Human Mobility Modeling with Household Coordination Activities under Limited Information via Retrieval-Augmented LLMs

TL;DR

This paper introduces a retrieval-augmented LLM framework that models human mobility by incorporating household coordination activities using only publicly available data, overcoming data scarcity issues in transportation modeling.

Contribution

It presents a novel retrieval-augmented LLM approach that generates realistic activity chains with household coordination, requiring minimal mobility data and maintaining statistical consistency.

Findings

Effective mobility synthesis demonstrated on NHTS and SCAG-ABM datasets.

Strong adaptability to regions with limited mobility data.

Addresses key gaps in existing human mobility modeling methods.

Abstract

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.