Skip to content
AI News HubLIVE
Original source2 min read

Deep Learning-Based Lunar Crater Terrain Relative Navigation

Summary

This paper proposes a terrain relative navigation algorithm that combines a deep-learning crater detector with an Extended Kalman Filter for autonomous lunar landing. The detector, designed for the NASA Crater Detection Challenge, analyzes crater features from monocular orbital images and matches them to a global database using Hungarian assignment and consensus-based outlier removal. Simulations show that even with an initial position error of up to 5 km, the system can reduce navigation error to a few hundred meters.

SourcearXiv RoboticsAuthor: Batu Candan, Simone Servadio
Deep Learning-Based Lunar Crater Terrain Relative Navigation
Report an error

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

Correction instructions
Read article

[2606.14776] Deep Learning-Based Lunar Crater Terrain Relative Navigation

[Submitted on 10 Jun 2026]

Title:Deep Learning-Based Lunar Crater Terrain Relative Navigation

View a PDF of the paper titled Deep Learning-Based Lunar Crater Terrain Relative Navigation, by Batu Candan and 1 other authors

View PDF HTML (experimental)

Abstract:Accurate position estimation is crucial for the successful implementation of future lunar landings using autonomous vehicles, especially in dangerous environments with sparse terrain features. In this paper, we propose a terrain relative navigation (TRN) algorithm combining our deep-learning crater detector, which was designed specifically for the NASA Crater Detection Challenge problem, and an Extended Kalman Filter (EKF). Our detector analyzes crater features from the monocular images acquired from orbit, and their matches with craters from a global database are identified via a Hungarian assignment approach followed by the consensus-based outliers removal method. The estimated measurements are then used to refine an EKF, where spacecraft pose estimation in the Lunar-Centered Lunar-Fixed (LCLF) frame of reference, augmented with altitude aiding information, constrains radial drift. The simulation results indicate that even if the spacecraft is off from its actual location up to 5 km, TRN could recover from this situation, achieving navigation error reduction to a few hundred meters. It should be noted that in order to maintain crater feature correspondences, it is important to match the image resolution and the scales within the scene to the detector training set distribution.

Subjects:

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

Cite as: arXiv:2606.14776 [cs.RO]

(or arXiv:2606.14776v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2606.14776

arXiv-issued DOI via DataCite

Submission history

From: Batu Candan [view email] [v1] Wed, 10 Jun 2026 03:03:26 UTC (12,969 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Deep Learning-Based Lunar Crater Terrain Relative Navigation, by Batu Candan and 1 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

InvestorsAdvanced

Key points

  • Combines deep-learning crater detector with Extended Kalman Filter for terrain relative navigation
  • Uses Hungarian assignment and consensus-based outlier removal for crater feature matching
  • Simulations show recovery from 5 km initial position error, reducing error to a few hundred meters
  • Emphasizes need to match image resolution and scene scale to detector training distribution

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