English

DiffuTraj: A Stochastic Vessel Trajectory Prediction Approach via Guided Diffusion Process

Computer Vision and Pattern Recognition 2024-10-15 v1

Abstract

Maritime vessel maneuvers, characterized by their inherent complexity and indeterminacy, requires vessel trajectory prediction system capable of modeling the multi-modality nature of future motion states. Conventional stochastic trajectory prediction methods utilize latent variables to represent the multi-modality of vessel motion, however, tends to overlook the complexity and dynamics inherent in maritime behavior. In contrast, we explicitly simulate the transition of vessel motion from uncertainty towards a state of certainty, effectively handling future indeterminacy in dynamic scenes. In this paper, we present a novel framework (\textit{DiffuTraj}) to conceptualize the trajectory prediction task as a guided reverse process of motion pattern uncertainty diffusion, in which we progressively remove uncertainty from maritime regions to delineate the intended trajectory. Specifically, we encode the previous states of the target vessel, vessel-vessel interactions, and the environment context as guiding factors for trajectory generation. Subsequently, we devise a transformer-based conditional denoiser to capture spatio-temporal dependencies, enabling the generation of trajectories better aligned for particular maritime environment. Comprehensive experiments on vessel trajectory prediction benchmarks demonstrate the superiority of our method.

Keywords

Cite

@article{arxiv.2410.09550,
  title  = {DiffuTraj: A Stochastic Vessel Trajectory Prediction Approach via Guided Diffusion Process},
  author = {Changlin Li and Yanglei Gan and Tian Lan and Yuxiang Cai and Xueyi Liu and Run Lin and Qiao Liu},
  journal= {arXiv preprint arXiv:2410.09550},
  year   = {2024}
}

Comments

containing 14pages, 9 figures and 3 tables; Submitted to IEEE Transactions on Intelligent Transportation Systems on 17-June-2024

R2 v1 2026-06-28T19:19:03.269Z