Kessler : A machine learning library for spacecraft collision avoidance

Acciarini, Giacomo and Pinto, Francesco and Letizia, Francesca and Martinez-Heras, José A. and Merz, Klaus and Bridges, Christopher and Baydin, Atılım Güneş (2021) Kessler : A machine learning library for spacecraft collision avoidance. In: 8th European Conference on Space Debris, 2021-04-20 - 2021-04-23, ESA/ESOC.

[thumbnail of Acciarini-etal-ECSD-2021-A-machine-learning-library-for-spacecraft-collision-avoidance]
Text. Filename: Acciarini_etal_ECSD_2021_A_machine_learning_library_for_spacecraft_collision_avoidance.pdf
Accepted Author Manuscript

Download (1MB)| Preview


As megaconstellations are launched and the space sector grows, space debris pollution is posing an increasing threat to operational spacecraft. Low Earth orbit is a junkyard of dead satellites, rocket bodies, shrapnels, and other debris that travel at very high speed in an uncontrolled manner. Collisions at orbital speeds can generate fragments and potentially trigger a cascade of more collisions endangering the whole population, a scenario known since the late 1970s as the Kessler syndrome. In this work we present Kessler: an open-source Python package for machine learning (ML) applied to collision avoidance. Kessler provides functionalities to import and export conjunction data messages (CDMs) in their standard format and predict the evolution of conjunction events based on explainable ML models. In Kessler we provide Bayesian recurrent neural networks that can be trained with existing collections of CDM data and then deployed in order to predict the contents of future CDMs in a given conjunction event, conditioned on all CDMs received up to now, with associated uncertainty estimates about all predictions. Furthermore Kessler includes a novel generative model of conjunction events and CDM sequences implemented using probabilistic programming, simulating the CDM generation process of the Combined Space Operations Center (CSpOC). The model allows Bayesian inference and also the generation of large datasets of realistic synthetic CDMs that we believe will be pivotal to enable further ML approaches given the sensitive nature and public unavailability of real CDM data.