Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities
This addresses the problem of unrealistic assumptions in VLN for robotics researchers, providing a tool to evaluate and improve cross-embodiment adaptability, though it is incremental in offering a new evaluation platform rather than a novel method.
The paper tackles the gap between idealized Vision-and-Language Navigation (VLN) methods and real-world robotic deployment by introducing VLN-PE, a physically realistic platform for humanoid, quadruped, and wheeled robots, revealing significant performance degradation due to factors like limited observation space and environmental variations.
Recent Vision-and-Language Navigation (VLN) advancements are promising, but their idealized assumptions about robot movement and control fail to reflect physically embodied deployment challenges. To bridge this gap, we introduce VLN-PE, a physically realistic VLN platform supporting humanoid, quadruped, and wheeled robots. For the first time, we systematically evaluate several ego-centric VLN methods in physical robotic settings across different technical pipelines, including classification models for single-step discrete action prediction, a diffusion model for dense waypoint prediction, and a train-free, map-based large language model (LLM) integrated with path planning. Our results reveal significant performance degradation due to limited robot observation space, environmental lighting variations, and physical challenges like collisions and falls. This also exposes locomotion constraints for legged robots in complex environments. VLN-PE is highly extensible, allowing seamless integration of new scenes beyond MP3D, thereby enabling more comprehensive VLN evaluation. Despite the weak generalization of current models in physical deployment, VLN-PE provides a new pathway for improving cross-embodiment's overall adaptability. We hope our findings and tools inspire the community to rethink VLN limitations and advance robust, practical VLN models. The code is available at https://crystalsixone.github.io/vln_pe.github.io/.