Propose a vehicle trajectory learning model capable of transferring across regions and tasks without retraining.

We propose a novel trajectory representation learning approach that efficiently learns travel semantics, including movement patterns and travel purposes, from vehicle trajectories.

We propose a trajectory recovery model based on PLM to address the challenge of the availability of dense trajectories is limited and to generalize across sparse trajectories with varying sampling intervals.

We built the first worldwide trajectory dataset and trained a universal trajectory foundation model.