Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.21189 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915513761792000 |
|---|---|
| author | Chandaka, Bhargav Wang, Gloria X. Chen, Haozhe Che, Henry Zhai, Albert J. Wang, Shenlong |
| author_facet | Chandaka, Bhargav Wang, Gloria X. Chen, Haozhe Che, Henry Zhai, Albert J. Wang, Shenlong |
| contents | When navigating in a man-made environment they haven't visited before--like an office building--humans employ behaviors such as reading signs and asking others for directions. These behaviors help humans reach their destinations efficiently by reducing the need to search through large areas. Existing robot navigation systems lack the ability to execute such behaviors and are thus highly inefficient at navigating within large environments. We present ReasonNav, a modular navigation system which integrates these human-like navigation skills by leveraging the reasoning capabilities of a vision-language model (VLM). We design compact input and output abstractions based on navigation landmarks, allowing the VLM to focus on language understanding and reasoning. We evaluate ReasonNav on real and simulated navigation tasks and show that the agent successfully employs higher-order reasoning to navigate efficiently in large, complex buildings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21189 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Human-like Navigation in a World Built for Humans Chandaka, Bhargav Wang, Gloria X. Chen, Haozhe Che, Henry Zhai, Albert J. Wang, Shenlong Robotics Artificial Intelligence Computer Vision and Pattern Recognition When navigating in a man-made environment they haven't visited before--like an office building--humans employ behaviors such as reading signs and asking others for directions. These behaviors help humans reach their destinations efficiently by reducing the need to search through large areas. Existing robot navigation systems lack the ability to execute such behaviors and are thus highly inefficient at navigating within large environments. We present ReasonNav, a modular navigation system which integrates these human-like navigation skills by leveraging the reasoning capabilities of a vision-language model (VLM). We design compact input and output abstractions based on navigation landmarks, allowing the VLM to focus on language understanding and reasoning. We evaluate ReasonNav on real and simulated navigation tasks and show that the agent successfully employs higher-order reasoning to navigate efficiently in large, complex buildings. |
| title | Human-like Navigation in a World Built for Humans |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.21189 |