Research/ ORBITAL ROBOTICS
Real-Time, Flight-Ready, Non-Cooperative Spacecraft Pose Estimation Using Monocular Imagery
Kevin Black, Shrivu Shankar, Daniel Fonseka, Jacob Deutsch, Abhimanyu Dhir, and Maruthi R. Akella
Perception & State EstimationarXiv: cs.CV · Learning-based MethodsarXiv: cs.LG · Rendezvous, Proximity Ops & DockingOpenAlex keyword: non-cooperative spacecraft
arXivcs.CV · cs.LG · cs.ROOpenAlexSpace Satellite Systems and Control · Advanced Neural Network Applications · Spacecraft Dynamics and Control
A key requirement for autonomous on-orbit proximity operations is the estimation of a target spacecraft's relative pose (position and orientation). It is desirable to employ monocular cameras for this problem due to their low cost, weight, and power requirements. This work presents a novel convolutional neural network (CNN)-based monocular pose estimation system that achieves state-of-the-art accuracy with low computational demand. In combination with a Blender-based synthetic data generation scheme, the system demonstrates the ability to generalize from purely synthetic training data to real in-space imagery of the Northrop Grumman Enhanced Cygnus spacecraft. Additionally, the system achieves real-time performance on low-power flight-like hardware.
Comments: Presented at the 31st AAS/AIAA Space Flight Mechanics Meeting, February 2021. 16 pages, 7 figures