LaViRA: Language-Vision-Robot Actions Translation for Zero-Shot Vision Language Navigation in Continuous Environments
Published in IEEE International Conference on Robotics and Automation (ICRA), 2026
Abstract
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 perceptual grounding, and Robot Action for robust navigation. 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.
This paper proposes LaViRA, a novel framework for zero-shot Vision Language Navigation (VLN) in continuous environments.
Real-Robot Demos
Captured on a Unitree Go1 during real-robot deployment.
Recommended citation:
Hongyu Ding, Ziming Xu, Yudong Fang, You Wu, Zixuan Chen, Jieqi Shi, Jing Huo, Yang Gao. (2026). "LaViRA: Language-Vision-Robot Actions Translation for Zero-Shot Vision Language Navigation in Continuous Environments." IEEE International Conference on Robotics and Automation (ICRA).