TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model

• URL: http://arxiv.org/abs/2510.17545v2
• Date: Tue, 21 Oct 2025 03:00:21 GMT
• Title: TrajMamba: An Efficient and Semantic-rich Vehicle Trajectory Pre-training Model
• Authors: Yichen Liu, Yan Lin, Shengnan Guo, Zeyu Zhou, Youfang Lin, Huaiyu Wan,
• Abstract summary: Vehicle GPS record how vehicles move over time, storing valuable travel semantics, including movement patterns and travel purposes.<n>Learning travel semantics effectively and efficiently is crucial for real-world applications of trajectory data.<n>We propose TrajMamba, a novel approach for efficient and semantically rich vehicle trajectory learning.
• Score: 31.21671608884327
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vehicle GPS trajectories record how vehicles move over time, storing valuable travel semantics, including movement patterns and travel purposes. Learning travel semantics effectively and efficiently is crucial for real-world applications of trajectory data, which is hindered by two major challenges. First, travel purposes are tied to the functions of the roads and points-of-interest (POIs) involved in a trip. Such information is encoded in textual addresses and descriptions and introduces heavy computational burden to modeling. Second, real-world trajectories often contain redundant points, which harm both computational efficiency and trajectory embedding quality. To address these challenges, we propose TrajMamba, a novel approach for efficient and semantically rich vehicle trajectory learning. TrajMamba introduces a Traj-Mamba Encoder that captures movement patterns by jointly modeling both GPS and road perspectives of trajectories, enabling robust representations of continuous travel behaviors. It also incorporates a Travel Purpose-aware Pre-training procedure to integrate travel purposes into the learned embeddings without introducing extra overhead to embedding calculation. To reduce redundancy in trajectories, TrajMamba features a Knowledge Distillation Pre-training scheme to identify key trajectory points through a learnable mask generator and obtain effective compressed trajectory embeddings. Extensive experiments on two real-world datasets and three downstream tasks show that TrajMamba outperforms state-of-the-art baselines in both efficiency and accuracy.

Related papers

• Trajectory Representation Learning on Road Networks and Grids with Spatio-Temporal Dynamics [0.8655526882770742]
  Trajectory representation learning is a fundamental task for applications in fields including smart city, and urban planning.<n>We propose TIGR, a novel model designed to integrate grid and road network modalities while incorporatingtemporal dynamics.<n>We evaluate TIGR on two realworld datasets and demonstrate the effectiveness of combining both modalities.
  arXiv  Detail & Related papers  (2024-11-21T10:56:02Z)
• PTrajM: Efficient and Semantic-rich Trajectory Learning with Pretrained Trajectory-Mamba [22.622613591771152]
  Vehicle trajectories provide crucial movement information for various real-world applications. It is essential to develop a trajectory learning approach that efficiently extract rich semantic information, including movement and travel purposes. We propose PTrajM, a novel method of efficient and semantic-rich vehicle trajectory learning.
  arXiv  Detail & Related papers  (2024-08-09T07:48:51Z)
• Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory [53.37473225728298]
  The rapid evolution of deep learning and large language models has led to an exponential growth in the demand for training data. Matching Training Trajectories (MTT) has been a prominent approach, which replicates the training trajectory of an expert network on real data with a synthetic dataset. We introduce a novel method called Matching Convexified Trajectory (MCT), which aims to provide better guidance for the student trajectory.
  arXiv  Detail & Related papers  (2024-06-28T11:06:46Z)
• Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder for Map-Constrained Trajectory Recovery [21.911875343270683]
  Recovering missing GPS points in a sparse trajectory could offer deep insights into users' moving behaviors in intelligent transportation systems. It is extremely hard for them to comprehensively capture the micro-semantics of individual trajectory. We propose a Micro-Macro- Spatial Graph-Decoder (MM-STGED) to efficiently describe the micro-semantics of trajectory and design a novel message-passing mechanism.
  arXiv  Detail & Related papers  (2024-04-29T22:54:35Z)
• NLP-enabled Trajectory Map-matching in Urban Road Networks using a Transformer-based Encoder-decoder [1.3812010983144802]
  This study introduces a data-driven, deep learning-based map-matching framework, formulating the task as machine translation, inspired by NLP.<n>A transformer-based encoder-decoder model learns contextual representations of noisy GPS points to infer trajectory behavior and road structures in an end-to-end manner.<n>Experiments on synthetic trajectories show that this approach outperforms conventional methods by integrating contextual awareness.
  arXiv  Detail & Related papers  (2024-04-18T18:39:23Z)
• Deep Learning for Trajectory Data Management and Mining: A Survey and Beyond [58.63558696061679]
  Trajectory computing is crucial in various practical applications such as location services, urban traffic, and public safety. We present a review of development and recent advances in deep learning for trajectory computing (DL4Traj) Notably, we encapsulate recent advancements in Large Language Models (LLMs) that hold potential to augment trajectory computing.
  arXiv  Detail & Related papers  (2024-03-21T05:57:27Z)
• SEPT: Towards Efficient Scene Representation Learning for Motion Prediction [19.111948522155004]
  This paper presents SEPT, a modeling framework that leverages self-supervised learning to develop powerful models for complex traffic scenes. experiments demonstrate that SEPT, without elaborate architectural design or feature engineering, achieves state-of-the-art performance on the Argoverse 1 and Argoverse 2 motion forecasting benchmarks.
  arXiv  Detail & Related papers  (2023-09-26T21:56:03Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics [30.9735101687326]
  Trajectory Representation Learning (TRL) is a powerful tool for spatial-temporal data analysis and management. Existing TRL works usually treat trajectories as ordinary sequence data, while some important spatial-temporal characteristics, such as temporal regularities and travel semantics, are not fully exploited. We propose a novel Self-supervised trajectory representation learning framework with TemporAl Regularities and Travel semantics, namely START.
  arXiv  Detail & Related papers  (2022-11-17T13:14:47Z)
• PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map [58.53373202647576]
  We propose PreTraM, a self-supervised pre-training scheme for trajectory forecasting. It consists of two parts: 1) Trajectory-Map Contrastive Learning, where we project trajectories and maps to a shared embedding space with cross-modal contrastive learning, and 2) Map Contrastive Learning, where we enhance map representation with contrastive learning on large quantities of HD-maps. On top of popular baselines such as AgentFormer and Trajectron++, PreTraM boosts their performance by 5.5% and 6.9% relatively in FDE-10 on the challenging nuScenes dataset.
  arXiv  Detail & Related papers  (2022-04-21T23:01:21Z)
• Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction [110.61383502442598]
  We introduce a novel neural network framework termed Cross-Modal Message Propagation Network (CMMPNet) CMMPNet is composed of two deep Auto-Encoders for modality-specific representation learning and a tailor-designed Dual Enhancement Module for cross-modal representation refinement. Experiments on three real-world benchmarks demonstrate the effectiveness of our CMMPNet for robust road extraction.
  arXiv  Detail & Related papers  (2021-11-30T04:30:10Z)
• AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points [92.91569287889203]
  We present a novel, label-free algorithm, AutoTrajectory, for trajectory extraction and prediction. To better capture the moving objects in videos, we introduce dynamic points. We aggregate dynamic points to instance points, which stand for moving objects such as pedestrians in videos.
  arXiv  Detail & Related papers  (2020-07-11T08:43:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.