Spacecraft collision avoidance challenge: Design and results of a machine learning competition

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.

[1]  Can Wang,et al.  Automated Machine Learning for Short-term Electric Load Forecasting , 2019, 2019 IEEE Symposium Series on Computational Intelligence (SSCI).

[2]  Robin Biesbroek,et al.  e.Deorbit – ESA’s Active Debris Removal Mission , 2017 .

[3]  N. Johnson,et al.  Instability of the Present LEO Satellite Populations , 2008 .

[4]  Holger Krag,et al.  Current Collision Avoidance service by ESA's Space Debris Office , 2017 .

[5]  Dario Izzo,et al.  Satellite Pose Estimation Challenge: Dataset, Competition Design, and Results , 2019, IEEE Transactions on Aerospace and Electronic Systems.

[6]  N. N. Smirnov.  Space Debris : Hazard Evaluation and Debris , 2001 .

[7]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[8]  R. Walker,et al.  Cost-effective and robust mitigation of space debris in low earth orbit , 2002 .

[9]  Omer Levy,et al.  GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding , 2018, BlackboxNLP@EMNLP.

[10]  Max Kuhn,et al.  Applied Predictive Modeling , 2013 .

[11]  J.-C. Liou,et al.  Controlling the growth of future LEO debris populations with active debris removal , 2010 .

[12]  George Athanasopoulos,et al.  Forecasting: principles and practice , 2013 .

[13]  Joseph Pelton,et al.  Overview of Commercial Small Satellite Systems in the “New Space” Age , 2019 .

[14]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[15]  Trevor Hastie,et al.  Boosting and Additive Trees , 2009 .

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Holger Krag,et al.  Consideration of Space Debris Mitigation Requirements in the Operation of LEO Missions , 2012 .

[18]  Deok-Jin Lee,et al.  Probability of Collision Error Analysis , 1999 .

[19]  Vlado Menkovski,et al.  Anomaly Detection for imbalanced datasets with Deep Generative Models , 2018, ArXiv.

[20]  H. Krag,et al.  Operational support to collision avoidance activities by ESA’s space debris office , 2016 .

[21]  Holger Krag,et al.  CREAM-ESA's Proposal for Collision Risk Estimation and Automated Mitigation , 2019 .

[22]  K. Merz,et al.  Operational Collision Avoidance at ESOC , 2018 .

[23]  Eric L. Christiansen,et al.  Hypervelocity impact testing of advanced materials and structures for micrometeoroid and orbital debris shielding , 2013 .

[24]  Bin Chen,et al.  TESTING FOR THE MARKOV PROPERTY IN TIME SERIES , 2011, Econometric Theory.

[25]  Rob J. Hyndman,et al.  A brief history of forecasting competitions , 2020 .

[26]  Dario Izzo,et al.  Effects of Orbital Parameter Uncertainties , 2005 .

[27]  Jonas Mueller,et al.  Siamese Recurrent Architectures for Learning Sentence Similarity , 2016, AAAI.

[28]  Randal S. Olson,et al.  Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science , 2016, GECCO.