Kernel Embedding Approaches to Orbit Determination of Spacecraft Clusters

This paper presents a novel formulation and solution of orbit determination over finite time horizons as a learning problem. We present an approach to orbit determination under very broad conditions that are satisfied for n-body problems. These weak conditions allow us to perform orbit determination with noisy and highly non-linear observations such as those presented by range-rate only (Doppler only) observations. We show that domain generalization and distribution regression techniques can learn to estimate orbits of a group of satellites and identify individual satellites especially with prior understanding of correlations between orbits and provide asymptotic convergence conditions. The approach presented requires only visibility and observability of the underlying state from observations and is particularly useful for autonomous spacecraft operations using low-cost ground stations or sensors. We validate the orbit determination approach using observations of two spacecraft (GRIFEX and MCubed-2) along with synthetic datasets of multiple spacecraft deployments and lunar orbits. We also provide a comparison with the standard techniques (EKF) under highly noisy conditions.

[1]  Andreas Maurer,et al.  Transfer bounds for linear feature learning , 2009, Machine Learning.

[2]  Thomas Schildknecht,et al.  Optical surveys for space debris , 2007 .

[3]  Hugh G. Lewis,et al.  The space debris environment: future evolution , 2011, The Aeronautical Journal (1968).

[4]  Barnabás Póczos,et al.  Two-stage sampled learning theory on distributions , 2015, AISTATS.

[5]  W. Rudin Principles of mathematical analysis , 1964 .

[6]  Deok-Jin Lee Nonlinear bayesian filtering with applications to estimation and navigation , 2005 .

[7]  Alessandro Rossi,et al.  Collision risk against space debris in Earth orbits , 2006 .

[8]  Michael I. Jordan,et al.  Convexity, Classification, and Risk Bounds , 2006 .

[9]  Kyle Colton,et al.  Supporting the Flock: Building a Ground Station Network for Autonomy and Reliability , 2016 .

[10]  Ingo Steinwart,et al.  On the Influence of the Kernel on the Consistency of Support Vector Machines , 2002, J. Mach. Learn. Res..

[11]  Barnabás Póczos,et al.  Distribution-Free Distribution Regression , 2013, AISTATS.

[12]  R. Bass,et al.  Review: P. Billingsley, Convergence of probability measures , 1971 .

[13]  Armando Fox,et al.  A Framework For Robust and Flexible Ground Station Networks , 2006, J. Aerosp. Comput. Inf. Commun..

[14]  A. Milani,et al.  Theory of Orbit Determination , 2009 .

[15]  Shai Ben-David,et al.  Multi-task and Lifelong Learning of Kernels , 2015, ALT.

[16]  Gilles Blanchard,et al.  Generalizing from Several Related Classification Tasks to a New Unlabeled Sample , 2011, NIPS.

[17]  Arthur Gretton,et al.  Learning Theory for Distribution Regression , 2014, J. Mach. Learn. Res..

[18]  D. Vallado,et al.  ACCURATE ORBIT DETERMINATION FROM SHORT-ARC DENSE OBSERVATIONAL DATA , 1998 .

[19]  D. Farnocchia,et al.  Innovative methods of correlation and orbit determination for space debris , 2009, 0911.0149.

[20]  Gilles Blanchard,et al.  Domain Generalization by Marginal Transfer Learning , 2017, J. Mach. Learn. Res..

[21]  Jay Wyatt,et al.  Architecture and CONOPS of Next-Generation Ground Network for Communications and Tracking of Interplanetary SmallSats , 2016 .

[22]  E. D. Vito,et al.  Risk Bounds for Regularized Least-squares Algorithm with Operator-valued kernels , 2005 .

[23]  Bernhard Schölkopf,et al.  Domain Generalization via Invariant Feature Representation , 2013, ICML.

[24]  David M. Rider,et al.  NASA’s Earth Science Technology Office CubeSats for Technology Maturation , 2013 .

[25]  Saptarshi Bandyopadhyay,et al.  Review of Formation Flying and Constellation Missions Using Nanosatellites , 2016 .

[26]  Aniket Anand Deshmukh,et al.  Multiclass Domain Generalization , 2017 .

[27]  A. Krener The Convergence of the Extended Kalman Filter , 2002, math/0212255.

[28]  A. Caponnetto,et al.  Optimal Rates for the Regularized Least-Squares Algorithm , 2007, Found. Comput. Math..

[29]  Hamid Hemmati Deep‐Space Communications and Navigation Series , 2006 .

[30]  E. Belbruno,et al.  Capture Dynamics and Chaotic Motions in Celestial Mechanics , 2004 .

[31]  Andrew Vernon Schaeperkoetter A Comprehensive Comparison Between Angles-Only Initial Orbit Determination Techniques , 2012 .

[32]  Sudharman K. Jayaweera,et al.  Blind cyclostationary feature detection based spectrum sensing for autonomous self-learning cognitive radios , 2012, 2012 IEEE International Conference on Communications (ICC).

[33]  Fabio Curti,et al.  A genetic algorithm for Initial Orbit Determination from a too short arc optical observation , 2013 .

[34]  Alessandro Rossi,et al.  Orbit determination of space debris: admissible regions , 2007 .

[35]  Andreas Christmann,et al.  Universal Kernels on Non-Standard Input Spaces , 2010, NIPS.

[36]  James Agi Wright Orbit Determination Tool Kit Theory and Algorithms , 2013 .

[37]  Kyle J. DeMars,et al.  Probabilistic Initial Orbit Determination Using Gaussian Mixture Models , 2013 .

[38]  Mark L. Psiaki,et al.  Gaussian Mixture Approximation of Angles-Only Initial Orbit Determination Likelihood Function , 2017 .

[39]  Joshua Schoolcraft,et al.  MarCO: Interplanetary Mission Development on a CubeSat Scale , 2016 .

[40]  Greg Richardson,et al.  Small Satellite Trends 2009-2013 , 2015 .

[41]  J. Junkins,et al.  Optimal Estimation of Dynamic Systems , 2004 .

[42]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[43]  Eric D. Gustafson,et al.  Interplanetary CubeSat Navigational Challenges , 2015 .

[44]  William Gardner,et al.  Spectral Correlation of Modulated Signals: Part I - Analog Modulation , 1987, IEEE Transactions on Communications.

[45]  Jordi Puig-Suari,et al.  Global Educational Network for Satellite Operations (GENSO) , 2007 .

[46]  William A. Gardner,et al.  Spectral Correlation of Modulated Signals: Part II - Digital Modulation , 1987, IEEE Transactions on Communications.

[47]  D. Vallado Fundamentals of Astrodynamics and Applications , 1997 .

[48]  Mark Schenk,et al.  How to Set Up a CubeSat Project – Preliminary Survey Results , 2016 .

[49]  A. Milani,et al.  Orbit determination with very short arcs. I admissible regions , 2004 .

[50]  Massimiliano Pontil,et al.  Sparse coding for multitask and transfer learning , 2012, ICML.

[51]  Charles D. Norton,et al.  Spaceborne flight validation of NASA ESTO technologies , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[52]  Jonathan Baxter,et al.  A Model of Inductive Bias Learning , 2000, J. Artif. Intell. Res..

[53]  B. Quarles,et al.  The three-body problem , 2015, Reports on progress in physics. Physical Society.