SatSplatYOLO: 3D Gaussian Splatting-based Virtual Object Detection Ensembles for Satellite Feature Recognition
This addresses the need for autonomous satellite inspection and servicing in space, but is incremental as it combines existing methods (3D Gaussian splatting and YOLOv5) for a specific domain.
The paper tackles the problem of detecting components of unknown, non-cooperative satellites for autonomous on-orbit missions by using accelerated 3D Gaussian splatting to create a 3D representation, rendering virtual views, and ensembling YOLOv5 detections, resulting in reliable, accurate, and precise detections.
On-orbit servicing (OOS), inspection of spacecraft, and active debris removal (ADR). Such missions require precise rendezvous and proximity operations in the vicinity of non-cooperative, possibly unknown, resident space objects. Safety concerns with manned missions and lag times with ground-based control necessitate complete autonomy. In this article, we present an approach for mapping geometries and high-confidence detection of components of unknown, non-cooperative satellites on orbit. We implement accelerated 3D Gaussian splatting to learn a 3D representation of the satellite, render virtual views of the target, and ensemble the YOLOv5 object detector over the virtual views, resulting in reliable, accurate, and precise satellite component detections. The full pipeline capable of running on-board and stand to enable downstream machine intelligence tasks necessary for autonomous guidance, navigation, and control tasks.