NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917984937705472 |
|---|---|
| author | Zeng, Yiming Ren, Hao Wang, Shuhang Huang, Junlong Cheng, Hui |
| author_facet | Zeng, Yiming Ren, Hao Wang, Shuhang Huang, Junlong Cheng, Hui |
| contents | Visual navigation, a fundamental challenge in mobile robotics, demands versatile policies to handle diverse environments. Classical methods leverage geometric solutions to minimize specific costs, offering adaptability to new scenarios but are prone to system errors due to their multi-modular design and reliance on hand-crafted rules. Learning-based methods, while achieving high planning success rates, face difficulties in generalizing to unseen environments beyond the training data and often require extensive training. To address these limitations, we propose a hybrid approach that combines the strengths of learning-based methods and classical approaches for RGB-only visual navigation. Our method first trains a conditional diffusion model on diverse path-RGB observation pairs. During inference, it integrates the gradients of differentiable scene-specific and task-level costs, guiding the diffusion model to generate valid paths that meet the constraints. This approach alleviates the need for retraining, offering a plug-and-play solution. Extensive experiments in both indoor and outdoor settings, across simulated and real-world scenarios, demonstrate zero-shot transfer capability of our approach, achieving higher success rates and fewer collisions compared to baseline methods. Code will be released at https://github.com/SYSU-RoboticsLab/NaviD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10003 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation Zeng, Yiming Ren, Hao Wang, Shuhang Huang, Junlong Cheng, Hui Robotics Computer Vision and Pattern Recognition Visual navigation, a fundamental challenge in mobile robotics, demands versatile policies to handle diverse environments. Classical methods leverage geometric solutions to minimize specific costs, offering adaptability to new scenarios but are prone to system errors due to their multi-modular design and reliance on hand-crafted rules. Learning-based methods, while achieving high planning success rates, face difficulties in generalizing to unseen environments beyond the training data and often require extensive training. To address these limitations, we propose a hybrid approach that combines the strengths of learning-based methods and classical approaches for RGB-only visual navigation. Our method first trains a conditional diffusion model on diverse path-RGB observation pairs. During inference, it integrates the gradients of differentiable scene-specific and task-level costs, guiding the diffusion model to generate valid paths that meet the constraints. This approach alleviates the need for retraining, offering a plug-and-play solution. Extensive experiments in both indoor and outdoor settings, across simulated and real-world scenarios, demonstrate zero-shot transfer capability of our approach, achieving higher success rates and fewer collisions compared to baseline methods. Code will be released at https://github.com/SYSU-RoboticsLab/NaviD. |
| title | NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10003 |