Gregory Badura, Georgia Tech Research Institute; Brian Gunter, Georgia Institute of Technology; Christopher Valenta, Georgia Tech
Keywords: machine learning, satellite attitude, Convolutional Neural Networks (CNNs), bidirectional reflectance distribution function (BRDF), light curves
Abstract:
Convolutional neural networks (CNNs) are employed for the task of inferring the attitude status of resident space objects (RSOs) from simulated light curve measurements of RSOs. Research into the performance of CNNs on synthetic light curve data-sets has shown significant promise that has not yet translated into success when working with empirically collected light curves. This limitation appears to be due to a number of factors including: mixing of bidirectional reflectance distribution function (BRDF) signatures, the effects of sensor noise, and blurring due to atmospheric turbulence. A synthetic data-set of approximately 7500 light curves was generated that takes into account realistic BRDF signatures and environmental parameters. The RSO used in this study was texture mapped with three unique material BRDF signatures: silicon solar panel, glossy paint, and aluminum. A two-step BRDF model inversion of the Beard-Maxwell model was performed using empirically collected data-sets of these materials in order to physically derive the BRDF model parameters. The CNN was trained on light curves resulting from the RSO performing four different maneuvers: tumbling, accelerating in rotational rate, stabilizing in rotational rate, and inactive (or stable in rotation rate). The CNN achieved an overall classification accuracy of 86.2% across the four maneuver classes. A confusion matrix analysis of the different classes of maneuvers suggested that our model performed best when classifying tumbling and accelerating RSOs (94% accuracy) and worst at classifying inactive RSOs (60% accuracy). This performance limitation when classifying inactive RSOs to (1) back-scatter signatures and specular glints within the synthetic light curves of inactive satellites being mistaken as attitude maneuvers, (2) low signal-to-noise ratio due to factors such as atmospheric blurring. These results suggest that CNNs have strong potential for aiding in the problem of classifying satellite attitude status from light curves, but that machine learning research must focus on developing training sets and pre-processing techniques that account for these complications.
Date of Conference: September 15-18, 2020
Track: Non-Resolved Object Characterization