Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914177321271296 |
|---|---|
| author | Xiang, Wentao Zhang, Haokang Yang, Tianhang Chu, Zedong Chu, Ruihang Xie, Shichao Yuan, Yujian Sun, Jian Gu, Zhining Wang, Junjie Wu, Xiaolong Xu, Mu Yang, Yujiu |
| author_facet | Xiang, Wentao Zhang, Haokang Yang, Tianhang Chu, Zedong Chu, Ruihang Xie, Shichao Yuan, Yujian Sun, Jian Gu, Zhining Wang, Junjie Wu, Xiaolong Xu, Mu Yang, Yujiu |
| contents | Object-goal navigation in open-vocabulary settings requires agents to locate novel objects in unseen environments, yet existing approaches suffer from opaque decision-making processes and low success rate on locating unseen objects. To address these challenges, we propose Nav-$R^2$, a framework that explicitly models two critical types of relationships, target-environment modeling and environment-action planning, through structured Chain-of-Thought (CoT) reasoning coupled with a Similarity-Aware Memory. We construct a Nav$R^2$-CoT dataset that teaches the model to perceive the environment, focus on target-related objects in the surrounding context and finally make future action plans. Our SA-Mem preserves the most target-relevant and current observation-relevant features from both temporal and semantic perspectives by compressing video frames and fusing historical observations, while introducing no additional parameters. Compared to previous methods, Nav-R^2 achieves state-of-the-art performance in localizing unseen objects through a streamlined and efficient pipeline, avoiding overfitting to seen object categories while maintaining real-time inference at 2Hz. Resources will be made publicly available at \href{https://github.com/AMAP-EAI/Nav-R2}{github link}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02400 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation Xiang, Wentao Zhang, Haokang Yang, Tianhang Chu, Zedong Chu, Ruihang Xie, Shichao Yuan, Yujian Sun, Jian Gu, Zhining Wang, Junjie Wu, Xiaolong Xu, Mu Yang, Yujiu Computer Vision and Pattern Recognition Object-goal navigation in open-vocabulary settings requires agents to locate novel objects in unseen environments, yet existing approaches suffer from opaque decision-making processes and low success rate on locating unseen objects. To address these challenges, we propose Nav-$R^2$, a framework that explicitly models two critical types of relationships, target-environment modeling and environment-action planning, through structured Chain-of-Thought (CoT) reasoning coupled with a Similarity-Aware Memory. We construct a Nav$R^2$-CoT dataset that teaches the model to perceive the environment, focus on target-related objects in the surrounding context and finally make future action plans. Our SA-Mem preserves the most target-relevant and current observation-relevant features from both temporal and semantic perspectives by compressing video frames and fusing historical observations, while introducing no additional parameters. Compared to previous methods, Nav-R^2 achieves state-of-the-art performance in localizing unseen objects through a streamlined and efficient pipeline, avoiding overfitting to seen object categories while maintaining real-time inference at 2Hz. Resources will be made publicly available at \href{https://github.com/AMAP-EAI/Nav-R2}{github link}. |
| title | Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.02400 |