Uncertainty-Aware Trajectory Forecasting from Imperfect Tracking

2026-08-31

AI Summary

该论文提出一种不确定性感知的轨迹预测方法，通过利用跟踪器提供的可靠性线索，改进了在不完美多目标跟踪下的轨迹预测准确性。

Abstract

Most trajectory forecasting models are trained on clean annotated histories, and are often evaluated under the same idealized assumption, although practical deployments rely on trajectories produced by imperfect multi-object trackers. The real-world observations exhibit localization jitter, missed or unstable detections, and data-association ambiguity, which are usually either ignored or removed through denoising. This paper instead treats tracking-derived reliability cues as an informative signal to be propagated to the predictor. We propose a plug-in uncertainty-aware formulation in which each observed state is encoded as an uncertain state representation, modeled by a Gaussian distribution whose covariance combines detection-level localization uncertainty and association-level ambiguity through the law of total variance. Existing backbones are adapted with minimal architectural changes: input trajectories are represented as Gaussian observations, and predicted trajectories are produced as Gaussian forecasts rather than deterministic coordinates. To train predictors that remain robust under structured observation noise, we combine temporally correlated Ornstein-Uhlenbeck perturbations with response-based knowledge distillation from a teacher trained on clean trajectories. Experiments on Oxford Town Centre and VIRAT using real tracker outputs, together with a complementary ETH/UCY pseudo-detection protocol, show that the proposed formulation improves displacement accuracy and the reliability-sharpness trade-off of probabilistic forecasts.

Problem

• trajectory forecasting
• imperfect tracking
• uncertainty-aware
• reliability cues
• structured observation noise

Innovation

• uncertainty-aware
• imperfect tracking
• Gaussian distribution
• knowledge distillation
• temporally correlated perturbations