Space debris populating the geostationary orbit is a hazardous threat to active satellites and motivates a routine surveillance of this orbital region by ground-based optical telescopes. Due to limited resources short measurement arcs, called tracklets, are collected that do not provide sufficient information to determine full orbital states of the measured objects.The paper proposes a method to determine the orbit of an object using the available information of two tracklets, i.e. their line-of-sights and their derivatives. The line-of-sights at both observation epochs are augmented with range hypotheses in order to obtain possible orbit candidates. The derivatives of the line-of-sights are used to determine whether an orbit hypothesis fits to the actual measured tracklets or not. Computational optimization schemes are exploited to find the best hypotheses. If a hypothesis is found that approximates both tracklets sufficiently, they are both associated to each other. The association and run-time performance is assessed using real measurements.
Spacecraft collision avoidance procedures have become an essential part of satellite operations. Complex and constantly updated estimates of the collision risk between orbiting objects inform the various operators who can then plan risk mitigation measures. Such measures could be aided by the development of suitable machine learning models predicting, for example, the evolution of the collision risk in time. In an attempt to study this opportunity, the European Space Agency released, in October 2019, a large curated dataset containing information about close approach events, in the form of Conjunction Data Messages (CDMs), collected from 2015 to 2019. This dataset was used in the Spacecraft Collision Avoidance Challenge, a machine learning competition where participants had to build models to predict the final collision risk between orbiting objects. This paper describes the design and results of the competition and discusses the challenges and lessons learned when applying machine learning methods to this problem domain.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.