Entropy-based space object data association using an adaptive gaussian sum filter

Daniel R. Giza, Puneet Singla, John L. Crassidis, Richard Linares, Paul J. Cefola, Keric Hill

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations


This paper shows an approach to improve the statistical validity of orbital estimates and uncertainties as well as a method of associating measurements with the correct resident space objects and classifying events in near realtime. The approach involves using an adaptive Gaussian mixture solution to the Fokker-Planck-Kolmogorov equation for its applicability to the resident space object tracking problem. The Fokker-Planck-Kolmogorov equation describes the time-evolution of the probability density function for nonlinear stochastic systems with Gaussian inputs, which often results in non-Gaussian outputs. The adaptive Gaussian sum filter provides a computationally efficient and accurate solution for this equation, which captures the non-Gaussian behavior associated with these nononding measurement association methods are evaluated using simulated data in realistic scenarios to determine their performance and feasibility.

Original languageEnglish (US)
Title of host publicationAIAA/AAS Astrodynamics Specialist Conference 2010
StatePublished - 2010
EventAIAA/AAS Astrodynamics Specialist Conference 2010 - Toronto, ON, Canada
Duration: Aug 2 2010Aug 5 2010

Publication series

NameAIAA/AAS Astrodynamics Specialist Conference 2010


OtherAIAA/AAS Astrodynamics Specialist Conference 2010
CityToronto, ON

Bibliographical note

Funding Information:
This work was supported by an Air Force Research Laboratory Phase I SBIR grant, FA9451-10-M-0089, under the supervision of Dr. Moriba Jah, and an Air Force Office of Scientific Research Phase I STTR grant,FA9550-10-C-0077, under the supervision of Dr. Kent Miller. The authors greatly appreciate the support.


Dive into the research topics of 'Entropy-based space object data association using an adaptive gaussian sum filter'. Together they form a unique fingerprint.

Cite this