Skip to content
AI News HubLIVE
Original source2 min read

VISTA: Scale-Aware Visual Navigation via Action History Conditioning

Summary

VISTA addresses the scale vulnerability of normalized actions in vision navigation foundation models by conditioning on action histories and integrating a DINOv3 encoder, achieving 100% goal prediction accuracy and an average of 95% checkpoints crossed in zero-shot real-world deployment.

SourcearXiv RoboticsAuthor: Maeva Guerrier, Koki Kobayashi, Simon Roy, Jana Pavlasek, Giovanni Beltrame
VISTA: Scale-Aware Visual Navigation via Action History Conditioning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.17294] VISTA: Scale-Aware Visual Navigation via Action History Conditioning

[Submitted on 15 Jun 2026]

Title:VISTA: Scale-Aware Visual Navigation via Action History Conditioning

View a PDF of the paper titled VISTA: Scale-Aware Visual Navigation via Action History Conditioning, by Maeva Guerrier and 4 other authors

View PDF HTML (experimental)

Abstract:Vision Navigation Foundation Models (VNMs) promise end-to-end learned navigation policies capable of zero-shot deployment across diverse embodiments and environments. To maintain generality, many vision-based navigation models predict normalized actions. However, this normalization introduces a critical deployment vulnerability: applying different scaling factors to the same normalized trajectory alters its physical geometry, which degrades navigation performance and increases collision risks. We address this vulnerability by conditioning the model on normalized action histories alongside image observations, providing explicit context on the relationship between the model's predictions and the robot's actual physical displacement. Furthermore, current VNMs often struggle in visually repetitive environments that lack distinct features. To resolve this issue, we integrate a DINOv3 encoder, whose richer representations enable our model to capture both spatial and geometric dimensions between observations. VISTA generalizes robustly to out-of-distribution environments, achieving 100% goal prediction accuracy in zero-shot, real-world deployment in Outdoor, Forest and Office settings, and an average of 95% checkpoints crossed, demonstrating consistent path following in unseen environments.

Subjects:

Robotics (cs.RO); Machine Learning (cs.LG)

Cite as: arXiv:2606.17294 [cs.RO]

(or arXiv:2606.17294v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2606.17294

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Maeva Guerrier [view email] [v1] Mon, 15 Jun 2026 21:01:30 UTC (35,708 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled VISTA: Scale-Aware Visual Navigation via Action History Conditioning, by Maeva Guerrier and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-06

Change to browse by:

cs cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Normalized actions change physical geometry under different scaling factors, degrading navigation and raising collision risk
  • VISTA conditions on normalized action histories to provide explicit context between predictions and actual physical displacement
  • A DINOv3 encoder improves performance in visually repetitive environments lacking distinct features
  • Achieves 100% goal prediction accuracy and 95% average checkpoints crossed in zero-shot Outdoor, Forest, and Office deployments

Highlights and analysis are generated automatically and may contain errors. Check the original source.