Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.01477 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912937045655552 |
|---|---|
| author | Xiong, Chaoran Wei, Litao Hu, Xinhao Ma, Kehui Xia, Ziyi Jiang, Zixin Sun, Zhen Pei, Ling |
| author_facet | Xiong, Chaoran Wei, Litao Hu, Xinhao Ma, Kehui Xia, Ziyi Jiang, Zixin Sun, Zhen Pei, Ling |
| contents | Recent advances in large vision-language models (VLMs) and large language models (LLMs) have enabled zero-shot approaches to visual language navigation (VLN), where an agent follows natural language instructions using only ego perception and reasoning. However, existing zero-shot methods typically construct a naive observation graph and perform per-step VLM-LLM inference on it, resulting in high latency and computation costs that limit real-time deployment. To address this, we present SFCo-Nav, an efficient zero-shot VLN framework inspired by the principle of slow-fast cognitive collaboration. SFCo-Nav integrates three key modules: 1) a slow LLM-based planner that produces a strategic chain of subgoals, each linked to an imagined object graph; 2) a fast reactive navigator for real-time object graph construction and subgoal execution; and 3) a lightweight asynchronous slow-fast bridge aligns advanced structured, attributed imagined and perceived graphs to estimate navigation confidence, triggering the slow LLM planner only when necessary. To the best of our knowledge, SFCo-Nav is the first slow-fast collaboration zero-shot VLN system supporting asynchronous LLM triggering according to the internal confidence. Evaluated on the public R2R and REVERIE benchmarks, SFCo-Nav matches or exceeds prior state-of-the-art zero-shot VLN success rates while cutting total token consumption per trajectory by over 50% and running more than 3.5 times faster. Finally, we demonstrate SFCo-Nav on a legged robot in a hotel suite, showcasing its efficiency and practicality in indoor environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01477 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SFCo-Nav: Efficient Zero-Shot Visual Language Navigation via Collaboration of Slow LLM and Fast Attributed Graph Alignment Xiong, Chaoran Wei, Litao Hu, Xinhao Ma, Kehui Xia, Ziyi Jiang, Zixin Sun, Zhen Pei, Ling Robotics Recent advances in large vision-language models (VLMs) and large language models (LLMs) have enabled zero-shot approaches to visual language navigation (VLN), where an agent follows natural language instructions using only ego perception and reasoning. However, existing zero-shot methods typically construct a naive observation graph and perform per-step VLM-LLM inference on it, resulting in high latency and computation costs that limit real-time deployment. To address this, we present SFCo-Nav, an efficient zero-shot VLN framework inspired by the principle of slow-fast cognitive collaboration. SFCo-Nav integrates three key modules: 1) a slow LLM-based planner that produces a strategic chain of subgoals, each linked to an imagined object graph; 2) a fast reactive navigator for real-time object graph construction and subgoal execution; and 3) a lightweight asynchronous slow-fast bridge aligns advanced structured, attributed imagined and perceived graphs to estimate navigation confidence, triggering the slow LLM planner only when necessary. To the best of our knowledge, SFCo-Nav is the first slow-fast collaboration zero-shot VLN system supporting asynchronous LLM triggering according to the internal confidence. Evaluated on the public R2R and REVERIE benchmarks, SFCo-Nav matches or exceeds prior state-of-the-art zero-shot VLN success rates while cutting total token consumption per trajectory by over 50% and running more than 3.5 times faster. Finally, we demonstrate SFCo-Nav on a legged robot in a hotel suite, showcasing its efficiency and practicality in indoor environments. |
| title | SFCo-Nav: Efficient Zero-Shot Visual Language Navigation via Collaboration of Slow LLM and Fast Attributed Graph Alignment |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.01477 |