# Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problem

arXiv: https://arxiv.org/abs/2012.15329 · HTML: https://mlsanity.com/paper/2012.15329/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2020.

## Built on by (most cited first, 22 of 22)

- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [Evaluating the World Model Implicit in a Generative Model](https://mlsanity.com/paper/2406.03689/) (2024)
- [VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View](https://mlsanity.com/paper/2307.06082/) (2023)
- [Lana: A Language-Capable Navigator for Instruction Following and Generation](https://mlsanity.com/paper/2303.08409/) (2023)
- [V-IRL: Grounding Virtual Intelligence in Real Life](https://mlsanity.com/paper/2402.03310/) (2024)
- [CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory](https://mlsanity.com/paper/2505.05622/) (2025)
- [Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas](https://mlsanity.com/paper/2203.13838/) (2022)
- [Ground then Navigate: Language-guided Navigation in Dynamic Scenes](https://mlsanity.com/paper/2209.11972/) (2022)
- [NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation](https://mlsanity.com/paper/2411.08579/) (2024)
- [Loc4Plan: Locating Before Planning for Outdoor Vision and Language Navigation](https://mlsanity.com/paper/2408.05090/) (2024)
- [DOROTHIE: Spoken Dialogue for Handling Unexpected Situations in Interactive Autonomous Driving Agents](https://mlsanity.com/paper/2210.12511/) (2022)
- [How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?](https://mlsanity.com/paper/2402.09546/) (2024)
- [CitySeeker: How Do VLMS Explore Embodied Urban Navigation With Implicit Human Needs?](https://mlsanity.com/paper/2512.16755/) (2025)
- [CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality](https://mlsanity.com/paper/2306.11477/) (2023)
- [Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory System](https://mlsanity.com/paper/2506.19433/) (2025)
- [Bridging the Indoor-Outdoor Gap: Vision-Centric Instruction-Guided Embodied Navigation for the Last Meters](https://mlsanity.com/paper/2602.06427/) (2026)
- [Into the Unknown: Generating Geospatial Descriptions for New Environments](https://mlsanity.com/paper/2406.19967/) (2024)
- [City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMs](https://mlsanity.com/paper/2512.15933/) (2025)
- [360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents](https://mlsanity.com/paper/2608.08814/) (2026)
- [TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route](https://mlsanity.com/paper/2509.18173/) (2025)
- [Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification](https://mlsanity.com/paper/2604.16993/) (2026)
- [NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation](https://mlsanity.com/paper/2607.19695/) (2026)

## Abstract (arXiv)

Car-focused navigation services are based on turns and distances of named streets, whereas navigation instructions naturally used by humans are centered around physical objects called landmarks. We present a neural model that takes OpenStreetMap representations as input and learns to generate navigation instructions that contain visible and salient landmarks from human natural language instructions. Routes on the map are encoded in a location- and rotation-invariant graph representation that is decoded into natural language instructions. Our work is based on a novel dataset of 7,672 crowd-sourced instances that have been verified by human navigation in Street View. Our evaluation shows that the navigation instructions generated by our system have similar properties as human-generated instructions, and lead to successful human navigation in Street View.