Abstract
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 various operators who can then plan risk mitigation measures. Such measures can be aided by the development of suitable machine learning (ML) models that predict, for example, the evolution of the collision risk over time. In October 2019, in an attempt to study this opportunity, the European Space Agency released a large curated dataset containing information about close approach events in the form of conjunction data messages (CDMs), which was collected from 2015 to 2019. This dataset was used in the Spacecraft Collision Avoidance Challenge, which was an ML 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 ML methods to this problem domain.
Highlights
Spacecraft collision avoidance procedures have become an essential part of satellite operations
The participants were requested to predict the final risk of collision at the time of closest approach (TCA) between a satellite and a space object using data cropped at two days to the TCA
The database of conjunction events constitutes an important historical record of risky conjunction events that occurred in low Earth orbit (LEO) and creates the opportunity to test the use of machine learning (ML) approaches in the collision avoidance process
Summary
To defining guidelines to mitigate collision risk and preserve the space environment for future generations [6]. F. Simoes, et al. To obtain a first assessment of the risk posed to an active satellite operating, for example, in a Sunsynchronous orbit, we computed the closest distance of a Sun-synchronous satellite to the LEO population and its distribution at random epochs and within a two-year window. A Weibull distribution can be fitted to the obtained data, where results from extreme value statistics justify its use to make preliminary inferences on collision probabilities [11]. Such inferences are very sensitive to the Weibull distribution parameters and, in particular, to the behavior of its tail close to the origin. Satellite collision avoidance systems are expected to be increasingly important, and their further improvement, in particular their full automation, will be a priority in the coming decades [14]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
