Target-Constrained Pooling for Trajectory Extrapolation
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.
Related
- Interval-Constrained Brownian Paths: Exact Interpolation and Extrapolation
- Distribution-Agnostic Robust Trajectory Optimization via Chance-Constrained Reinforcement Learning
- Trajectory Parameterization and Evolutionary Search for Constrained Optimal Control
- Target-Generated Dirichlet Problems in State-Constrained Stochastic Control
- Age-Optimal Target Wake Time: Provably Good Wake Schedules for Energy-Constrained Wi-Fi Status Updating
BibTeX
@misc{wang2026targetconstrained,
title = {{Target-Constrained Pooling for Trajectory Extrapolation}},
author = {Ning Wang and Claire Cardie and Sainyam Galhotra},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.13034},
eprint = {2610.13034},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.13034},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Target-Constrained Pooling for Trajectory Extrapolation
AU - Ning Wang
AU - Claire Cardie
AU - Sainyam Galhotra
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.13034
UR - https://arxiv.org/abs/2610.13034
AB - 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.
ER -