Papers

Spacecraft Collision Risk Assessment with Probabilistic Programming

G Acciarini, F Pinto, S Metz, S Boufelja… - arXiv preprint arXiv …, 2020 - arxiv.org
Computer Science paper cs.LG Suggest

… We believe that simulation-based inference and machine learning will be essential additions to the tool set for addressing these issues in a principled way. We do not foresee any …

Cited by Link to paper

BibTeX

@article{2012.10260v1,
Author        = {Giacomo Acciarini and Francesco Pinto and Sascha Metz and Sarah Boufelja and Sylvester Kaczmarek and Klaus Merz and José A. Martinez-Heras and Francesca Letizia and Christopher Bridges and Atılım Güneş Baydin},
Title         = {Spacecraft Collision Risk Assessment with Probabilistic Programming},
Eprint        = {2012.10260v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {cs.LG},
Abstract      = {Over 34,000 objects bigger than 10 cm in length are known to orbit Earth.
Among them, only a small percentage are active satellites, while the rest of
the population is made of dead satellites, rocket bodies, and debris that pose
a collision threat to operational spacecraft. Furthermore, the predicted growth
of the space sector and the planned launch of megaconstellations will add even
more complexity, therefore causing the collision risk and the burden on space
operators to increase. Managing this complex framework with internationally
agreed methods is pivotal and urgent. In this context, we build a novel
physics-based probabilistic generative model for synthetically generating
conjunction data messages, calibrated using real data. By conditioning on
observations, we use the model to obtain posterior distributions via Bayesian
inference. We show that the probabilistic programming approach to conjunction
assessment can help in making predictions and in finding the parameters that
explain the observed data in conjunction data messages, thus shedding more
light on key variables and orbital characteristics that more likely lead to
conjunction events. Moreover, our technique enables the generation of
physically accurate synthetic datasets of collisions, answering a fundamental
need of the space and machine learning communities working in this area.},
Year          = {2020},
Month         = {Dec},
Note          = {Third Workshop on Machine Learning and the Physical Sciences
  (NeurIPS 2020), Vancouver, Canada},
Url           = {http://arxiv.org/abs/2012.10260v1},
File          = {2012.10260v1.pdf}
}

Share