AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913153428750336 |
|---|---|
| author | Guo, Wenxuan Xu, Xiuwei Liu, Yichen Li, Xiangyu Yin, Hang Chen, Huangxing Zheng, Wenzhao Feng, Jianjiang Zhou, Jie Lu, Jiwen |
| author_facet | Guo, Wenxuan Xu, Xiuwei Liu, Yichen Li, Xiangyu Yin, Hang Chen, Huangxing Zheng, Wenzhao Feng, Jianjiang Zhou, Jie Lu, Jiwen |
| contents | Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of-the-art methods leverage the reasoning capabilities of Vision-Language Models (VLMs) for end-to-end action prediction, they often lack an explicit and explainable understanding of the relationships between the agent, the instruction, and the scene. Conversely, explicitly building a scene map for heuristic planning is intuitively appealing but relies on additional 3D sensors and hinders large-scale vision-language pre-training. To bridge this gap, we propose AwareVLN, a novel framework that equips the navigation model with a self-aware reasoning mechanism, enabling it to understand the agent's state and task progress in a fully end-to-end and data-driven manner. Our approach features two key innovations: (1) a structural reasoning module that fosters spatial and task-oriented self-awareness, and (2) an automatic data engine with progress division for effective training. Extensive experiments on various datasets in Habitat simulator show our AwareVLN significantly outperforms previous state-of-the-art vision-language navigation methods. Project page: https://gwxuan.github.io/AwareVLN/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22816 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation Guo, Wenxuan Xu, Xiuwei Liu, Yichen Li, Xiangyu Yin, Hang Chen, Huangxing Zheng, Wenzhao Feng, Jianjiang Zhou, Jie Lu, Jiwen Robotics Computer Vision and Pattern Recognition Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of-the-art methods leverage the reasoning capabilities of Vision-Language Models (VLMs) for end-to-end action prediction, they often lack an explicit and explainable understanding of the relationships between the agent, the instruction, and the scene. Conversely, explicitly building a scene map for heuristic planning is intuitively appealing but relies on additional 3D sensors and hinders large-scale vision-language pre-training. To bridge this gap, we propose AwareVLN, a novel framework that equips the navigation model with a self-aware reasoning mechanism, enabling it to understand the agent's state and task progress in a fully end-to-end and data-driven manner. Our approach features two key innovations: (1) a structural reasoning module that fosters spatial and task-oriented self-awareness, and (2) an automatic data engine with progress division for effective training. Extensive experiments on various datasets in Habitat simulator show our AwareVLN significantly outperforms previous state-of-the-art vision-language navigation methods. Project page: https://gwxuan.github.io/AwareVLN/. |
| title | AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.22816 |