| 注册
首页|期刊导航|中山大学学报(自然科学版)(中英文)|图模体矩阵增强下的扩散模型轨迹生成方法

图模体矩阵增强下的扩散模型轨迹生成方法

袁洲旅 何兆成 谢传智

中山大学学报(自然科学版)(中英文)2026,Vol.65Issue(5):99-108,10.
✕
中山大学学报(自然科学版)(中英文)2026,Vol.65Issue(5):99-108,10.DOI:10.11714/acta.snus.ZR20260066

图模体矩阵增强下的扩散模型轨迹生成方法

Graph-Motif matrix enhanced conditional diffusion model for vehicle trajectory generation

袁洲旅 1何兆成 2谢传智1

作者信息

  • 1. 中山大学智能工程学院/广东省智能交通系统重点实验室,广东 深圳 518107
  • 2. 中山大学智能工程学院/广东省智能交通系统重点实验室,广东 深圳 518107||鹏城实验室,广东 深圳 518055
  • 折叠

摘要

Abstract

In practical intelligent transportation systems,failures of IoT may lead to data interruption,underscoring the importance of trajectory data generation algorithms.Existing trajectory generation methods can be categorized into two types,both of which exhibit limitations.Physics-based algorithms are unable to adapt to dynamically changing traffic scenarios,whereas data-driven methods tend to overlook interactions among vehicles.To address complex scenarios such as intersections,this paper proposes a trajectory generation method based on a conditional diffusion model.The proposed method introduces a motif matrix to quantify the influence of surrounding vehicles on the target vehicle,and employs a graph attention mechanism to accurately identify key neighboring vehicle information,and the conditional information is incorporated into the reverse denoising process of the diffusion model to generate vehicle trajectories.Experiments conducted on the nuScenes dataset and a self-collected trajectory dataset demonstrate that the proposed method outperforms existing mainstream models across multiple accuracy evaluation metrics and is more consistent with kinematic principles.

关键词

智能交通/车辆轨迹生成/条件扩散模型

Key words

intelligent transportation/vehicle trajectory generation/conditional diffusion model

分类

交通工程

引用本文复制引用

袁洲旅,何兆成,谢传智..图模体矩阵增强下的扩散模型轨迹生成方法[J].中山大学学报(自然科学版)(中英文),2026,65(5):99-108,10.

基金项目

国家重点研发计划(2023YFB4301900) (2023YFB4301900)

深圳市基础研究专项(JCYJ20240813151445059) (JCYJ20240813151445059)

中山大学学报(自然科学版)(中英文)

0529-6579

访问量0
|
下载量0
段落导航相关论文