PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models

2024-10-18

AI Summary

Sparse spatiotemporal trajectory recovery remains challenging due to device failures and network instability. Method: This paper proposes a few-shot trajectory reconstruction approach leveraging pre-trained language models (PLMs). Its core innovations include: (i) the first formulation of trajectory sampling intervals and motion characteristics as natural language prompts; (ii) an implicit trajectory prompting mechanism guided by regional traffic flow, enabling road-condition modeling without explicit road network dependencies; and (iii) a unified interval-aware trajectory encoder coupled with a trajectory-to-text representation framework. Results: Evaluated on two public benchmarks under three sampling intervals, the method significantly outperforms state-of-the-art approaches, demonstrating strong generalization, high scalability, and robust few-shot adaptability.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Motion & Tracking
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Spatiotemporal trajectory data is crucial for various applications. However, issues such as device malfunctions and network instability often cause sparse trajectories, leading to lost detailed movement information. Recovering the missing points in sparse trajectories to restore the detailed information is thus essential. Despite recent progress, several challenges remain. First, the lack of large-scale dense trajectory data makes it difficult to train a trajectory recovery model from scratch. Second, the varying spatiotemporal correlations in sparse trajectories make it hard to generalize recovery across different sampling intervals. Third, the lack of location information complicates the extraction of road conditions for missing points. To address these challenges, we propose a novel trajectory recovery model called PLMTrajRec. It leverages the scalability of a pre-trained language model (PLM) and can be fine-tuned with only a limited set of dense trajectories. To handle different sampling intervals in sparse trajectories, we first convert each trajectory's sampling interval and movement features into natural language representations, allowing the PLM to recognize its interval. We then introduce a trajectory encoder to unify trajectories of varying intervals into a single interval and capture their spatiotemporal relationships. To obtain road conditions for missing points, we propose an area flow-guided implicit trajectory prompt, which models road conditions by collecting traffic flows in each region. We also introduce a road condition passing mechanism that uses observed points' road conditions to infer those of the missing points. Experiments on two public trajectory datasets with three sampling intervals each demonstrate the effectiveness, scalability, and generalization ability of PLMTrajRec.

Problem

• Recover missing points in sparse trajectories
• Handle varying spatiotemporal correlations
• Infer road conditions for missing points

Innovation

• Utilizes pre-trained language models
• Converts trajectories to natural language
• Models road conditions with traffic flows