Human Mobility Modeling with Household Coordination Activities under Limited Information via Retrieval-Augmented LLMs
This work addresses the challenge of realistic human mobility modeling for transportation planning in regions with limited data availability, though it is incremental as it builds on existing LLM and retrieval-augmentation techniques.
The paper tackles the problem of human mobility modeling by addressing the lack of high-quality training data and the neglect of semantic relationships like household coordination activities, proposing a retrieval-augmented LLM framework that generates activity chains using only public statistical information, with validation on NHTS and SCAG-ABM datasets showing effective synthesis and adaptability for data-scarce regions.
Understanding human mobility patterns has long been a challenging task in transportation modeling. Due to the difficulties in obtaining high-quality training datasets across diverse locations, conventional activity-based models and learning-based human mobility modeling algorithms are particularly limited by the availability and quality of datasets. Current approaches primarily focus on spatial-temporal patterns while neglecting semantic relationships such as logical connections or dependencies between activities and household coordination activities like joint shopping trips or family meal times, both crucial for realistic mobility modeling. We propose a retrieval-augmented large language model (LLM) framework that generates activity chains with household coordination using only public accessible statistical and socio-demographic information, reducing the need for sophisticated mobility data. The retrieval-augmentation mechanism enables household coordination and maintains statistical consistency across generated patterns, addressing a key gap in existing methods. Our validation with NHTS and SCAG-ABM datasets demonstrates effective mobility synthesis and strong adaptability for regions with limited mobility data availability.