LOG-Nav: Efficient Layout-Aware Object-Goal Navigation with Hierarchical Planning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918237272276992 |
|---|---|
| author | Hou, Jiawei Xiao, Yuting Xue, Xiangyang Zeng, Taiping |
| author_facet | Hou, Jiawei Xiao, Yuting Xue, Xiangyang Zeng, Taiping |
| contents | We introduce LOG-Nav, an efficient layout-aware object-goal navigation approach designed for complex multi-room indoor environments. By planning hierarchically leveraging a global topologigal map with layout information and local imperative approach with detailed scene representation memory, LOG-Nav achieves both efficient and effective navigation. The process is managed by an LLM-powered agent, ensuring seamless effective planning and navigation, without the need for human interaction, complex rewards, or costly training. Our experimental results on the MP3D benchmark achieves 85\% object navigation success rate (SR) and 79\% success rate weighted by path length (SPL) (over 40\% point improvement in SR and 60\% improvement in SPL compared to exsisting methods). Furthermore, we validate the robustness of our approach through virtual agent and real-world robotic deployment, showcasing its capability in practical scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06131 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LOG-Nav: Efficient Layout-Aware Object-Goal Navigation with Hierarchical Planning Hou, Jiawei Xiao, Yuting Xue, Xiangyang Zeng, Taiping Robotics We introduce LOG-Nav, an efficient layout-aware object-goal navigation approach designed for complex multi-room indoor environments. By planning hierarchically leveraging a global topologigal map with layout information and local imperative approach with detailed scene representation memory, LOG-Nav achieves both efficient and effective navigation. The process is managed by an LLM-powered agent, ensuring seamless effective planning and navigation, without the need for human interaction, complex rewards, or costly training. Our experimental results on the MP3D benchmark achieves 85\% object navigation success rate (SR) and 79\% success rate weighted by path length (SPL) (over 40\% point improvement in SR and 60\% improvement in SPL compared to exsisting methods). Furthermore, we validate the robustness of our approach through virtual agent and real-world robotic deployment, showcasing its capability in practical scenarios. |
| title | LOG-Nav: Efficient Layout-Aware Object-Goal Navigation with Hierarchical Planning |
| topic | Robotics |
| url | https://arxiv.org/abs/2505.06131 |