Skip to content
Preprint

AnchorVLN: Geometry-Anchored Vision-Language Grounding Reasoning for Open-Vocabulary Navigation

Sep 2026 · 0 citations · 36 references
Computer Science

TL;DR

AnchorVLN is introduced, an open-vocabulary VLN system built on a simple rule: the VLM proposes semantics; geometry decides metrics, which enforces the semantic-geometry boundary without modifying the downstream autonomy stack.

Abstract

Vision-Language Navigation (VLN) in unseen indoor environments is useful in real-world robotics, where an agent must follow natural-language instructions, locate objects, and answer spatial questions without a pre-built map or fixed object vocabulary. Multimodal vision-language models (VLMs) provide strong open-vocabulary grounding and zero-shot reasoning, but struggle to emit reliable metric quantities such as range, bearing, and comparative spatial relations directly from images. Existing approaches address this by folding geometry into hand-engineered pipelines or asking models to output waypoints, requiring changes to the control stack for different robots, tasks, or vocabularies. We introduce AnchorVLN, an open-vocabulary VLN system built on a simple rule: the VLM proposes semantics; geometry decides metrics. It is realised as EMBODIED-NAV-MCP, a Model Context Protocol (MCP) server driven by a VLM agent through a compact set of callable tools. Since no tool accepts distance in metres or bearing in radians, the schema enforces the semantic-geometry boundary without modifying the downstream autonomy stack. We benchmark both tasks of the CMU Vision-Language Navigation Challenge 2026: 30 instruction-following questions over 15 scenes and a frozen 45-question object-reference set. The full system achieves 64.4 percent on instruction following, dropping by 13.3 percentage points without controller modeling (t = 2.77). On object reference, geometric anchoring clears the challenge overlap threshold on 10 of 45 questions, versus 0 of 45 for direct coordinate estimation, reducing median center error from 3.37 m to 2.48 m.

View source

Similar papers

Sep 2026

Spatial and Semantic Reasoning for LLM-Driven Robot Navigation via MCP

This work proposes a non-invasive framework that connects LLM reasoning with ROS-based navigation through a navigation-oriented representation layer, exposed through the Model Context Protocol as standardized, reusable tools so that any MCP-compatible LLM can access them without robot-specific wrappers.

Jungsoo Lee, Jaegyun Park, Wansoo Kim · 0 citations
Preprint Oct 2026

Spa-Bench: A Real-Robot Benchmark for Spatial Grounding in Vision-Language-Action Models

Spa-Bench is introduced, a real-robot benchmark that evaluates spatial grounding across six tabletop tasks covering Object State, Relative Size, Referential Description, Relational Placement, Ordinal Position, and Counting, and shows that the evaluated VLAs can often execute the required manipulations but lack robust s...

Justin Tien-Smith, Matthew Pidden, Rolandos Alexandros Potamias · 1 citation
Preprint Sep 2026

LG-VLN: A Zero-Shot Vision-and-Language Navigation Framework with LangGraph State Orchestration

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...

Jian-He Zhao, Yan-Hua Qiu, Zhi-Yu Zhang et al. · 0 citations
Sep 2026

NaViRrator: Robot Navigation from Human-Readable Maps through a Learned Visual Route

NaViRRator, a framework that translates user-specified start and goal locations on such maps into navigation instructions for a pretrained vision-and-language navigation (VLN) policy, is presented, supporting route-grounded language as a modular interface between human-readable maps and pretrained navigation policies.

Ayun Lee, Jiseon Kim, Giseop Kim · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.