arXiv：cs.LG· Ning Wang, Claire Cardie, Sainyam Galhotra·· 13 小时前
目标约束池化（TCP）用于轨迹外推
Target-Constrained Pooling for Trajectory Extrapolation
AI 导读
研究提出目标约束池化（TCP），将有限时域终点与延续形状分离，并用均匀池化和匹配增量池化两种信号估计终点，再投影到目标一致区域对自由预测进行校正。
正文
Abstract:Trajectory extrapolation from a partial target trajectory is underdetermined, but completed related trajectories provide information about the unresolved continuation. We propose target-constrained pooling (TCP), which separates the finite-horizon endpoint from continuation shape and estimates that endpoint from two complementary source signals. Uniform pooling captures final response levels, while matched-increment pooling captures the remaining change after aligning source and target states. TCP selects representative sources, projects both endpoint estimates onto a target-consistent region, converts them into corrections of the free forecast, and controls their influence through strength calibration and degradation-aware weighting. Across 25,245 targets from five domains and both forecasting directions, TCP reduces mean RMSE by 35.8% to 42.1% for all ten target-only forecasters and improves all 100 forecaster, dataset, and direction comparisons. The two endpoint signals consistently outperform either alone, while representative selection remains within 0.64% to 1.02% of the full donor pool using 12.7x fewer donor inputs and 138.8x fewer matching distance computations.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.13034 [cs.LG] |
| (or arXiv:2610.13034v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13034 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ning Wang [view email]
[v1]
Fri, 9 Oct 2026 05:46:48 UTC (222 KB)
来源：arXiv：cs.LG · arxiv.org