CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Rui, He, Dan, Jin, Fengmei, Zhang, Chen, Zhou, Xiaofang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912722068701184
author Xue, Rui
He, Dan
Jin, Fengmei
Zhang, Chen
Zhou, Xiaofang
author_facet Xue, Rui
He, Dan
Jin, Fengmei
Zhang, Chen
Zhou, Xiaofang
contents Detecting trajectory anomalies is a vital task in modern Intelligent Transportation Systems (ITS), enabling the identification of unsafe, inefficient, or irregular travel behaviours. While deep learning has emerged as the dominant approach, several key challenges remain unresolved. First, sub-trajectory anomaly detection, capable of pinpointing the precise segments where anomalies occur, remains underexplored compared to whole-trajectory analysis. Second, many existing methods depend on carefully tuned thresholds, limiting their adaptability in real-world applications. Moreover, the irregular sampling of trajectory data and the presence of noise in training sets further degrade model performance, making it difficult to learn reliable representations of normal routes. To address these challenges, we propose a contrastive reinforcement learning framework for online trajectory anomaly detection, CroTad. Our method is threshold-free and robust to noisy, irregularly sampled data. By incorporating contrastive learning, CroTad learns to extract diverse normal travel patterns for different itineraries and effectively distinguish anomalous behaviours at both sub-trajectory and point levels. The detection module leverages deep reinforcement learning to perform online, real-time anomaly scoring, enabling timely and fine-grained identification of abnormal segments. Extensive experiments on two real-world datasets demonstrate the effectiveness and robustness of our framework across various evaluation scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16929
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection
Xue, Rui
He, Dan
Jin, Fengmei
Zhang, Chen
Zhou, Xiaofang
Machine Learning
Databases
Detecting trajectory anomalies is a vital task in modern Intelligent Transportation Systems (ITS), enabling the identification of unsafe, inefficient, or irregular travel behaviours. While deep learning has emerged as the dominant approach, several key challenges remain unresolved. First, sub-trajectory anomaly detection, capable of pinpointing the precise segments where anomalies occur, remains underexplored compared to whole-trajectory analysis. Second, many existing methods depend on carefully tuned thresholds, limiting their adaptability in real-world applications. Moreover, the irregular sampling of trajectory data and the presence of noise in training sets further degrade model performance, making it difficult to learn reliable representations of normal routes. To address these challenges, we propose a contrastive reinforcement learning framework for online trajectory anomaly detection, CroTad. Our method is threshold-free and robust to noisy, irregularly sampled data. By incorporating contrastive learning, CroTad learns to extract diverse normal travel patterns for different itineraries and effectively distinguish anomalous behaviours at both sub-trajectory and point levels. The detection module leverages deep reinforcement learning to perform online, real-time anomaly scoring, enabling timely and fine-grained identification of abnormal segments. Extensive experiments on two real-world datasets demonstrate the effectiveness and robustness of our framework across various evaluation scenarios.
title CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection
topic Machine Learning
Databases
url https://arxiv.org/abs/2511.16929