TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models

2026-03-16

AI Summary

Real-world mobile GPS trajectories are difficult to deploy widely due to privacy concerns, high acquisition costs, and limited accessibility. Existing synthetic trajectory generation methods suffer from limitations in spatial scale, diversity of transportation modes, and computational efficiency. To address these challenges, this work proposes TrajFlow, the first framework to adapt flow matching models to GPS trajectory synthesis. By integrating trajectory coordination and reconstruction strategies, TrajFlow is trained on millions of real trajectories across Japan, enabling high-fidelity, multi-scale, and multi-modal pseudo-trajectory generation with high efficiency. Experimental results demonstrate that TrajFlow significantly outperforms state-of-the-art diffusion models and deep generative baselines across urban, metropolitan, and nationwide scales, offering a powerful tool for cross-regional urban planning, traffic management, and emergency response applications.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

The importance of mobile phone GPS trajectory data is widely recognized across many fields, yet the use of real data is often hindered by privacy concerns, limited accessibility, and high acquisition costs. As a result, generating pseudo-GPS trajectory data has become an active area of research. Recent diffusion-based approaches have achieved strong fidelity but remain limited in spatial scale (small urban areas), transportation-mode diversity, and efficiency (requiring numerous sampling steps). To address these challenges, we introduce TrajFlow, which to the best of our knowledge is the first flow-matching-based generative model for GPS trajectory generation. TrajFlow leverages the flow-matching paradigm to improve robustness and efficiency across multiple geospatial scales, and incorporates a trajectory harmonization and reconstruction strategy to jointly address scalability, diversity, and efficiency. Using a nationwide mobile phone GPS dataset with millions of trajectories across Japan, we show that TrajFlow or its variants consistently outperform diffusion-based and deep generative baselines at urban, metropolitan, and nationwide levels. As the first nationwide, multi-scale GPS trajectory generation model, TrajFlow demonstrates strong potential to support inter-region urban planning, traffic management, and disaster response, thereby advancing the resilience and intelligence of future mobility systems.

Problem

• pseudo-GPS trajectory generation
• privacy-preserving mobility data
• nationwide trajectory modeling
• scalable generative models
• multi-modal transportation

Innovation

• flow matching
• pseudo-GPS trajectory generation
• multi-scale modeling
• trajectory harmonization
• nationwide mobility data