Diffusion^2: Dual Diffusion Model with Uncertainty-Aware Adaptive Noise for Momentary Trajectory Prediction

• URL: http://arxiv.org/abs/2510.04365v1
• Date: Sun, 05 Oct 2025 21:19:33 GMT
• Title: Diffusion^2: Dual Diffusion Model with Uncertainty-Aware Adaptive Noise for Momentary Trajectory Prediction
• Authors: Yuhao Luo, Yuang Zhang, Kehua Chen, Xinyu Zheng, Shucheng Zhang, Sikai Chen, Yinhai Wang,
• Abstract summary: Earlier studies primarily utilized sufficient observational data to predict future trajectories.<n>In real-world scenarios, such as pedestrians suddenly emerging from blind spots, sufficient observational data is often unavailable.<n>We propose a novel framework termed Diffusion2, tailored for momentary trajectory prediction.
• Score: 18.85021503551474
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate pedestrian trajectory prediction is crucial for ensuring safety and efficiency in autonomous driving and human-robot interaction scenarios. Earlier studies primarily utilized sufficient observational data to predict future trajectories. However, in real-world scenarios, such as pedestrians suddenly emerging from blind spots, sufficient observational data is often unavailable (i.e. momentary trajectory), making accurate prediction challenging and increasing the risk of traffic accidents. Therefore, advancing research on pedestrian trajectory prediction under extreme scenarios is critical for enhancing traffic safety. In this work, we propose a novel framework termed Diffusion^2, tailored for momentary trajectory prediction. Diffusion^2 consists of two sequentially connected diffusion models: one for backward prediction, which generates unobserved historical trajectories, and the other for forward prediction, which forecasts future trajectories. Given that the generated unobserved historical trajectories may introduce additional noise, we propose a dual-head parameterization mechanism to estimate their aleatoric uncertainty and design a temporally adaptive noise module that dynamically modulates the noise scale in the forward diffusion process. Empirically, Diffusion^2 sets a new state-of-the-art in momentary trajectory prediction on ETH/UCY and Stanford Drone datasets.

Related papers

• DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving [28.22372133560876]
  We propose DiffRefiner, a novel two-stage trajectory prediction framework.<n>The first stage uses a transformer-based Proposal Decoder to generate coarse trajectory predictions.<n>The second stage applies a Diffusion Refiner that iteratively denoises and refines these initial predictions.
  arXiv  Detail & Related papers  (2025-11-21T11:16:00Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Adaptive Conformal Prediction Intervals Over Trajectory Ensembles [50.31074512684758]
  Future trajectories play an important role across domains such as autonomous driving, hurricane forecasting, and epidemic modeling.<n>We propose a unified framework based on conformal prediction that transforms sampled trajectories into calibrated prediction intervals with theoretical coverage guarantees.
  arXiv  Detail & Related papers  (2025-08-18T21:14:07Z)
• EP-Diffuser: An Efficient Diffusion Model for Traffic Scene Generation and Prediction via Polynomial Representations [1.9191778789375846]
  We introduce EP-Diffuser, a parameter-efficient diffusion-based generative model designed to capture the distribution of possible traffic scene evolutions.<n>Conditioned on road layout and agent history, our model acts as a predictor and generates diverse, plausible scene continuations.<n>We benchmark EP-Diffuser against two SotA models in terms of accuracy and plausibility of predictions on the Argoverse 2 dataset.
  arXiv  Detail & Related papers  (2025-04-07T18:45:49Z)
• C2F-TP: A Coarse-to-Fine Denoising Framework for Uncertainty-Aware Trajectory Prediction [28.462298047242367]
  We propose C2F-TP, a coarse-to-fine denoising framework for uncertainty-aware vehicle trajectory prediction.<n>C2F-TP features an innovative two-stage coarse-to-fine prediction process.
  arXiv  Detail & Related papers  (2024-12-17T13:42:49Z)
• ITPNet: Towards Instantaneous Trajectory Prediction for Autonomous Driving [46.17683799762322]
  Trajectory prediction of agents is crucial for the safety of autonomous vehicles.<n>Previous approaches usually rely on sufficiently long-observed trajectory to predict the future trajectory of the agents.<n>We propose a general and plug-and-play instantaneous trajectory prediction approach, called ITPNet.
  arXiv  Detail & Related papers  (2024-12-10T10:09:41Z)
• ADM: Accelerated Diffusion Model via Estimated Priors for Robust Motion Prediction under Uncertainties [6.865435680843742]
  We propose a novel diffusion-based, acceleratable framework that adeptly predicts future trajectories of agents with enhanced resistance to noise. Our method meets the rigorous real-time operational standards essential for autonomous vehicles. It achieves significant improvement in multi-agent motion prediction on the Argoverse 1 motion forecasting dataset.
  arXiv  Detail & Related papers  (2024-05-01T18:16:55Z)
• Pedestrian Trajectory Forecasting Using Deep Ensembles Under Sensing Uncertainty [125.41260574344933]
  We consider an encoder-decoder based deep ensemble network for capturing both perception and predictive uncertainty simultaneously. Overall, deep ensembles provided more robust predictions and the consideration of upstream uncertainty further increased the estimation accuracy for the model.
  arXiv  Detail & Related papers  (2023-05-26T04:27:48Z)
• Uncertainty estimation of pedestrian future trajectory using Bayesian approximation [137.00426219455116]
  Under dynamic traffic scenarios, planning based on deterministic predictions is not trustworthy. The authors propose to quantify uncertainty during forecasting using approximation which deterministic approaches fail to capture. The effect of dropout weights and long-term prediction on future state uncertainty has been studied.
  arXiv  Detail & Related papers  (2022-05-04T04:23:38Z)
• Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion [88.45326906116165]
  We present a new framework to formulate the trajectory prediction task as a reverse process of motion indeterminacy diffusion (MID) We encode the history behavior information and the social interactions as a state embedding and devise a Transformer-based diffusion model to capture the temporal dependencies of trajectories. Experiments on the human trajectory prediction benchmarks including the Stanford Drone and ETH/UCY datasets demonstrate the superiority of our method.
  arXiv  Detail & Related papers  (2022-03-25T16:59:08Z)
• From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting [54.273455592965355]
  Uncertainty in future trajectories stems from two sources: (a) sources known to the agent but unknown to the model, such as long term goals and (b)sources that are unknown to both the agent & the model, such as intent of other agents & irreducible randomness indecisions. We model the epistemic un-certainty through multimodality in long term goals and the aleatoric uncertainty through multimodality in waypoints& paths. To exemplify this dichotomy, we also propose a novel long term trajectory forecasting setting, with prediction horizons upto a minute, an order of magnitude longer than prior works.
  arXiv  Detail & Related papers  (2020-12-02T21:01:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.