoming vehicle be the next second? 2008 IEEE Intelligent Vehicles Symposium (IV). New York: IEEE. 2008:1068–1073.
  10. [10] Carvalho A, et al. Stochastic predictive control of autonomous vehicles in uncertain environments. 12th International Symposium on Advanced vehicle control. 2014:712–719.
  11. [11] Houenou A, et al. vehicle trajectory prediction based on motion model and maneuver recognition. 2013 IEEE International Conference on Intelligent Robots and Systems. New York: IEEE.2013;4363–4369.
  12. [12] Rafael TM, Miguel ZI. IMM-based lane-change prediction in highways with low-cost GPS/INS. 2009 IEEE Transactions on Intelligent Transportation Systems, 2009;10(1):180–185. DOI: 10.1109/TITS.2008.2011691.
  13. [13] Enke K. Possibilities for improving safety within the driver vehicle environment control loop. 7th International Conference on Experimental Safety Vehicles Proceeding. 1979;789–802.
  14. [14] Chovan JD. Examination of lane change crashes and potential IVHS countermeasures. America: National Highway Traffic Safety Administration, 1994.
  15. [15] Kim S, Jeon H, Choi JW, Kum D. Diverse multiple trajectory prediction using a two-stage prediction network trained with lane loss. IEEE Robotics and Automation Letters. 2023;8(4):2038–2045.
  16. [16] Barth A, Franke U. Where will the oncoming vehicle be the next second? 2008 IEEE Intelligent Vehicles Symposium (IV). New York: IEEE. 2008. p. 1068–1073.
  17. [17] Carvalho A, et al. Stochastic predictive control of autonomous vehicles in uncertain environments. 12th International Symposium on Advanced Vehicle Control. 2014. p. 712–719.
  18. [18] Tay C, Mekhnacha K, Laugier C. Probabilistic vehicle motion modeling and risk estimation. Handbook of Intelligent Vehicles. 2012;1479–1516. DOI: 10.1007/978-0-85729-085-4_57.
  19. [19] Streubel T, Hoffmann KH. Prediction of driver intended path at intersections. 2014 IEEE Intelligent Vehicles Symposium Proceedings. IEEE. 2014. p. 134–139.
  20. [20] Guo Y, et al. Modeling multi-vehicle interaction scenarios using gaussian random field. In 2019 IEEE Intelligent Transportation Systems Conference (ITSC). IEEE. 2019. p. 3974–3980.
  21. [21] Goli SA, Far BH, Fapojuwo A. Vehicle trajectory prediction with gaussian process regression in connected vehicle environment. 2018 IEEE Intelligent Vehicles Symposium. Piscataway: IEEE Press. 2018. p. 550–555.
  22. [22] Tran Q, Firl J. Online maneuver recognition and multimodal trajectory prediction for intersection assistance using non-parametric regression. 2014 IEEE Intelligent Vehicles Symposium Proceedings. IEEE. 2014. p. 918–923.
  23. [23] Li J, et al. Generic probabilistic interactive situation recognition and prediction: From virtual to real. 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2018. p. 3218–3224.
  24. [24] Altchéa F, Fortelle AL. An LSTM network for highway trajectory prediction. IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). Yokohama: IEEE Press. 2017. p. 123–128.
  25. [25] Kim BD, et a1. Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network. IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). Yokohama: IEEE Press. 2017. p. 399–404.
  26. [26] Park SH, et al. Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture. 2018 IEEE Intelligent Vehicles Symposium(IV). New York: IEEE Press. 2018. p. 1672–1678.
  27. [27] Deo N, Trivedi MM. Convolutional social pooling for vehicle trajectory prediction. 2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE Press. 2018. p. 1468–1476.
  28. [28] Karatzolou A, Jablonski A, Beigl M. A seq2seq learning approach for modeling semantic trajectories and predicting the next location. The 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York: ACM Press. 2018. p. 528–531.
  29. [29] Goodfellow I, et al. Generative adversarial nets. Conference and Workshop on Neural Information Processing Systems. New York: Curran Associates Press. 2014. p. 2672–2680.
  30. [30] Kipf T, Welling M. Variational graph auto-encoders. Arxiv Preprint, 2016. DOI: 10.48550/arXiv.1611.07308.
  31. [31] Khandelwal S, et al. What-if motion prediction for autonomous driving. Arxiv Preprint, 2020. DOI: 10.48550/arXiv.2008.10587.
  32. [32] Liang M, et al. Learning lane graph representations for motion forecasting. European Conference on Computer Vision. Germany: Springer. 2020. p. 541–556.
  33. [33] Gao J, et al. VectorNet: Encoding HD maps and agent dynamics from vectorized representation. IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. p. 11525–11533.
  34. [34] Zhao H, et al. TNT: target-driven trajectory prediction. Conference on Robot Learning. 2020.
  35. [35] Velikovi P, et al. Graph attention networks. International Conference on Learning Representations, Vancouver, Canada. 2018.
  36. [36] Vaswani, A et al. Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems. December 2017. p. 6000–6010.
  37. [37] Krajewski R, et al. The highD dataset: A drone dataset of naturalistic vehicle trajectories on German highways for validation of highly automated driving systems. 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE. 2018. p. 2118-2125.
  38. [38] Chang MF et al. Argoverse: 3d tracking and forecasting with rich maps. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019. p. 8748-8757.
  39. [39] Winkler M . What is a Savitzky-Golay Filter?. IEEE Signal Processing Magazine. 2011;4:111–117.
  40. [40] Monti F, Otness K, Bronstein MM. MOTIFNET: a motif-based graph convolutional network for directed graphs. 2018 IEEE Data Science Workshop (DSW), Lausanne, Switzerland. 2018. p. 225–228.
  41. [41] Brody S, Alon U, Yahav E. How attentive are graph attention networks. International Conference on Learning Representations, Vienna, Austria. 2021.
  42. [42] Jiang B, et al. Acquisition of localization confidence for accurate object detection. Computer Vision – ECCV. 2018;816–832. DOI:10.48550/arXiv.1807.11590.
  43. [43] Lefkopoulos V, Menner M, Domahidi A, Zeilinger MN. Interaction-aware motion prediction for autonomous driving: A multiple model Kalman filtering scheme. IEEE Robotics and Automation Letters. 2021;6(1):80–87. DOI: 10.1109/LRA.2020.3032079.
  44. [44] Penngian H, et al. STF: Spatial temporal fusion for trajectory prediction. Computer Vision and Pattern Recognition. 2023. DOI: 10.1109/M2VIP58386.2023.10413434.
Show more


Accelerating Discoveries in Traffic Science |
2024 © Promet - Traffic&Transportation journal