Diff-RNTraj: A Structure-Aware Diffusion Model for Road Network-Constrained Trajectory Generation

Trajectory data is essential for various applications. However, publicly available trajectory datasets remain limited in scale due to privacy concerns, which hinders the development of trajectory mining and applications. Although some trajectory generation methods have been proposed to expand datase...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on knowledge and data engineering 2024-12, Vol.36 (12), p.7940-7953
Main Authors: Wei, Tonglong, Lin, Youfang, Guo, Shengnan, Lin, Yan, Huang, Yiheng, Xiang, Chenyang, Bai, Yuqing, Wan, Huaiyu
Format: Article
Language:English
Subjects:
diffusion model
Diffusion models
Global Positioning System
Hybrid power systems
Navigation
Noise reduction
road network
Roads
Spatial-temporal data mining
Trajectory
trajectory generation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Trajectory data is essential for various applications. However, publicly available trajectory datasets remain limited in scale due to privacy concerns, which hinders the development of trajectory mining and applications. Although some trajectory generation methods have been proposed to expand dataset scale, they generate trajectories in the geographical coordinate system, posing two limitations for practical applications: 1) failing to ensure that the generated trajectories are road-constrained. 2) lacking road-related information. In this paper, we propose a new problem, road network-constrained trajectory (RNTraj) generation, which can directly generate trajectories on the road network with road-related information. Specifically, RNTraj is a hybrid type of data, in which each point is represented by a discrete road segment and a continuous moving rate. To generate RNTraj, we design a diffusion model called Diff-RNTraj, which can effectively handle the hybrid RNTraj using a continuous diffusion framework by incorporating a pre-training strategy to embed hybrid RNTraj into continuous representations. During the sampling stage, a RNTraj decoder is designed to map the continuous representation generated by the diffusion model back to the hybrid RNTraj format. Furthermore, Diff-RNTraj introduces a novel loss function to enhance trajectory's spatial validity. Extensive experiments conducted on two datasets demonstrate the effectiveness of Diff-RNTraj.
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2024.3460051