aiqbench analysis
LG-VLN introduces a monocular zero-shot framework for vision-and-language navigation by integrating shared visual features with LangGraph-based state orchestration to manage complex decision-making loops. This approach eliminates the need for specialized sensors like LiDAR while maintaining spatial-semantic consistency through dense feature sharing and modular failure recovery mechanisms. The method demonstrates that explicit state graph representation significantly enhances performance in continuous-environment navigation tasks using only RGB input.
LG-VLN: A Zero-Shot Vision-and-Language Navigation Framework with LangGraph State Orchestration
arXiv:2609.15098v1 Announce Type: cross Abstract: Continuous-environment vision-and-language navigation (VLN-CE) requires interpreting natural-language instructions in unseen 3D environments and executing continuous low-level actions. Existing methods often depend on LiDAR, panoramic cameras, or extra sensors; separate geometric-mapping and semantic-navigation visual representations can cause long-trajectory spatial-semantic inconsistencies. We propose LG-VLN, a monocular zero-shot framework with shared visual features and LangGraph-based state orchestration. An online feed-forward 3D reconstruction network predicts depth, camera poses, and dense point clouds for agent-pose estimation and global map fusion. Geometry and navigation share dense CleanDIFT features: semantic consistency rejects incorrect inter-frame correspondences, while target-instance constraints define visual references whose similarity combines with local BLIP-2 image-text relevance to form a semantic value map. LangGraph represents instruction parsing, geometric perception, semantic value updates, path planning, action execution, and failure recovery as a directed state graph with conditional transitions, persistent state, and modular recovery mechanisms. On a fixed 550-episode subset of the R2R-CE val-unseen split, LG-VLN achieves 21.3% success and 12.1% success weighted by path length. Ablations show shared semantic features improve navigation, further boosted by combining visual similarity and image-text relevance. Results establish shared visual representations and explicit state orchestration as effective for zero-shot VLN-CE using monocular RGB alone. Code will be publicly released for reproducibility.
Abstract:Continuous-environment vision-and-language navigation (VLN-CE) requires interpreting natural-language instructions in unseen 3D environments and executing continuous low-level actions. Existing methods often depend on LiDAR, panoramic cameras, or extra sensors; separate geometric-mapping and semantic-navigation visual representations can cause long-trajectory spatial-semantic inconsistencies. We propose LG-VLN, a monocular zero-shot framework with shared visual features and LangGraph-based state orchestration. An online feed-forward 3D reconstruction network predicts depth, camera poses, and dense point clouds for agent-pose estimation and global map fusion. Geometry and navigation share dense CleanDIFT features: semantic consistency rejects incorrect inter-frame correspondences, while target-instance constraints define visual references whose similarity combines with local BLIP-2 image-text relevance to form a semantic value map. LangGraph represents instruction parsing, geometric perception, semantic value updates, path planning, action execution, and failure recovery as a directed state graph with conditional transitions, persistent state, and modular recovery mechanisms. On a fixed 550-episode subset of the R2R-CE val-unseen split, LG-VLN achieves 21.3% success and 12.1% success weighted by path length. Ablations show shared semantic features improve navigation, further boosted by combining visual similarity and image-text relevance. Results establish shared visual representations and explicit state orchestration as effective for zero-shot VLN-CE using monocular RGB alone. Code will be publicly released for reproducibility.
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
arXiv:2609.15098 [cs.CV]
(or arXiv:2609.15098v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.15098 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 299 words
Related coverage
SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning
arXiv · Jun 9, 2026
VLN-AVP: Zero-Shot Vision-Language Navigation with Hybrid Long-Short-Term Memory for Autonomous Valet Parking
arXiv · Jul 21, 2026
AirAnchor: Bridging Local and Global Spatial Information for Zero-Shot Aerial Vision-and-Language Navigation
arXiv · Sep 9, 2026
HiMemVLN: Enhancing Reliability of Open-Source Zero-Shot Vision-and-Language Navigation with Hierarchical Memory System
arXiv · Jul 21, 2026