Multirobot lunar excavation and ISRU using artificial-neural-tissue controllers

Jekanthan Thangavelautham, Alexander Smith, Nader Abu El Samid, Alexander Ho, Dale Boucher, Jim Richard, Gabriele M T D'Eleuterio

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

1 Citation (Scopus)

Abstract

Automation of site preparation and resource utilization on the Moon with teams of autonomous robots holds considerable promise for establishing a lunar base. Such multirobot autonomous systems would require limited human support infrastructure, complement necessary manned operations and reduce overall mission risk. We present an Artificial Neural Tissue (ANT) architecture as a control system for autonomous multirobot excavation tasks. An ANT approach requires much less human supervision and pre-programmed human expertise than previous techniques. Only a single global fitness function and a set of allowable basis behaviors need be specified. An evolutionary (Darwinian) selection process is used to 'breed' controllers for the task at hand in simulation and the fittest controllers are transferred onto hardware for further validation and testing. ANT facilitates 'machine creativity', with the emergence of novel functionality through a process of self-organized task decomposition of mission goals. ANT based controllers are shown to extdbit self-organization, employ stigmergy (communication mediated through the environment) and make use of templates (unlabeled environmental cues). With lunar in-situ resource utilization (ISRU) efforts in mind, ANT controllers have been tested on a multirobot excavation task in which teams of robots with no explicit supervision can successfully avoid obstacles, interpret excavation blueprints, perform layered digging, avoid burying or trapping other robots and clear/maintain digging routes.

Original languageEnglish (US)
Title of host publicationAIP Conference Proceedings
Pages229-236
Number of pages8
Volume969
DOIs
StatePublished - 2008
Externally publishedYes
EventSpace Technology and Applications International Forum: Enabling Space Exploration, STAIF 2008 - Albuquerque, NM, United States
Duration: Feb 10 2008Feb 14 2008

Other

OtherSpace Technology and Applications International Forum: Enabling Space Exploration, STAIF 2008
CountryUnited States
CityAlbuquerque, NM
Period2/10/082/14/08

Fingerprint

in situ resource utilization
excavation
controllers
robots
blueprints
fitness
cues
moon
automation
complement
resources
hardware
templates
communication
trapping
routes
decomposition
preparation
simulation

Keywords

  • Collective robotics
  • Developmental systems
  • Evolutionary algorithms
  • ISRU
  • Neural networks

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

Thangavelautham, J., Smith, A., El Samid, N. A., Ho, A., Boucher, D., Richard, J., & D'Eleuterio, G. M. T. (2008). Multirobot lunar excavation and ISRU using artificial-neural-tissue controllers. In AIP Conference Proceedings (Vol. 969, pp. 229-236) https://doi.org/10.1063/1.2844972

Multirobot lunar excavation and ISRU using artificial-neural-tissue controllers. / Thangavelautham, Jekanthan; Smith, Alexander; El Samid, Nader Abu; Ho, Alexander; Boucher, Dale; Richard, Jim; D'Eleuterio, Gabriele M T.

AIP Conference Proceedings. Vol. 969 2008. p. 229-236.

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

Thangavelautham, J, Smith, A, El Samid, NA, Ho, A, Boucher, D, Richard, J & D'Eleuterio, GMT 2008, Multirobot lunar excavation and ISRU using artificial-neural-tissue controllers. in AIP Conference Proceedings. vol. 969, pp. 229-236, Space Technology and Applications International Forum: Enabling Space Exploration, STAIF 2008, Albuquerque, NM, United States, 2/10/08. https://doi.org/10.1063/1.2844972
Thangavelautham J, Smith A, El Samid NA, Ho A, Boucher D, Richard J et al. Multirobot lunar excavation and ISRU using artificial-neural-tissue controllers. In AIP Conference Proceedings. Vol. 969. 2008. p. 229-236 https://doi.org/10.1063/1.2844972
Thangavelautham, Jekanthan ; Smith, Alexander ; El Samid, Nader Abu ; Ho, Alexander ; Boucher, Dale ; Richard, Jim ; D'Eleuterio, Gabriele M T. / Multirobot lunar excavation and ISRU using artificial-neural-tissue controllers. AIP Conference Proceedings. Vol. 969 2008. pp. 229-236
@inproceedings{17bcb0014c79420ca1a2351622586f6d,
title = "Multirobot lunar excavation and ISRU using artificial-neural-tissue controllers",
abstract = "Automation of site preparation and resource utilization on the Moon with teams of autonomous robots holds considerable promise for establishing a lunar base. Such multirobot autonomous systems would require limited human support infrastructure, complement necessary manned operations and reduce overall mission risk. We present an Artificial Neural Tissue (ANT) architecture as a control system for autonomous multirobot excavation tasks. An ANT approach requires much less human supervision and pre-programmed human expertise than previous techniques. Only a single global fitness function and a set of allowable basis behaviors need be specified. An evolutionary (Darwinian) selection process is used to 'breed' controllers for the task at hand in simulation and the fittest controllers are transferred onto hardware for further validation and testing. ANT facilitates 'machine creativity', with the emergence of novel functionality through a process of self-organized task decomposition of mission goals. ANT based controllers are shown to extdbit self-organization, employ stigmergy (communication mediated through the environment) and make use of templates (unlabeled environmental cues). With lunar in-situ resource utilization (ISRU) efforts in mind, ANT controllers have been tested on a multirobot excavation task in which teams of robots with no explicit supervision can successfully avoid obstacles, interpret excavation blueprints, perform layered digging, avoid burying or trapping other robots and clear/maintain digging routes.",
keywords = "Collective robotics, Developmental systems, Evolutionary algorithms, ISRU, Neural networks",
author = "Jekanthan Thangavelautham and Alexander Smith and {El Samid}, {Nader Abu} and Alexander Ho and Dale Boucher and Jim Richard and D'Eleuterio, {Gabriele M T}",
year = "2008",
doi = "10.1063/1.2844972",
language = "English (US)",
isbn = "9780735404861",
volume = "969",
pages = "229--236",
booktitle = "AIP Conference Proceedings",

