Spatio-Temporal Trajectory Foundation Model - Recent Advances and Future Directions

TL;DR

This paper reviews recent advances in spatio-temporal trajectory foundation models, highlighting their methodologies, strengths, limitations, and future research directions to enhance spatio-temporal intelligence.

Contribution

It provides a comprehensive taxonomy and critical analysis of trajectory foundation models, addressing a significant research gap in the field.

Findings

Taxonomy of existing TFM methodologies

Critical analysis of TFM strengths and limitations

Open challenges and future research directions

Abstract

Foundation models (FMs) have emerged as a powerful paradigm, enabling a diverse range of data analytics and knowledge discovery tasks across scientific fields. Inspired by the success of FMs, particularly large language models, researchers have recently begun to explore spatio-temporal foundation models (STFMs) to improve adaptability and generalization across a wide spectrum of spatio-temporal (ST) tasks. Despite rapid progress, a systematic investigation of trajectory foundation models (TFMs), a crucial subclass of STFMs, is largely lacking. This tutorial addresses this gap by offering a comprehensive overview of recent advances in TFMs, including a taxonomy of existing methodologies and a critical analysis of their strengths and limitations. In addition, the tutorial highlights open challenges and outlines promising research directions to advance spatio-temporal general intelligence through the development of robust, responsible, and transferable TFMs.