Microsatellites-and-Space-Microsystems/pose_estimation_domain_gap

Two methods for solving domain gap in satellite pose estimation in space exploiting vision Transformers.

21
/ 100
Experimental

This project helps operations engineers and mission controllers accurately determine the 3D position and orientation (pose) of a known satellite from a single 2D image captured in space. It takes synthetic training images and real orbital images as input, producing precise satellite pose estimates. This is designed for those managing active chaser spacecraft tasked with servicing uncooperative targets.

No commits in the last 6 months.

Use this if you need robust and accurate satellite pose estimation for critical space missions, even when your AI models are trained on simulated data.

Not ideal if your mission does not involve autonomous rendezvous and docking or close-proximity operations with other satellites.

satellite-operations orbital-servicing spacecraft-guidance computer-vision-for-space onboard-autonomy
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jul 14, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Microsatellites-and-Space-Microsystems/pose_estimation_domain_gap"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.