Galen O’Shea
-
Deploying Artificial Intelligence Capabilities by Hybridizing a Neural Network on a Satellite
Read more: Deploying Artificial Intelligence Capabilities by Hybridizing a Neural Network on a SatelliteIn this paper wepresent one of the first cases of hybridization of a convolutional neural network in space,validated onboard ESA’s OPS-SAT with the SmartCam convolutional neural network. Copyright © 2023 by Mission Control Space Services Inc.. Published by the American Institute of Aeronautics and Astronautics, Inc., with permission.
-
Development and Test of Deep Learning Techniques for Stereo-based Pose Estimation of Small Satellites
Read more: Development and Test of Deep Learning Techniques for Stereo-based Pose Estimation of Small SatellitesIn this paper, we outline our approach and limited results from a recently completed project on the development and test of a neural network designed to allow a servicing spacecraft to estimate the pose of a target object in proximity, in real-time, using stereo vision, so as to enable planning for subsequent manoeuvres.
-
Advancing AI Reliability for Space Missions through Machine Learning Operations
Read more: Advancing AI Reliability for Space Missions through Machine Learning OperationsMission Control, with the support of the Canadian Space Agency, is developing and launching Mission Persistence in 2025 to introduce and test new approaches to AI in space operations. Mission Control’s technology demonstration will maintain onboard AI models in-orbit through the use of an MLOps pipeline in the ground segment that divides pre-production data and…
-
Federated Learning on Edge Devices in a Lunar Analogue Environment
Read more: Federated Learning on Edge Devices in a Lunar Analogue EnvironmentTo explore the use of federated learning in a lunar operations scenario, we implemented federated learning in a lunar analogue environment across a network of distributed lunar nodes, including rovers, and trained a flight-ready deep learning lunar terrain classifier, MoonNet Federated. We offer our insights as to how to construct an optimal federation for a…
