Mobile-URSONet: an Embeddable Neural Network for Onboard Spacecraft Pose Estimation
This work addresses the need for embeddable pose estimation for spacecraft autonomy, but it is incremental as it optimizes an existing method for computational constraints.
The paper tackles the problem of spacecraft pose estimation by proposing Mobile-URSONet, a neural network with 178 times fewer parameters than URSONet, while degrading accuracy by no more than four times.
Spacecraft pose estimation is an essential computer vision application that can improve the autonomy of in-orbit operations. An ESA/Stanford competition brought out solutions that seem hardly compatible with the constraints imposed on spacecraft onboard computers. URSONet is among the best in the competition for its generalization capabilities but at the cost of a tremendous number of parameters and high computational complexity. In this paper, we propose Mobile-URSONet: a spacecraft pose estimation convolutional neural network with 178 times fewer parameters while degrading accuracy by no more than four times compared to URSONet.