}

TY - GEN

T1 - Multirobot lunar excavation and ISRU using artificial-neural-tissue controllers

AU - Thangavelautham, Jekanthan

AU - Smith, Alexander

AU - El Samid, Nader Abu

AU - Ho, Alexander

AU - Boucher, Dale

AU - Richard, Jim

AU - D'Eleuterio, Gabriele M T

PY - 2008

Y1 - 2008

N2 - Automation of site preparation and resource utilization on the Moon with teams of autonomous robots holds considerable promise for establishing a lunar base. Such multirobot autonomous systems would require limited human support infrastructure, complement necessary manned operations and reduce overall mission risk. We present an Artificial Neural Tissue (ANT) architecture as a control system for autonomous multirobot excavation tasks. An ANT approach requires much less human supervision and pre-programmed human expertise than previous techniques. Only a single global fitness function and a set of allowable basis behaviors need be specified. An evolutionary (Darwinian) selection process is used to 'breed' controllers for the task at hand in simulation and the fittest controllers are transferred onto hardware for further validation and testing. ANT facilitates 'machine creativity', with the emergence of novel functionality through a process of self-organized task decomposition of mission goals. ANT based controllers are shown to extdbit self-organization, employ stigmergy (communication mediated through the environment) and make use of templates (unlabeled environmental cues). With lunar in-situ resource utilization (ISRU) efforts in mind, ANT controllers have been tested on a multirobot excavation task in which teams of robots with no explicit supervision can successfully avoid obstacles, interpret excavation blueprints, perform layered digging, avoid burying or trapping other robots and clear/maintain digging routes.

AB - Automation of site preparation and resource utilization on the Moon with teams of autonomous robots holds considerable promise for establishing a lunar base. Such multirobot autonomous systems would require limited human support infrastructure, complement necessary manned operations and reduce overall mission risk. We present an Artificial Neural Tissue (ANT) architecture as a control system for autonomous multirobot excavation tasks. An ANT approach requires much less human supervision and pre-programmed human expertise than previous techniques. Only a single global fitness function and a set of allowable basis behaviors need be specified. An evolutionary (Darwinian) selection process is used to 'breed' controllers for the task at hand in simulation and the fittest controllers are transferred onto hardware for further validation and testing. ANT facilitates 'machine creativity', with the emergence of novel functionality through a process of self-organized task decomposition of mission goals. ANT based controllers are shown to extdbit self-organization, employ stigmergy (communication mediated through the environment) and make use of templates (unlabeled environmental cues). With lunar in-situ resource utilization (ISRU) efforts in mind, ANT controllers have been tested on a multirobot excavation task in which teams of robots with no explicit supervision can successfully avoid obstacles, interpret excavation blueprints, perform layered digging, avoid burying or trapping other robots and clear/maintain digging routes.

KW - Collective robotics

KW - Developmental systems

KW - Evolutionary algorithms

KW - ISRU

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=72349099896&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72349099896&partnerID=8YFLogxK

U2 - 10.1063/1.2844972

DO - 10.1063/1.2844972

M3 - Conference contribution

AN - SCOPUS:72349099896

SN - 9780735404861

VL - 969

SP - 229

EP - 236

BT - AIP Conference Proceedings

ER -