# Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation

arXiv: https://arxiv.org/abs/2606.00095 · HTML: https://mlsanity.com/paper/2606.00095/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 43 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 30 of 41)

- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation](https://mlsanity.com/paper/2312.03275/) (2023)
- [PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs](https://mlsanity.com/paper/2402.07872/) (2024)
- [ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2304.03047/) (2023)
- [InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment](https://mlsanity.com/paper/2406.04882/) (2024)
- [Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks](https://mlsanity.com/paper/2412.06224/) (2024)
- [Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.02764/) (2022)
- [Waypoint Models for Instruction-guided Navigation in Continuous Environments](https://mlsanity.com/paper/2110.02207/) (2021)
- [GridMM: Grid Memory Map for Vision-and-Language Navigation](https://mlsanity.com/paper/2307.12907/) (2023)
- [Scaling Data Generation in Vision-and-Language Navigation](https://mlsanity.com/paper/2307.15644/) (2023)
- [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025)
- [Sim-to-Real Transfer for Vision-and-Language Navigation](https://mlsanity.com/paper/2011.03807/) (2020)
- [MapGPT: Map-Guided Prompting with Adaptive Path Planning for Vision-and-Language Navigation](https://mlsanity.com/paper/2401.07314/) (2024)
- [Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method](https://mlsanity.com/paper/2412.09082/) (2024)
- [Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation](https://mlsanity.com/paper/2407.05890/) (2024)
- [VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.17221/) (2025)
- [A2Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models](https://mlsanity.com/paper/2308.07997/) (2023)
- [Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs](https://mlsanity.com/paper/2409.18794/) (2024)
- [MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation](https://mlsanity.com/paper/2502.13451/) (2025)

## Built on by (most cited first, 6 of 6)

- [AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness](https://mlsanity.com/paper/2606.10577/) (2026)
- [HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness](https://mlsanity.com/paper/2609.15195/) (2026)
- [The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2608.04589/) (2026)
- [Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation](https://mlsanity.com/paper/2609.29934/) (2026)
- [Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation](https://mlsanity.com/paper/2609.32292/) (2026)
- [Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds](https://mlsanity.com/paper/2609.39166/) (2026)

## Abstract (arXiv)

Vision-Language Navigation (VLN) enables embodied agents to reach target locations in unseen environments by following language instructions. Despite recent progress with vision-language models (VLMs), a critical semantic-geometric gap remains: while VLMs excel at language and 2D visual understanding, they struggle with 3D spatial reasoning and fail to capture the causal dynamics between actions and spatial transitions, resulting in unreliable navigation, particularly in zero-shot settings. To bridge this gap, we propose a Hierarchical Semantic-Geometric Map (HSGM) that transforms 3D geometric information into a structured representation compatible with VLMs, effectively linking them to the physical world. Specifically, HSGM is represented as a multi-channel top-down map organized into three levels: (1) geometric level that records navigable regions and obstacles, (2) semantic level that represents objects and their relations, and (3) decision level that supports high-level task reasoning and goal selection. During navigation, the VLM acts as a high-level semantic planner, interpreting the spatial layout encoded in the HSGM to select geometrically valid waypoints, while low-level, collision-free movements between waypoints are executed by a classical path-planning algorithm, fully decoupling semantic reasoning from action execution. Additionally, complex instructions are decomposed into subtasks to alleviate the problem of progress forgetting or hallucinating in long-horizon navigation. Extensive experiments on R2R-CE and RxR-CE benchmarks demonstrate that our zero-shot framework achieves state-of-the-art performance and even outperforms several supervised methods. Code is available at https://github.com/Teacher-Tom/HSGM_public.