发表机构
SATIE – CNRS UMR 8029, Université Paris-Saclay; ENS Paris-Saclay, Université Paris-Saclay（巴黎萨克雷大学SATIE实验室（法国国家科学研究中心联合研究单位）; 巴黎萨克雷高等师范学校，巴黎萨克雷大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对实际跟踪轨迹的不完美问题，本文提出不确定性感知轨迹预测方法，结合检测与关联不确定性建模，通过扰动与知识蒸馏训练，提升了预测精度与概率预测的可靠性-清晰度权衡。
AI 中文摘要
大多数轨迹预测模型在干净标注的历史数据上进行训练，且通常在相同的理想化假设下进行评估，尽管实际部署依赖于不完美的多目标跟踪器生成的轨迹。真实世界的观测存在定位抖动、漏检或不稳定检测以及数据关联模糊等问题，这些问题通常被忽略或通过去噪处理去除。本文反而将跟踪衍生的可靠性线索视为可传播给预测器的信息信号。我们提出了一种即插即用的不确定性感知公式，其中每个观测状态被编码为不确定状态表示，由高斯分布建模，其协方差通过总方差定律结合了检测级定位不确定性和关联级模糊性。现有骨干网络仅需进行最小的架构调整：输入轨迹表示为高斯观测，预测轨迹生成高斯预测而非确定性坐标。为训练在结构化观测噪声下仍保持鲁棒性的预测器，我们将时间相关的奥恩斯坦-乌伦贝克扰动与在干净轨迹上训练的教师模型的基于响应的知识蒸馏相结合。在使用真实跟踪器输出的牛津市中心和VIRAT数据集上的实验，以及补充的ETH/UCY伪检测协议实验表明，所提出的公式提高了位移精度和概率预测的可靠性-清晰度权衡。
英文摘要
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.
