Skip to search formSkip to main contentSkip to account menu

Space Objects Classification via Light-Curve Measurements: Deep Convolutional Neural Networks and Model-based Transfer Learning

A data-driven method to classification of SO based on a deep learning approach that takes advantage of the representational power of deep neural networks is presented and the concept of model-based transfer learning is proposed as possible path forward to increase the accuracy and speedup the training process.

Lumio: Achieving autonomous operations for lunar exploration with a cubesat

The Lunar Meteoroid Impacts Observer (LUMIO) is one of the four projects selected within ESA’s SysNova competition to develop a small satellite for scientific and technology demonstration purposes to…
View via Publisher (opens in a new tab)

Modeling irregular small bodies gravity field via extreme learning machines and Bayesian optimization

View via Publisher (opens in a new tab)

Space Objects Classification and Characterization via Deep Learning and Light Curves: Applications to Space Traffic Management

LUMIO: An Autonomous CubeSat for Lunar Exploration

This chapter describes the mission concept and focuses on the performance of a novel navigation concept using Moon images taken as byproduct of the LUMIO-Cam operations, aiming at autonomous orbit-attitude navigation and control.
View via Publisher (opens in a new tab)

LUMIO: a Cubesat at Earth-Moon L2

The Lunar Meteoroid Impact Observer (LUMIO) is a CubeSat mission to observe, quantify, and characterize the meteoroid impacts by detecting their flashes on the lunar farside. LUMIO is one of the two…

Space Objects Classification via Light-Curve Measurements Using Deep Convolutional Neural Networks

The design, train, and validate a Convolutional Neural Network capable of learning to classify SOs from collected light-curve measurements, which relies on a physics-based model capable of accurately representing SO reflected light as a function of time, size, shape, and state of motion.
View on Springer (opens in a new tab)

Space Debris Identification and Characterization via Deep Meta-Learning

A new class of deep learning algorithms that can discriminate debris from non-debris objects using light curve real and simulated data is described and preliminary results show that meta-learning framework can efficiently and quickly learn to discriminatebris from nondebris object under a variety of observational conditions.

On-Orbit Smart Camera System to Observe Illuminated and Unilluminated Space Objects

The performance of the space object detection algorithm coupled with a spacecraft guidance, navigation, and control system is demonstrated and enables detecting and tracking objects that can't readily be detected by humans.
View PDF on arXiv (opens in a new tab)

Training the Next Generation in Space Situational Awareness Research

The experience shows that development of hardware and software for SSA research could be accomplished in an academic environment that would enable the training of the next generation with active support from local small businesses.
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)