A Survey on Learning-Based Trajectory Similarity Computation
ACM Computing Surveys · 31.10.2026 · 58 (14) · 1-36
DOI: 10.1145/3820160 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.07.2026. Verfasst von Xiangfu Meng und 6 weiteren Autor:innen. Die Arbeit nennt 133 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Trajectory Similarity Computation (TSC) quantifies the similarity or dissimilarity between trajectories, which is a fundamental task in trajectory data analysis. However, the high computational cost of traditional trajectory distance measures has become a key bottleneck for large-scale trajectory data analysis. With advancements in deep learning, learning-based TSC methods map trajectories into a uniform embedding space, enabling constant-time similarity computations and improving efficiency. Additionally, these methods exhibit robustness to low-quality data and adapt to various similarity measures through diverse learning strategies. This article surveys recent learning-based TSC methods, classifying them by representation form (sequence, image, and graph) and learning strategy(supervised and self-supervised). We analyze their principles and characteristics, focusing on intra-trajectory representation learning, inter-trajectory embedding learning, and training data construction. We also review publicly available datasets and evaluation metrics, and discuss current challenges and future research directions in TSC.
Zitieren
APA
Meng, X., Ge, X., Zhang, X., Shi, G., Siyu, L., Han, X., & Wang, S. (2026). A Survey on Learning-Based Trajectory Similarity Computation. ACM Computing Surveys, 58(14), 1-36. https://doi.org/10.1145/3820160
Vancouver
Meng X, Ge X, Zhang X, Shi G, Siyu L, Han X, et al. A Survey on Learning-Based Trajectory Similarity Computation. ACM Computing Surveys. 2026;58(14):1-36. doi:10.1145/3820160
BibTeX
@article{Meng2026,
author = {Meng, Xiangfu and Ge, Xiwen and Zhang, Xiaoyan and Shi, Guangqi and Siyu, Liu and Han, Xinyu and Wang, Shuangbin},
title = {A Survey on Learning-Based Trajectory Similarity Computation},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {14},
pages = {1--36},
doi = {10.1145/3820160}
}
EUVIMED