MarineFormer: A Spatio-Temporal Attention Model for USV Navigation in Dynamic Marine Environments
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915380075692032 |
|---|---|
| author | Kazemi, Ehsan Gao, Dechen Soltani, Iman |
| author_facet | Kazemi, Ehsan Gao, Dechen Soltani, Iman |
| contents | Autonomous navigation in marine environments can be extremely challenging, especially in the presence of spatially varying flow disturbances and dynamic and static obstacles. In this work, we demonstrate that incorporating local flow field measurements fundamentally alters the nature of the problem, transforming otherwise unsolvable navigation scenarios into tractable ones. However, the mere availability of flow data is not sufficient; it must be effectively fused with conventional sensory inputs such as ego-state and obstacle states. To this end, we propose \textbf{MarineFormer}, a Transformer-based policy architecture that integrates two complementary attention mechanisms: spatial attention for sensor fusion, and temporal attention for capturing environmental dynamics. MarineFormer is trained end-to-end via reinforcement learning in a 2D simulated environment with realistic flow features and obstacles. Extensive evaluations against classical and state-of-the-art baselines show that our approach improves episode completion success rate by nearly 23\% while reducing path length. Ablation studies further highlight the critical role of flow measurements and the effectiveness of our proposed architecture in leveraging them. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_13973 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MarineFormer: A Spatio-Temporal Attention Model for USV Navigation in Dynamic Marine Environments Kazemi, Ehsan Gao, Dechen Soltani, Iman Robotics Artificial Intelligence Autonomous navigation in marine environments can be extremely challenging, especially in the presence of spatially varying flow disturbances and dynamic and static obstacles. In this work, we demonstrate that incorporating local flow field measurements fundamentally alters the nature of the problem, transforming otherwise unsolvable navigation scenarios into tractable ones. However, the mere availability of flow data is not sufficient; it must be effectively fused with conventional sensory inputs such as ego-state and obstacle states. To this end, we propose \textbf{MarineFormer}, a Transformer-based policy architecture that integrates two complementary attention mechanisms: spatial attention for sensor fusion, and temporal attention for capturing environmental dynamics. MarineFormer is trained end-to-end via reinforcement learning in a 2D simulated environment with realistic flow features and obstacles. Extensive evaluations against classical and state-of-the-art baselines show that our approach improves episode completion success rate by nearly 23\% while reducing path length. Ablation studies further highlight the critical role of flow measurements and the effectiveness of our proposed architecture in leveraging them. |
| title | MarineFormer: A Spatio-Temporal Attention Model for USV Navigation in Dynamic Marine Environments |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2410.13973 |