Autonomous real-time site selection for venus and titan landing using evolutionary fuzzy cognitive maps

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

Abstract

Future science-driven landing missions, conceived to collect in-situ data on regions of planetary bodies that have the highest potential to yield important scientific discoveries, will require a higher degree of autonomy. The latter includes the ability of the spacecraft to autonomously select the landing site using real-time data acquired during the descent phase. This paper presents the development of an Evolutionary Fuzzy Cognitive Map (E-FCM) model that implements an artificial intelligence system capable of selecting a landing site with the highest potential for scientific discoveries constrained by the requirement of soft landing on a region with safe terrain. The proposed E-FCM evolves its internal states and interconnections as function of the external data collected during the descent, therefore improving the decision process as more accurate information is available. The E-FCM is constructed using knowledge accumulated by experts and it is tested on scenarios that simulate the decision-making process during the descent toward the Hyndla Regio on Venus. The E-FCM is shown to quickly reach conclusions that are consistent with what a planetary expert would decide if the scientist were presented, in real-time, with the same available information. The proposed methodology is fast and efficient and may be suitable for on-board spacecraft implementation and real-time decision-making during the course of any robotic exploration of the Solar System.

Original languageEnglish (US)
Title of host publicationProceedings of the 2011 International Conference on Artificial Intelligence, ICAI 2011
Pages691-697
Number of pages7
Volume2
StatePublished - 2011
Event2011 International Conference on Artificial Intelligence, ICAI 2011 - Las Vegas, NV, United States
Duration: Jul 18 2011Jul 21 2011

Other

Other2011 International Conference on Artificial Intelligence, ICAI 2011
CountryUnited States
CityLas Vegas, NV
Period7/18/117/21/11

Fingerprint

Site selection
Landing
Spacecraft
Decision making
Solar system
Artificial intelligence
Robotics

Keywords

  • Autonomous systems
  • Fuzzy cognitive maps
  • Planetary exploration
  • Planetary landing

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Furfaro, R., Kargel, J. S., & Fink, W. (2011). Autonomous real-time site selection for venus and titan landing using evolutionary fuzzy cognitive maps. In Proceedings of the 2011 International Conference on Artificial Intelligence, ICAI 2011 (Vol. 2, pp. 691-697)

Autonomous real-time site selection for venus and titan landing using evolutionary fuzzy cognitive maps. / Furfaro, Roberto; Kargel, J. S.; Fink, Wolfgang.

Proceedings of the 2011 International Conference on Artificial Intelligence, ICAI 2011. Vol. 2 2011. p. 691-697.

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

Furfaro, R, Kargel, JS & Fink, W 2011, Autonomous real-time site selection for venus and titan landing using evolutionary fuzzy cognitive maps. in Proceedings of the 2011 International Conference on Artificial Intelligence, ICAI 2011. vol. 2, pp. 691-697, 2011 International Conference on Artificial Intelligence, ICAI 2011, Las Vegas, NV, United States, 7/18/11.
Furfaro R, Kargel JS, Fink W. Autonomous real-time site selection for venus and titan landing using evolutionary fuzzy cognitive maps. In Proceedings of the 2011 International Conference on Artificial Intelligence, ICAI 2011. Vol. 2. 2011. p. 691-697
Furfaro, Roberto ; Kargel, J. S. ; Fink, Wolfgang. / Autonomous real-time site selection for venus and titan landing using evolutionary fuzzy cognitive maps. Proceedings of the 2011 International Conference on Artificial Intelligence, ICAI 2011. Vol. 2 2011. pp. 691-697
@inproceedings{001139a4780d412fa3b9f3c6030b9e07,
title = "Autonomous real-time site selection for venus and titan landing using evolutionary fuzzy cognitive maps",
abstract = "Future science-driven landing missions, conceived to collect in-situ data on regions of planetary bodies that have the highest potential to yield important scientific discoveries, will require a higher degree of autonomy. The latter includes the ability of the spacecraft to autonomously select the landing site using real-time data acquired during the descent phase. This paper presents the development of an Evolutionary Fuzzy Cognitive Map (E-FCM) model that implements an artificial intelligence system capable of selecting a landing site with the highest potential for scientific discoveries constrained by the requirement of soft landing on a region with safe terrain. The proposed E-FCM evolves its internal states and interconnections as function of the external data collected during the descent, therefore improving the decision process as more accurate information is available. The E-FCM is constructed using knowledge accumulated by experts and it is tested on scenarios that simulate the decision-making process during the descent toward the Hyndla Regio on Venus. The E-FCM is shown to quickly reach conclusions that are consistent with what a planetary expert would decide if the scientist were presented, in real-time, with the same available information. The proposed methodology is fast and efficient and may be suitable for on-board spacecraft implementation and real-time decision-making during the course of any robotic exploration of the Solar System.",
keywords = "Autonomous systems, Fuzzy cognitive maps, Planetary exploration, Planetary landing",
author = "Roberto Furfaro and Kargel, {J. S.} and Wolfgang Fink",
year = "2011",
language = "English (US)",
isbn = "9781601321855",
volume = "2",
pages = "691--697",
booktitle = "Proceedings of the 2011 International Conference on Artificial Intelligence, ICAI 2011",

