Space & aviationResearch findings
Neural Operator for Collision-Aware Trajectory Planning in Spacecraft Swarms
Original published 2026.08.01 07:10 KSTAdded to Blackdeck 2026.11.19 15:03 KST
What has changed?
A neural operator that maps initial state distributions of spacecraft and obstacles to collision-avoidant, fuel-efficient trajectories is proposed.
Key points
- A method for achieving both fuel efficiency and collision avoidance in spacecraft swarms is introduced.
- The neural operator generates trajectories that avoid collisions and conserve fuel based on state distributions.
- The model generalizes zero-shot to 1,000 spacecraft and 11,000 obstacles without retraining.
Connect it to your work
The model generalizes zero-shot to 1,000 spacecraft and 11,000 obstacles without retraining.
What remains unproven
This research note is based on an abstract; check the original for test conditions and application scope.
Originals used for this note
Links open the original publisher in a new tab.