Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Joint Pedestrian Trajectory Prediction through Posterior Sampling (2404.00237v2)

Published 30 Mar 2024 in cs.RO

Abstract: Joint pedestrian trajectory prediction has long grappled with the inherent unpredictability of human behaviors. Recent investigations employing variants of conditional diffusion models in trajectory prediction have exhibited notable success. Nevertheless, the heavy dependence on accurate historical data results in their vulnerability to noise disturbances and data incompleteness. To improve the robustness and reliability, we introduce the Guided Full Trajectory Diffuser (GFTD), a novel diffusion model framework that captures the joint full (historical and future) trajectory distribution. By learning from the full trajectory, GFTD can recover the noisy and missing data, hence improving the robustness. In addition, GFTD can adapt to data imperfections without additional training requirements, leveraging posterior sampling for reliable prediction and controllable generation. Our approach not only simplifies the prediction process but also enhances generalizability in scenarios with noise and incomplete inputs. Through rigorous experimental evaluation, GFTD exhibits superior performance in both trajectory prediction and controllable generation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. From goals, waypoints & paths to long term human trajectory forecasting. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 15233–15242, 2021.
  2. Agentformer: Agent-aware transformers for socio-temporal multi-agent forecasting. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9813–9823, 2021.
  3. Stepwise goal-driven networks for trajectory prediction. IEEE Robotics and Automation Letters, 7(2):2716–2723, 2022.
  4. Human trajectory prediction via neural social physics. In European conference on computer vision, pages 376–394. Springer, 2022.
  5. View vertically: A hierarchical network for trajectory prediction via fourier spectrums. In European Conference on Computer Vision, pages 682–700. Springer, 2022.
  6. Joint metrics matter: A better standard for trajectory forecasting. arXiv preprint arXiv:2305.06292, 2023.
  7. Pedestrian trajectory prediction with convolutional neural networks. Pattern Recognition, 121:108252, 2022.
  8. Robust trajectory prediction against adversarial attacks. In Conference on Robot Learning, pages 128–137. PMLR, 2023.
  9. Trajectory prediction from a mass of sparse and missing external sensor data. In 2019 20th IEEE International conference on mobile data management (MDM), pages 310–319. IEEE, 2019.
  10. Reconstruction of missing trajectory data: a deep learning approach. In 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pages 1–6. IEEE, 2020.
  11. Imitative non-autoregressive modeling for trajectory forecasting and imputation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12736–12745, 2020.
  12. Uncovering the missing pattern: Unified framework towards trajectory imputation and prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9632–9643, 2023.
  13. Stochastic trajectory prediction via motion indeterminacy diffusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17113–17122, 2022.
  14. Leapfrog diffusion model for stochastic trajectory prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5517–5526, 2023.
  15. Elucidating the design space of diffusion-based generative models. Advances in Neural Information Processing Systems, 35:26565–26577, 2022.
  16. Diffusion posterior sampling for general noisy inverse problems. arXiv preprint arXiv:2209.14687, 2022.
  17. Tweedie moment projected diffusions for inverse problems. arXiv preprint arXiv:2310.06721, 2023.
  18. Diffusion models as plug-and-play priors. Advances in Neural Information Processing Systems, 35:14715–14728, 2022.
  19. Planning with diffusion for flexible behavior synthesis. arXiv preprint arXiv:2205.09991, 2022.
  20. Guided conditional diffusion for controllable traffic simulation. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 3560–3566. IEEE, 2023.
  21. Social physics informed diffusion model for crowd simulation. arXiv preprint arXiv:2402.06680, 2024.
  22. Motiondiffuser: Controllable multi-agent motion prediction using diffusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9644–9653, 2023.
  23. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840–6851, 2020.
  24. Repaint: Inpainting using denoising diffusion probabilistic models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11461–11471, 2022.
  25. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695, 2022.
  26. Eigentrajectory: Low-rank descriptors for multi-modal trajectory forecasting. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10017–10029, 2023.
  27. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.
  28. Social gan: Socially acceptable trajectories with generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2255–2264, 2018.
  29. Pecnet: A deep multi-label segmentation network for eosinophilic esophagitis biopsy diagnostics. arXiv preprint arXiv:2103.02015, 2021.
  30. Remember intentions: Retrospective-memory-based trajectory prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6488–6497, 2022.
  31. Crowds by example. In Computer graphics forum, volume 26, pages 655–664. Wiley Online Library, 2007.
  32. You’ll never walk alone: Modeling social behavior for multi-target tracking. In 2009 IEEE 12th international conference on computer vision, pages 261–268. IEEE, 2009.
  33. It is not the journey but the destination: Endpoint conditioned trajectory prediction. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16, pages 759–776. Springer, 2020.
  34. Diganta Misra. Mish: A self regularized non-monotonic activation function. arXiv preprint arXiv:1908.08681, 2019.
  35. Efficient diffusion training via min-snr weighting strategy. arXiv preprint arXiv:2303.09556, 2023.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets