arXiv cs.AI· Yueyang Liu, Joon-Seok Kim, Andreas Z\"ufle·· 1 天前AI 评分24
LLM 驱动的轨迹异常合成框架：地图约束路由与传感器噪声模拟
Synthesizing Human Trajectory Anomalies: An LLM-Driven Framework with Map-Constrained Routing and Sensor Noise Simulation
AI 导读
研究团队提出一个端到端生成框架，用 LLM 智能体在基线模拟轨迹中注入语义上有意义的行为异常，如分布外签到和跳过常规访问。系统通过地图约束路由模块重算停留点间的物理转移以保证空间有效性，并用环境与位置变量参数化的上下文感知空间噪声模型模拟异构 GPS 传感器退化。该流程产出带标注异常的 CTI & EBI 格式移动数据集，为下游空间数据挖掘任务提供基准。
正文 · 原文
Abstract:Although the study of human trajectory anomalies is vital for spatial data mining, empirical research remains constrained by the lack of ground-truth datasets. Despite the availability of several real-world and simulated human trajectory datasets, most only include normal mobility patterns and lack annotated anomalies. This limitation primarily arises because anomalous events are rare in the real world and difficult to collect. Furthermore, collecting large-scale mobility data is hindered by strict privacy regulations and acquisition costs. To overcome these limitations and establish an explainable human trajectory anomalies dataset with annotated ground truth, we introduce an end-to-end generative framework designed to synthesize context-aware trajectory anomalies at scale. Unlike existing models, our framework applies real-world physical constraints on baseline simulated trajectories. We employ Large Language Model (LLM) agents to systematically inject semantically meaningful behavioral anomalies such as irregular out-of-distribution check-ins and skipped routine visits. To ensure the spatial validity, the system leverages a map-constrained routing module to recalculate the physical transitions between these LLM agent-modified staypoints. Moreover, to narrow the simulation-to-reality gap, we augment the resulting trajectories with a context-aware spatial noise model, parameterized by environmental and location-specific variables, to emulate heterogeneous GPS sensor degradation. Through this pipeline, our framework produces a CTI & EBI formatted mobility dataset with annotated anomalies, providing a benchmark for downstream spatial data mining tasks.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.10314 [cs.AI] |
| (or arXiv:2606.10314v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.10314 arXiv-issued DOI via DataCite |
Submission history
From: Yueyang Liu [view email]
[v1]
Tue, 9 Jun 2026 02:09:02 UTC (21,546 KB)
[v2]
Sun, 8 Nov 2026 20:37:45 UTC (22,027 KB)
[v3]
Thu, 12 Nov 2026 01:21:15 UTC (11,505 KB)
来源：arXiv cs.AI · arxiv.org