Modelling irregular small bodies gravity field via extreme learning machines

Roberto Furfaro, Richard Linares, Vishnu Reddy, Jules Simo, Lucille Le Corre

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

7 Scopus citations


Close proximity operations around small bodies are extremely challenging due to their uncertain dynamical environment. Autonomous guidance and navigation around small bodies require fast and accurate modeling of the gravitational field for potential on-board computation. In this paper, we investigate a model-based, data-driven approach to compute and predict the gravitational acceleration around irregular small bodies. More specifically, we employ Extreme Learning Machine (ELM) theories to design, train and validate Single-Layer Forward Networks (SLFN) capable of learning the relationship between the spacecraft position and the gravitational acceleration. ELMs-base neural networks are trained without iterative tuning therefore dramatically reducing the training time. Analysis of performance in constant density models for 433 Eros and 25143 Itokawa show that ELM-based SLFN are able learn the desired functional relationship both globally and in localized areas near the surface. The latter results in a robust neural algorithm for on-board, real-time calculation of the gravity field needed for close-proximity operations near the asteroid surface.

Original languageEnglish (US)
Title of host publicationSpaceflight Mechanics 2017
EditorsJon A. Sims, Frederick A. Leve, Jay W. McMahon, Yanping Guo
PublisherUnivelt Inc.
Number of pages16
ISBN (Print)9780877036371
StatePublished - 2017
Event27th AAS/AIAA Space Flight Mechanics Meeting, 2017 - San Antonio, United States
Duration: Feb 5 2017Feb 9 2017

Publication series

NameAdvances in the Astronautical Sciences
ISSN (Print)0065-3438


Other27th AAS/AIAA Space Flight Mechanics Meeting, 2017
Country/TerritoryUnited States
CitySan Antonio


Dive into the research topics of 'Modelling irregular small bodies gravity field via extreme learning machines'. Together they form a unique fingerprint.

Cite this