# NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM

arXiv: https://arxiv.org/abs/2502.11142 · HTML: https://mlsanity.com/paper/2502.11142/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 35 of its 40 references that are in the map.
- First posted on arXiv 16 Feb 2025.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 35)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [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)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [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)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Speaker-Follower Models for Vision-and-Language Navigation](https://mlsanity.com/paper/1806.02724/) (2018)
- [REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments](https://mlsanity.com/paper/1904.10151/) (2019)
- [History Aware Multimodal Transformer for Vision-and-Language Navigation](https://mlsanity.com/paper/2110.13309/) (2021)
- [Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout](https://mlsanity.com/paper/1904.04195/) (2019)
- [Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training](https://mlsanity.com/paper/2002.10638/) (2020)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [Towards Learning a Generalist Model for Embodied Navigation](https://mlsanity.com/paper/2312.02010/) (2023)
- [BEVBert: Multimodal Map Pre-training for Language-guided Navigation](https://mlsanity.com/paper/2212.04385/) (2022)
- [SOON: Scenario Oriented Object Navigation with Graph-based Exploration](https://mlsanity.com/paper/2103.17138/) (2021)
- [Bird's-Eye-View Scene Graph for Vision-Language Navigation](https://mlsanity.com/paper/2308.04758/) (2023)
- [Less is More: Generating Grounded Navigation Instructions from Landmarks](https://mlsanity.com/paper/2111.12872/) (2021)
- [A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning](https://mlsanity.com/paper/2210.03112/) (2022)
- [Vision-and-Language Navigation via Causal Learning](https://mlsanity.com/paper/2404.10241/) (2024)
- [Learning Vision-and-Language Navigation from YouTube Videos](https://mlsanity.com/paper/2307.11984/) (2023)
- [Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation](https://mlsanity.com/paper/2409.18313/) (2024)
- [Lana: A Language-Capable Navigator for Instruction Following and Generation](https://mlsanity.com/paper/2303.08409/) (2023)
- [March in Chat: Interactive Prompting for Remote Embodied Referring Expression](https://mlsanity.com/paper/2308.10141/) (2023)
- [Simple and Effective Synthesis of Indoor 3D Scenes](https://mlsanity.com/paper/2204.02960/) (2022)

## Built on by (most cited first, 19 of 19)

- [Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation](https://mlsanity.com/paper/2505.11383/) (2025)
- [A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI](https://mlsanity.com/paper/2505.01458/) (2025)
- [Meta-Memory: Retrieving and Integrating Semantic-Spatial Memories for Robot Spatial Reasoning](https://mlsanity.com/paper/2509.20754/) (2025)
- [GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning](https://mlsanity.com/paper/2508.09547/) (2025)
- [D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation](https://mlsanity.com/paper/2512.12622/) (2025)
- [Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach](https://mlsanity.com/paper/2601.03534/) (2026)
- [Affordance RAG: Hierarchical Multimodal Retrieval with Affordance-Aware Embodied Memory for Mobile Manipulation](https://mlsanity.com/paper/2512.18987/) (2025)
- [GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation](https://mlsanity.com/paper/2605.22036/) (2026)
- [FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI](https://mlsanity.com/paper/2511.13524/) (2025)
- [TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation](https://mlsanity.com/paper/2605.01700/) (2026)
- [Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator](https://mlsanity.com/paper/2607.05765/) (2026)
- [Exploring the Link Between Bayesian Inference and Embodied Intelligence: Toward Open Physical-World Embodied AI Systems](https://mlsanity.com/paper/2507.21589/) (2025)
- [Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation](https://mlsanity.com/paper/2606.07244/) (2026)
- [Advancing DialNav through Automatic Embodied Dialog Augmentation](https://mlsanity.com/paper/2606.19948/) (2026)
- [NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation](https://mlsanity.com/paper/2607.19695/) (2026)
- [Goal-oriented Navigation Instruction Generation with Tour Video Priors](https://mlsanity.com/paper/2608.08596/) (2026)
- [ExploreAI: Agentic Exploration Knowledge Bases for Reproducible Observable-Regression Testing of Black-Box VR and 3D Applications](https://mlsanity.com/paper/2608.21628/) (2026)
- [Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method](https://mlsanity.com/paper/2609.35965/) (2026)
- [Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping](https://mlsanity.com/paper/2610.15782/) (2026)

## Abstract (arXiv)

Vision-and-Language Navigation (VLN) is an essential skill for embodied agents, allowing them to navigate in 3D environments following natural language instructions. High-performance navigation models require a large amount of training data, the high cost of manually annotating data has seriously hindered this field. Therefore, some previous methods translate trajectory videos into step-by-step instructions for expanding data, but such instructions do not match well with users' communication styles that briefly describe destinations or state specific needs. Moreover, local navigation trajectories overlook global context and high-level task planning. To address these issues, we propose NavRAG, a retrieval-augmented generation (RAG) framework that generates user demand instructions for VLN. NavRAG leverages LLM to build a hierarchical scene description tree for 3D scene understanding from global layout to local details, then simulates various user roles with specific demands to retrieve from the scene tree, generating diverse instructions with LLM. We annotate over 2 million navigation instructions across 861 scenes and evaluate the data quality and navigation performance of trained models.