# Narrate2Nav: Real-Time Visual Navigation with Implicit Language Reasoning in Human-Centric Environments

arXiv: https://arxiv.org/abs/2506.14233 · HTML: https://mlsanity.com/paper/2506.14233/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [ViPlanner: Visual Semantic Imperative Learning for Local Navigation](https://mlsanity.com/paper/2310.00982/) (2023)
- [CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos](https://mlsanity.com/paper/2411.17820/) (2024)
- [NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments](https://mlsanity.com/paper/2402.06838/) (2024)
- [Selective Visual Representations Improve Convergence and Generalization for Embodied AI](https://mlsanity.com/paper/2311.04193/) (2023)
- [OLiVia-Nav: An Online Lifelong Vision Language Approach for Mobile Robot Social Navigation](https://mlsanity.com/paper/2409.13675/) (2024)
- [Social-LLaVA: Enhancing Robot Navigation through Human-Language Reasoning in Social Spaces](https://mlsanity.com/paper/2501.09024/) (2024)
- [The One RING: a Robotic Indoor Navigation Generalist](https://mlsanity.com/paper/2412.14401/) (2024)
- [A Protocol for Validating Social Navigation Policies](https://mlsanity.com/paper/2204.05443/) (2022)
- [ViLAM: Distilling Vision-Language Reasoning into Attention Maps for Social Robot Navigation](https://mlsanity.com/paper/2503.09820/) (2025)
- [VertiFormer: A Data-Efficient Multi-Task Transformer for Off-Road Robot Mobility](https://mlsanity.com/paper/2502.00543/) (2025)

## Built on by (most cited first, 2 of 2)

- [TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments](https://mlsanity.com/paper/2602.02459/) (2026)
- [HumAIN: Human-Aware Implicit Social Robot Navigation](https://mlsanity.com/paper/2607.07357/) (2026)

## Abstract (arXiv)

Large Vision-Language Models (VLMs) have demonstrated potential in enhancing mobile robot navigation in human-centric environments by understanding contextual cues, human intentions, and social dynamics while exhibiting reasoning capabilities. However, their computational complexity and limited sensitivity to continuous numerical data impede real-time performance and precise motion control. To this end, we propose Narrate2Nav, a novel real-time vision-action model that leverages a novel self-supervised learning framework based on the Barlow Twins redundancy reduction loss to embed implicit natural language reasoning, social cues, and human intentions within a visual encoder-enabling reasoning in the model's latent space rather than token space. The model combines RGB inputs, motion commands, and textual signals of scene context during training to bridge from robot observations to low-level motion commands for short-horizon point-goal navigation during deployment. Extensive evaluation of Narrate2Nav across various challenging scenarios in both offline unseen dataset and real-world experiments demonstrates an overall improvement of 52.94 percent and 41.67 percent, respectively, over the next best baseline. Additionally, qualitative comparative analysis of Narrate2Nav's visual encoder attention map against four other baselines demonstrates enhanced attention to navigation-critical scene elements, underscoring its effectiveness in human-centric navigation tasks.