A Review of Trajectory Prediction for Autonomous Vehicles Based on Generative Models

XVII International Conference on Systems, Automatic Control and Measurements, SAUM 2024 (pp. 80-83)

АУТОР(И) / AUTHOR(S): Jianxun Cui , Huidong Gao , Miroslav Milovanović , Staniša Perić , Marko Milojković

Download Full Pdf  

DOI:  10.46793/SAUM24.080C

САЖЕТАК / ABSTRACT:

With the acceleration of urbanization, the technology of autonomous vehicle trajectory predictionis crucial for improving traffic conditions. This paper provides a comprehensive review of autonomous vehicle trajectory prediction methods, briefly summarizesthe traditional model-based methods and data-driven methods. And emphatically introduces trajectory prediction models based on generation, such as Generative Adversarial Network (GAN), Variational Auto-Encoder (VAE) and diffusion models. It analyzes their principles, characteristics, and application cases. In the end this paper prospects future research directions, including enhancing accuracy and stability, fusing multi-source data, reducing computational costs, and improving interpretability.

КЉУЧНЕ РЕЧИ / KEYWORDS:

autonomous vehicles, vehicle trajectory prediction, deep learning, generative models

ЛИТЕРАТУРА / REFERENCES:

  1. Ren, Bingtao, Weiwen Deng, and Bai Xuesong. „A Review of Simulation Scene Construction Technologies for Intelligent Driving Testing.“Journal of Image and Graphics, 2021.
  2. Li, Wei, Jing Wang, and Duan Jianmin. „Lane-changing trajectory planning for intelligent vehicles based on polynomials.“Computer Engineering and Applications, 2012.
  3. Salzmann, Tim, et al. „Trajectron++: Dynamically-feasible trajectory forecasting with heterogeneous data.“ Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVIII 16. Springer International Publishing, 2020.
  4. Alahi, Alexandre, et al. „Social lstm: Human trajectory prediction in crowded spaces.“ Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
  5. Chandra, Rohan, et al. „Traphic: Trajectory prediction in dense and heterogeneous traffic using weighted interactions.“ Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019.
  6. Huang, Renbo, et al. „A Review of Deep Learning-Based Vehicle Motion Prediction for Autonomous Driving.“ Sustainability 15.20 (2023): 14716.
  7. Gupta, Agrim, et al. „Social gan: Socially acceptable trajectories with generative adversarial networks.“ Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
  8. Sun Yasheng, et al. „Pedestrian trajectory prediction generation model based on attention mechanism.“Journal of Computer Applications, 2019.
  9. de Brito, Bruno Ferreira, et al. „Social-vrnn: One-shot multi-modal trajectory prediction for interacting pedestrians.“ Conference on Robot Learning. PMLR, 2021.
  10. Huang, Lei, et al. „STI-GAN: Multimodal pedestrian trajectory prediction using spatiotemporal interactions and a generative adversarial network.“ IEEE Access 9 (2021): 50846-50856.
  11. Gupta, Agrim, et al. „Social gan: Socially acceptable trajectories with generative adversarial networks.“ Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
  12. Chen, Xinyu, et al. „TrajVAE: A Variational AutoEncoder model for trajectory generation.“ Neurocomputing 428 (2021): 332-339.
  13. Ding, Wenhao, Wenshuo Wang, and Ding Zhao. „A multi-vehicle trajectories generator to simulate vehicle-to-vehicle encountering scenarios.“ 2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019.
  14. Yin, Zhao-Heng, et al. „Diverse critical interaction generation for planning and planner evaluation.“ 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2021.
  15. Feng, Xidong, et al. „Vehicle trajectory prediction using intention-based conditional variational autoencoder.“ 2019 IEEE Intelligent Transportation Systems Conference (ITSC). IEEE, 2019.
  16. Ding, Wenhao, Mengdi Xu, and Ding Zhao. „Cmts: A conditional multiple trajectory synthesizer for generating safety-critical driving scenarios.“ 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2020.
  17. Janner, Michael, et al. „Planning with diffusion for flexible behavior synthesis.“ arXiv preprint arXiv:2205.09991 (2022).
  18. Zhong, Ziyuan, et al. „Guided conditional diffusion for controllable traffic simulation.“ 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2023.
  19. Zhong, Ziyuan, et al. „Language-guided traffic simulation via scene-level diffusion.“ Conference on Robot Learning. PMLR, 2023.