GoMatch: Goal-Guided Truncated Flow Matching for Multimodal Trajectory Prediction
IEEE Internet of Things Journal · 2026-08 · 13 (16) · 36424-36439
DOI: 10.1109/jiot.2026.3698544 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, 2026-08. Verfasst von Yamei Xu und 5 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: Nature Science Foundation of China, Key Project of Public Benefit in Henan Province of China, Key Research and Development Program of Henan.
Abstract (Originalsprache)
Accurately predicting human future trajectories remains a core challenge in autonomous driving and human–robot interaction, primarily due to the inherent uncertainty of human motion and real-time requirements of decision making. While generative models have shown promise in multimodal trajectory prediction, they often fail to simultaneously achieve high fidelity, high diversity, and fast sampling efficiency. To address this, we propose a unified trajectory prediction framework based on goal-guided truncated flow matching, which jointly optimizes these objectives. Specifically, we introduce a truncated flow matching strategy that initializes the denoising process from a context-aware intermediate state closer to the true trajectory distribution, reducing the number of sampling steps from 100 to just 2 and significantly enhancing inference efficiency. To enhance intent awareness and behavioral plausibility, we design an internal intention module that incorporates goal-guided cross-attention and is supervised by both destination regression and physical feasibility constraints, leading to more accurate and realistic predictions. Furthermore, to promote behavioral diversity and mitigate mode collapse, we propose a modality-aware diversity modeling mechanism that explicitly disentangles semantic differences among trajectory modes. Meanwhile, we introduce a diversity metric to quantitatively evaluate the diversity of the generated predictions. Extensive experiments on three public datasets show that our method achieves competitive accuracy, significantly enhances motion diversity, and delivers superior inference efficiency compared to existing models. These results highlight its strong potential for real-world deployment in safety-critical applications.
Förderung
- Nature Science Foundation of China
- Key Project of Public Benefit in Henan Province of China
- Key Research and Development Program of Henan
Zitieren
APA
Xu, Y., Shi, Y., Gao, Z., Zhang, H., Liu, C., & Shi, L. (2026). GoMatch: Goal-Guided Truncated Flow Matching for Multimodal Trajectory Prediction. IEEE Internet of Things Journal, 13(16), 36424-36439. https://doi.org/10.1109/jiot.2026.3698544
Vancouver
Xu Y, Shi Y, Gao Z, Zhang H, Liu C, Shi L. GoMatch: Goal-Guided Truncated Flow Matching for Multimodal Trajectory Prediction. IEEE Internet of Things Journal. 2026;13(16):36424-36439. doi:10.1109/jiot.2026.3698544
BibTeX
@article{Xu2026,
author = {Xu, Yamei and Shi, Yucheng and Gao, Zhenghan and Zhang, Hong and Liu, Chengming and Shi, Lei},
title = {GoMatch: Goal-Guided Truncated Flow Matching for Multimodal Trajectory Prediction},
journal = {IEEE Internet of Things Journal},
year = {2026},
volume = {13},
number = {16},
pages = {36424--36439},
doi = {10.1109/jiot.2026.3698544}
}
EUVIMED