Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance

Jules Simo, Roberto Furfaro, Joel Mueting

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

85 Downloads (Pure)

Abstract

Computational intelligence techniques have been used in a wide range of application
areas. This paper proposes a new learning algorithm that dynamically shapes the landing trajectories, based on potential function methods, in order to provide
computationally efficient on-board guidance and control. Extreme Learning Machine
(ELM) devises a Single Layer Forward Network (SLFN) to learn the relationship between the current spacecraft position and the optimal velocity field. The SLFN design is tested and validated on a set of data comprising data points belonging
to the training set on which the network has not been trained. Furthermore, the proposed efficient algorithm is tested in typical simulation scenarios which include
a set of Monte Carlo simulation to evaluate the guidance performances.
Original languageEnglish
Title of host publicationAdvances in the Astronautical Sciences
Place of PublicationUSA
Pages2233-2248
Number of pages16
Volume155
Publication statusPublished - Sep 2015
Event25th AAS/AIAA Space Flight Mechanics Meeting - Willliamsburg, VA, United States
Duration: 11 Jan 201515 Jan 2015

Publication series

NameAdvances in the Astronautical Sciences
PublisherUnivelt Inc.
Volume155
ISSN (Print)0065-3438

Conference

Conference25th AAS/AIAA Space Flight Mechanics Meeting
CountryUnited States
CityWillliamsburg, VA
Period11/01/1515/01/15

Fingerprint

Landing
Learning algorithms
Artificial intelligence
Spacecraft
Learning systems
Trajectories
Neural networks
Monte Carlo simulation

Keywords

  • extreme learning maching (ELM)
  • single layer forward network (SLFN)
  • learning algorithms
  • landing trajectories
  • guidance control systems

Cite this

Simo, J., Furfaro, R., & Mueting, J. (2015). Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance. In Advances in the Astronautical Sciences (Vol. 155, pp. 2233-2248). (Advances in the Astronautical Sciences; Vol. 155). USA.
Simo, Jules ; Furfaro, Roberto ; Mueting, Joel. / Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance. Advances in the Astronautical Sciences. Vol. 155 USA, 2015. pp. 2233-2248 (Advances in the Astronautical Sciences).
@inbook{b3cd2daeb73049e78208d65243ac04a2,
title = "Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance",
abstract = "Computational intelligence techniques have been used in a wide range of applicationareas. This paper proposes a new learning algorithm that dynamically shapes the landing trajectories, based on potential function methods, in order to providecomputationally efficient on-board guidance and control. Extreme Learning Machine(ELM) devises a Single Layer Forward Network (SLFN) to learn the relationship between the current spacecraft position and the optimal velocity field. The SLFN design is tested and validated on a set of data comprising data points belongingto the training set on which the network has not been trained. Furthermore, the proposed efficient algorithm is tested in typical simulation scenarios which includea set of Monte Carlo simulation to evaluate the guidance performances.",
keywords = "extreme learning maching (ELM), single layer forward network (SLFN), learning algorithms, landing trajectories, guidance control systems",
author = "Jules Simo and Roberto Furfaro and Joel Mueting",
year = "2015",
month = "9",
language = "English",
volume = "155",
series = "Advances in the Astronautical Sciences",
publisher = "Univelt Inc.",
pages = "2233--2248",
booktitle = "Advances in the Astronautical Sciences",

}

Simo, J, Furfaro, R & Mueting, J 2015, Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance. in Advances in the Astronautical Sciences. vol. 155, Advances in the Astronautical Sciences, vol. 155, USA, pp. 2233-2248, 25th AAS/AIAA Space Flight Mechanics Meeting, Willliamsburg, VA, United States, 11/01/15.

Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance. / Simo, Jules; Furfaro, Roberto; Mueting, Joel.

Advances in the Astronautical Sciences. Vol. 155 USA, 2015. p. 2233-2248 (Advances in the Astronautical Sciences; Vol. 155).

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

TY - CHAP

T1 - Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance

AU - Simo, Jules

AU - Furfaro, Roberto

AU - Mueting, Joel

PY - 2015/9

Y1 - 2015/9

N2 - Computational intelligence techniques have been used in a wide range of applicationareas. This paper proposes a new learning algorithm that dynamically shapes the landing trajectories, based on potential function methods, in order to providecomputationally efficient on-board guidance and control. Extreme Learning Machine(ELM) devises a Single Layer Forward Network (SLFN) to learn the relationship between the current spacecraft position and the optimal velocity field. The SLFN design is tested and validated on a set of data comprising data points belongingto the training set on which the network has not been trained. Furthermore, the proposed efficient algorithm is tested in typical simulation scenarios which includea set of Monte Carlo simulation to evaluate the guidance performances.

AB - Computational intelligence techniques have been used in a wide range of applicationareas. This paper proposes a new learning algorithm that dynamically shapes the landing trajectories, based on potential function methods, in order to providecomputationally efficient on-board guidance and control. Extreme Learning Machine(ELM) devises a Single Layer Forward Network (SLFN) to learn the relationship between the current spacecraft position and the optimal velocity field. The SLFN design is tested and validated on a set of data comprising data points belongingto the training set on which the network has not been trained. Furthermore, the proposed efficient algorithm is tested in typical simulation scenarios which includea set of Monte Carlo simulation to evaluate the guidance performances.

KW - extreme learning maching (ELM)

KW - single layer forward network (SLFN)

KW - learning algorithms

KW - landing trajectories

KW - guidance control systems

M3 - Chapter (peer-reviewed)

VL - 155

T3 - Advances in the Astronautical Sciences

SP - 2233

EP - 2248

BT - Advances in the Astronautical Sciences

CY - USA

ER -

Simo J, Furfaro R, Mueting J. Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance. In Advances in the Astronautical Sciences. Vol. 155. USA. 2015. p. 2233-2248. (Advances in the Astronautical Sciences).