Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.14265 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914304757858304 |
|---|---|
| author | Zhang, Rui Li, Chao Liu, Kezhong Wang, Chen Zheng, Bolong Jiang, Hongbo |
| author_facet | Zhang, Rui Li, Chao Liu, Kezhong Wang, Chen Zheng, Bolong Jiang, Hongbo |
| contents | Vessel trajectory prediction is fundamental to intelligent maritime systems. Within this domain, short-term prediction of rapid behavioral changes in complex maritime environments has established multimodal trajectory prediction (MTP) as a promising research area. However, existing vessel MTP methods suffer from limited scenario applicability and insufficient explainability. To address these challenges, we propose a unified MTP framework incorporating explainable navigation intentions, which we classify into sustained and transient categories. Our method constructs sustained intention trees from historical trajectories and models dynamic transient intentions using a Conditional Variational Autoencoder (CVAE), while using a non-local attention mechanism to maintain global scenario consistency. Experiments on real Automatic Identification System (AIS) datasets demonstrates our method's broad applicability across diverse scenarios, achieving significant improvements in both ADE and FDE. Furthermore, our method improves explainability by explicitly revealing the navigational intentions underlying each predicted trajectory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14265 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unified Multimodal Vessel Trajectory Prediction with Explainable Navigation Intention Zhang, Rui Li, Chao Liu, Kezhong Wang, Chen Zheng, Bolong Jiang, Hongbo Machine Learning Vessel trajectory prediction is fundamental to intelligent maritime systems. Within this domain, short-term prediction of rapid behavioral changes in complex maritime environments has established multimodal trajectory prediction (MTP) as a promising research area. However, existing vessel MTP methods suffer from limited scenario applicability and insufficient explainability. To address these challenges, we propose a unified MTP framework incorporating explainable navigation intentions, which we classify into sustained and transient categories. Our method constructs sustained intention trees from historical trajectories and models dynamic transient intentions using a Conditional Variational Autoencoder (CVAE), while using a non-local attention mechanism to maintain global scenario consistency. Experiments on real Automatic Identification System (AIS) datasets demonstrates our method's broad applicability across diverse scenarios, achieving significant improvements in both ADE and FDE. Furthermore, our method improves explainability by explicitly revealing the navigational intentions underlying each predicted trajectory. |
| title | Unified Multimodal Vessel Trajectory Prediction with Explainable Navigation Intention |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.14265 |