mlsanityData to 14 Oct 2026

Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas

arXiv 2203.13838 ↗First posted 25 Mar 2022cs.CV cs.AI cs.CLcited by 24

Not on the map. Why?

Abstract (arXiv)

Vision and language navigation (VLN) is a challenging visually-grounded language understanding task. Given a natural language navigation instruction, a visual agent interacts with a graph-based environment equipped with panorama images and tries to follow the described route. Most prior work has been conducted in indoor scenarios where best results were obtained for navigation on routes that are similar to the training routes, with sharp drops in performance when testing on unseen environments. We focus on VLN in outdoor scenarios and find that in contrast to indoor VLN, most of the gain in outdoor VLN on unseen data is due to features like junction type embedding or heading delta that are specific to the respective environment graph, while image information plays a very minor role in generalizing VLN to unseen outdoor areas. These findings show a bias to specifics of graph representations of urban environments, demanding that VLN tasks grow in scale and diversity of geographical environments.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 25 Mar 2022.

Builds on

25 of 34 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  7. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  8. 2020Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environmentscited by 441
  9. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
  10. 2019Learning to Navigate Unseen Environments: Back Translation with Environmental Dropoutcited by 244
  11. 2018Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environmentscited by 239
  12. 2019BPE-Dropout: Simple and Effective Subword Regularizationcited by 195
13 more
  1. 2020Improving Vision-and-Language Navigation with Image-Text Pairs from the Webcited by 177
  2. 2019Stay on the Path: Instruction Fidelity in Vision-and-Language Navigationcited by 130
  3. 2018Learning to Navigate in Cities Without a Mapcited by 104
  4. 2017Gated-Attention Architectures for Task-Oriented Language Groundingcited by 72
  5. 2019Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigationcited by 55
  6. 2021On the Evaluation of Vision-and-Language Navigation Instructionscited by 45
  7. 2020Diagnosing the Environment Bias in Vision-and-Language Navigationcited by 41
  8. 2021Diagnosing Vision-and-Language Navigation: What Really Matterscited by 36
  9. 2018Shifting the Baseline: Single Modality Performance on Visual Navigation & QAcited by 30
  10. 2019Learning To Follow Directions in Street Viewcited by 29
  11. 2020Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigationcited by 22
  12. 2020Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problemcited by 22
  13. 2020Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigationcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 10; 2025: 5; 2026: 3.

24 papers.

Sort:

By area:

  1. 2024Evaluating the World Model Implicit in a Generative Modelcited by 113
  2. 2023VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street Viewcited by 67
  3. 2025UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobilitycited by 49
  4. 2023Learning Vision-and-Language Navigation from YouTube Videoscited by 47
  5. 2022Ground then Navigate: Language-guided Navigation in Dynamic Scenescited by 20
  6. 2024Policy Improvement using Language Feedback Modelscited by 16
  7. 2024VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigationcited by 14
  8. 2024Loc4Plan: Locating Before Planning for Outdoor Vision and Language Navigationcited by 11
  9. 2023Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertaintycited by 9
  10. 2024Vision-Language Navigation with Embodied Intelligence: A Surveycited by 9
  11. 2023LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Followingcited by 8
  12. 2024How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?cited by 8
12 more
  1. 2025UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectoriescited by 6
  2. 2022A Priority Map for Vision-and-Language Navigation with Trajectory Plans and Feature-Location Cuescited by 5
  3. 2025Mem4Nav: Boosting Vision-and-Language Navigation in Urban Environments with a Hierarchical Spatial-Cognition Long-Short Memory Systemcited by 3
  4. 2024Open-Set 3D Semantic Instance Maps for Vision Language Navigation -- O3D-SIMcited by 2
  5. 2024Multi-Task Domain Adaptation for Language Grounding with 3D Objectscited by 2
  6. 2024IVLMap: Instance-Aware Visual Language Grounding for Consumer Robot Navigationcited by 1
  7. 2025GENNAV: Polygon Mask Generation for Generalized Referring Navigable Regionscited by 1
  8. 2025City Navigation in the Wild: Exploring Emergent Navigation from Web-Scale Knowledge in MLLMscited by 1
  9. 2026A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigationcited by 1
  10. 2024Temporal-Spatial Object Relations Modeling for Vision-and-Language Navigationcited by 0
  11. 2026PM-Nav: Priori-Map Guided Embodied Navigation in Functional Buildingscited by 0
  12. 2026Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectificationcited by 0