}

TY - GEN

T1 - Autonomous real-time site selection for venus and titan landing using evolutionary fuzzy cognitive maps

AU - Furfaro, Roberto

AU - Kargel, J. S.

AU - Fink, Wolfgang

PY - 2011

Y1 - 2011

N2 - Future science-driven landing missions, conceived to collect in-situ data on regions of planetary bodies that have the highest potential to yield important scientific discoveries, will require a higher degree of autonomy. The latter includes the ability of the spacecraft to autonomously select the landing site using real-time data acquired during the descent phase. This paper presents the development of an Evolutionary Fuzzy Cognitive Map (E-FCM) model that implements an artificial intelligence system capable of selecting a landing site with the highest potential for scientific discoveries constrained by the requirement of soft landing on a region with safe terrain. The proposed E-FCM evolves its internal states and interconnections as function of the external data collected during the descent, therefore improving the decision process as more accurate information is available. The E-FCM is constructed using knowledge accumulated by experts and it is tested on scenarios that simulate the decision-making process during the descent toward the Hyndla Regio on Venus. The E-FCM is shown to quickly reach conclusions that are consistent with what a planetary expert would decide if the scientist were presented, in real-time, with the same available information. The proposed methodology is fast and efficient and may be suitable for on-board spacecraft implementation and real-time decision-making during the course of any robotic exploration of the Solar System.

AB - Future science-driven landing missions, conceived to collect in-situ data on regions of planetary bodies that have the highest potential to yield important scientific discoveries, will require a higher degree of autonomy. The latter includes the ability of the spacecraft to autonomously select the landing site using real-time data acquired during the descent phase. This paper presents the development of an Evolutionary Fuzzy Cognitive Map (E-FCM) model that implements an artificial intelligence system capable of selecting a landing site with the highest potential for scientific discoveries constrained by the requirement of soft landing on a region with safe terrain. The proposed E-FCM evolves its internal states and interconnections as function of the external data collected during the descent, therefore improving the decision process as more accurate information is available. The E-FCM is constructed using knowledge accumulated by experts and it is tested on scenarios that simulate the decision-making process during the descent toward the Hyndla Regio on Venus. The E-FCM is shown to quickly reach conclusions that are consistent with what a planetary expert would decide if the scientist were presented, in real-time, with the same available information. The proposed methodology is fast and efficient and may be suitable for on-board spacecraft implementation and real-time decision-making during the course of any robotic exploration of the Solar System.

KW - Autonomous systems

KW - Fuzzy cognitive maps

KW - Planetary exploration

KW - Planetary landing

UR - http://www.scopus.com/inward/record.url?scp=84866060106&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866060106&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781601321855

VL - 2

SP - 691

EP - 697

BT - Proceedings of the 2011 International Conference on Artificial Intelligence, ICAI 2011

ER -