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

Jules Simo; Roberto Furfaro; Joel Mueting

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

Jules Simo, Roberto Furfaro, Joel Mueting

Mechanical And Aerospace Engineering

Research output: Contribution to conference › Paper

74 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 language	English
Pages	AAS 15-356
Number of pages	19
Publication status	Published - 11 Jan 2015
Event	25th AAS/AIAA Space Flight Mechanics Meeting - Willliamsburg, VA, United States Duration: 11 Jan 2015 → 15 Jan 2015

Conference

Conference	25th AAS/AIAA Space Flight Mechanics Meeting
Country	United States
City	Willliamsburg, VA
Period	11/01/15 → 15/01/15

Keywords

performance evaluation
artificial neural network
algorithm design and analysis
guidance control systems
ELMS

Access to Document

Simo-etal-Spaceflight-Mechs-Mtg-2015-Performance-evaluation-of-shaping-algorithm-for-planetary-pinpoint-guidanceAccepted author manuscript, 1.31 MB

http://space-flight.org/docs/2015_winter/2015_winter.html

Fingerprint Dive into the research topics of 'Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance'. Together they form a unique fingerprint.

Cite this

Simo, J., Furfaro, R., & Mueting, J. (2015). Performance evaluation of artificial neural network-based shaping algorithm for planetary pinpoint guidance. AAS 15-356. Paper presented at 25th AAS/AIAA Space Flight Mechanics Meeting, Willliamsburg, VA, United States.

@conference{8e12d929071c4f41bc1408dc9e98cc3e,

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 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",

keywords = "performance evaluation, artificial neural network , algorithm design and analysis, guidance control systems, ELMS",

author = "Jules Simo and Roberto Furfaro and Joel Mueting",

year = "2015",

month = jan,

day = "11",

language = "English",

pages = "AAS 15--356",

note = "25th AAS/AIAA Space Flight Mechanics Meeting ; Conference date: 11-01-2015 Through 15-01-2015",

}

TY - CONF

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

AU - Simo, Jules

AU - Furfaro, Roberto

AU - Mueting, Joel

PY - 2015/1/11

Y1 - 2015/1/11

N2 - 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

AB - 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

KW - performance evaluation

KW - artificial neural network

KW - algorithm design and analysis

KW - guidance control systems

KW - ELMS

UR - http://space-flight.org/docs/2015_winter/2015_winter.html

M3 - Paper

SP - AAS 15-356

T2 - 25th AAS/AIAA Space Flight Mechanics Meeting

Y2 - 11 January 2015 through 15 January 2015

ER -