TSGen: A Framework for Indoor Trajectory-Semantic Data Synthesis
Open Access
- 30 September 2026
- journal article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 10 (3) , 1-33
Abstract
Smart homes are evolving from passive response to proactive service, where understanding the semantic information in user trajectories is essential. However, existing tracking systems output only sparse location sequences, insufficient for higher-level semantic reasoning. The core bottleneck lies in the lack of large-scale annotated datasets, while traditional data collection is costly and raises privacy concerns. We present TSGen, which formalizes indoor trajectory-semantic data synthesis as a structured decomposition problem. We first demonstrate that naive end-to-end LLM approaches are fundamentally limited for this task, then propose a hybrid workflow combining LLM-driven behavior simulation, physics-constrained trajectory synthesis, and a self-refining prompt architecture that evolves from runtime errors, to construct the T-S dataset (14,000 hours of trajectory-semantic pairs). We also implement a hierarchical processing pipeline as an initial baseline for semantic understanding, establishing reference benchmarks for future research. Evaluations cover data quality (user studies, diversity analysis, ablation studies) and baseline performance. On QA tasks over synthetic data and real-world deployments, our baseline significantly outperforms direct LLM methods while reducing computational costs. The open-sourced dataset and codebase provide foundational resources for this emerging research area 1 .Keywords
Funding Information
- National Natural Science Foundation of China (62472307)
- National Natural Science Foundation of China (62502339)
- National Natural Science Foundation of China (62372324)
- National Natural Science Foundation of China (62402336)
This publication has 37 references indexed in Scilit:
- Privacy-preserving generation and publication of synthetic trajectory microdata: A comprehensive surveyJournal of Network and Computer Applications, 2024
- PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI2024
- Holodeck: Language Guided Generation of 3D Embodied AI Environments2024
- Simulating human mobility with a trajectory generation framework based on diffusion modelInternational Journal of Geographical Information Science, 2024
- Synthesizing Diverse Human Motions in 3D Indoor Scenes2023
- Mobility trajectory generation: a surveyArtificial Intelligence Review, 2023
- WSTrack: A Wi-Fi and Sound Fusion System for Device-free Human Tracking2023
- Secur-Fi: A Secure Wireless Sensing System Based on Commercial Wi-Fi Devices2023
- Mining Semantic Trajectory Patterns from Geo-Tagged DataJournal of Computer Science and Technology, 2018
- The TimeGeo modeling framework for urban mobility without travel surveysProceedings of the National Academy of Sciences, 2016