Towards the use of artificial intelligence on the edge in space systems: Challenges and opportunities

G Furano, G Meoni, A Dunne… - IEEE Aerospace and …, 2020 - ieeexplore.ieee.org
The market for remote sensing space-based applications is fundamentally limited by up-and
downlink bandwidth and onboard compute capability for space data handling systems. This …

Reinforcement learning in spacecraft control applications: Advances, prospects, and challenges

M Tipaldi, R Iervolino, PR Massenio - Annual Reviews in Control, 2022 - Elsevier
This paper presents and analyzes Reinforcement Learning (RL) based approaches to solve
spacecraft control problems. Different application fields are considered, eg, guidance …

The final frontier: Deep learning in space

V Kothari, E Liberis, ND Lane - … of the 21st international workshop on …, 2020 - dl.acm.org
Machine learning, particularly deep learning, is being increasing utilised in space
applications, mirroring the groundbreaking success in many earthbound problems …

An fpga-based hardware accelerator for cnns inference on board satellites: benchmarking with myriad 2-based solution for the cloudscout case study

E Rapuano, G Meoni, T Pacini, G Dinelli, G Furano… - Remote Sensing, 2021 - mdpi.com
In recent years, research in the space community has shown a growing interest in Artificial
Intelligence (AI), mostly driven by systems miniaturization and commercial competition. In …

OPS-SAT spacecraft autonomy with TensorFlow lite, unsupervised learning, and online machine learning

G Labrèche, D Evans, D Marszk… - 2022 IEEE …, 2022 - ieeexplore.ieee.org
OPS-SAT is a 3U CubeSat launched on December 18, 2019, it is the first nanosatellite to be
directly owned and operated by the European Space Agency (ESA). The spacecraft is a …

A survey of deep learning on cpus: opportunities and co-optimizations

S Mittal, P Rajput, S Subramoney - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
CPU is a powerful, pervasive, and indispensable platform for running deep learning (DL)
workloads in systems ranging from mobile to extreme-end servers. In this article, we present …

SDebrisNet: A spatial–temporal saliency network for space debris detection

J Tao, Y Cao, M Ding - Applied Sciences, 2023 - mdpi.com
The rapidly growing number of space activities is generating numerous space debris, which
greatly threatens the safety of space operations. Therefore, space-based space debris …

Monte carlo tree search methods for the earth-observing satellite scheduling problem

AP Herrmann, H Schaub - Journal of Aerospace Information Systems, 2022 - arc.aiaa.org
This work explores on-board planning for the single spacecraft, multiple ground station Earth-
observing satellite scheduling problem through artificial neural network function …

Conv1D energy-aware path planner for mobile robots in unstructured environments

M Visca, A Bouton, R Powell, Y Gao… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Driving energy consumption plays a major role in the navigation of mobile robots in
challenging environments, especially if they are left to operate unattended under limited on …

Computational complexities of image plane algorithms for high contrast imaging in space telescopes

L Pogorelyuk, C Haughwout, N Belsten… - Journal of …, 2022 - spiedigitallibrary.org
Future planned space telescopes, such as the IR/O/UV Large Telescope, recommended by
Astro2020 will be used to directly image exo-Earths. They will employ high-order wavefront …