eCoMAE：面向行人/骑行者运动预测的证据式掩码预训练方法
Observability-Aligned Evidential Masked Pretraining for Reliable VRU Motion Prediction
一篇解决自动驾驶里行人意图预测不确定性的论文，eCoMAE 在 IMPTC 上 OOD 准确率从 0.7971 提到 0.8068，四个轨迹数据集 MSE 全部最优，做感知预测的可以看看。
论文提出 eCoMAE，一种针对多元时间序列的证据式掩码预训练方法，将预测证据与可观测内容对齐。方法结合分块时间步掩码、Normal-Inverse-Gamma 解码器，并加入不确定性加权均值一致性、掩码位置证据抑制、随机掩码表示一致性三项机制。在 IMPTC 基准的跨环境天气偏移设定下，OOD 准确率从 0.7971 提升到 0.8068，OOD AURC 从 0.0718 降至 0.0648。在 IMPTC、Waymo、nuScenes 和 inD 四个行人轨迹预测数据集上，微调后的 MSE 均为最优。
Observability-Aligned Evidential Masked Pretraining for Reliable VRU Motion Prediction
Vulnerable road user (VRU) prediction must operate under partial observability and distribution shift, so reliable uncertainty matters alongside accuracy. Masked pretraining is attractive in this setting because it naturally exposes the model to missing content during self-supervision, but existing time-series masked autoencoding methods are typically deterministic and do not constrain how confidence should change with observability. We introduce eCoMAE, an evidential masked pretraining method for multivariate time series that explicitly aligns predictive evidence with what is observed. eCoMAE combines block-wise time-step masking with a Normal-Inverse-Gamma decoder and three observability-aware mechanisms: uncertainty-weighted mean consistency on positions visible in both a masked view and a reference pass, evidence suppression on masked positions, and representation consistency across stochastic masks. On IMPTC benchmark for VRU intention prediction under leave-one-environment-out weather shift, eCoMAE improves the strongest baseline from 0.7971 to 0.8068 in OOD accuracy and from 0.0718 to 0.0648 in OOD AURC. Additional evaluation on pedestrian trajectory forecasting across IMPTC, Waymo, nuScenes, and inD further yields the best fine-tuning MSE on all four datasets. These results show that observability-aligned evidential pretraining improves reliability under shift and remains effective beyond the primary benchmark.