有限集多模态轨迹预测的目的地支持恢复
Destination Support Restoration for Finite-Set Multimodal Trajectory Prediction
浏览论文内容
中文总结 AI 辅助
针对机器人预测中有限集目的地支持不足问题，提出DSR后选择算子，在不重训练且不增集大小下修复支持，在爱丁堡数据集上显著降低ADE和FDE。
中文摘要 AI 辅助
在行人周围运行的机器人通常会对一组有限的预测人类未来进行推理。重复的在线更新可能会将有限的预测预算集中在主要目的地上，而使得合理的备选方案代表性不足或缺失，从而将这些备选方案从可供下游决策使用的有限表示中移除。我们引入了目的地支持恢复（DSR），这是一种因果选择后算子，无需重新训练宿主预测器或增加维护集大小即可修复目的地支持。在修复步骤中，DSR从观察到的前缀中评估一个临时的按目的地分层的候选库，将候选证据转换为整数目标计数，保护活动模式的代表，并将冗余的剩余假设重新分配给不足的模式。维护和返回的集合恰好保留$N$个假设，且DSR最多替换$\rceil\rho N\rceil$个条目。受保护的代表保留当前的类别支持；谱系感知粒子滤波器也保留存活的重新采样祖先。每次替换都将与证据驱动目标的分配不匹配减少一。在完整的3,719条轨迹的爱丁堡协议上，跨三个随机种子，DSR在$N=64$时将MIF加权ADE和FDE分别降低了13.36%和13.30%。与CLiFF、PPT、因果GDTS、Social Informer和PECNet的配对集成在每对评估中均改善了这两个指标。这些结果表明，当固定假设集作为与下游系统的接口时，有限集支持分配是一个有用的预测侧控制点。
英文摘要
Robots operating around pedestrians often reason over a finite set of predicted human futures. Repeated online updates can concentrate this limited prediction budget on dominant destinations and leave plausible alternatives underrepresented or absent, removing those alternatives from the finite representation available to downstream decision making. We introduce Destination Support Restoration (DSR), a causal post-selection operator that repairs destination support without retraining the host predictor or increasing the maintained set size. At a repair step, DSR evaluates a temporary destination-stratified candidate bank from the observed prefix, converts candidate evidence into integer target counts, protects representatives of active modes, and reallocates redundant surplus hypotheses to deficient modes. The maintained and returned sets retain exactly $N$ hypotheses, and DSR replaces at most $\lceilρN\rceil$ entries. Protected representatives preserve current categorical support; lineage-aware particle filters also preserve surviving resampling ancestors. Each replacement reduces the allocation mismatch to the evidence-driven target by one. On the complete 3,719-trajectory Edinburgh protocol over three seeds, DSR reduces MIF weighted ADE and FDE by 13.36% and 13.30% at $N=64$. Paired integrations with CLiFF, PPT, causal GDTS, Social Informer, and PECNet improve both metrics in every evaluated pair. These results show that finite-set support allocation is a useful prediction-side control point when a fixed hypothesis set serves as the interface to downstream systems.
发表机构
- East China Normal University（华东师范大学）
- University of Science and Technology of China（中国科学技术大学）
- Tongji University（同济大学）
- Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。
