LaViRA: Language-Vision-Robot Actions Translation for Zero-Shot Vision Language Navigation in Continuous Environments
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914368428441600 |
|---|---|
| author | Ding, Hongyu Xu, Ziming Fang, Yudong Wu, You Chen, Zixuan Shi, Jieqi Huo, Jing Zhang, Yifan Gao, Yang |
| author_facet | Ding, Hongyu Xu, Ziming Fang, Yudong Wu, You Chen, Zixuan Shi, Jieqi Huo, Jing Zhang, Yifan Gao, Yang |
| contents | LaViRA: Zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to navigate unseen environments based on natural language instructions without any prior training. Current methods face a critical trade-off: either rely on environment-specific waypoint predictors that limit scene generalization, or underutilize the reasoning capabilities of large models during navigation. We introduce LaViRA, a simple yet effective zero-shot framework that addresses this dilemma by decomposing action into a coarse-to-fine hierarchy: Language Action for high-level planning, Vision Action for middle-level perceptual grounding, and Robot Action for low-level control. This modular decomposition allows us to leverage the distinct strengths of different scales of Multimodal Large Language Models (MLLMs) at each stage, creating a system that is powerful in its reasoning, grounding and practical control. LaViRA significantly outperforms existing state-of-the-art methods on the VLN-CE benchmark, demonstrating superior generalization capabilities in unseen environments, while maintaining transparency and efficiency for real-world deployment. Project page: https://robo-lavira.github.io/lavira-zs-vln/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19655 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LaViRA: Language-Vision-Robot Actions Translation for Zero-Shot Vision Language Navigation in Continuous Environments Ding, Hongyu Xu, Ziming Fang, Yudong Wu, You Chen, Zixuan Shi, Jieqi Huo, Jing Zhang, Yifan Gao, Yang Robotics LaViRA: Zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to navigate unseen environments based on natural language instructions without any prior training. Current methods face a critical trade-off: either rely on environment-specific waypoint predictors that limit scene generalization, or underutilize the reasoning capabilities of large models during navigation. We introduce LaViRA, a simple yet effective zero-shot framework that addresses this dilemma by decomposing action into a coarse-to-fine hierarchy: Language Action for high-level planning, Vision Action for middle-level perceptual grounding, and Robot Action for low-level control. This modular decomposition allows us to leverage the distinct strengths of different scales of Multimodal Large Language Models (MLLMs) at each stage, creating a system that is powerful in its reasoning, grounding and practical control. LaViRA significantly outperforms existing state-of-the-art methods on the VLN-CE benchmark, demonstrating superior generalization capabilities in unseen environments, while maintaining transparency and efficiency for real-world deployment. Project page: https://robo-lavira.github.io/lavira-zs-vln/ |
| title | LaViRA: Language-Vision-Robot Actions Translation for Zero-Shot Vision Language Navigation in Continuous Environments |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.19655 |