Evolving decision-making functions in an autonomous robotic exploration strategy using grammatical evolution

Mohd Faisal Ibrahim, Bradley James Alexander

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

3 Citations (Scopus)

Abstract

Customising navigational control for autonomous robotic mapping platforms is still a challenging task. Control software must simultaneously maximise the area explored whilst maintaining safety and working within the constraints of the platform. Scoring functions to assess navigational options are typically written by hand and manually refined. As navigational tasks become more complex this manual approach is unlikely to yield the best results. In this paper we explore the automatic derivation of a scoring function for a ground based exploration platform. We show that it is possible to derive the entire structure of a scoring function and that allowing structure to evolve yields significant performance advantages over the evolution of embedded constants alone.

Original languageEnglish
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Pages4340-4346
Number of pages7
DOIs
Publication statusPublished - 2013
Event2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013 - Tokyo
Duration: 3 Nov 20138 Nov 2013

Other

Other2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013
CityTokyo
Period3/11/138/11/13

Fingerprint

Robotics
Decision making

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Ibrahim, M. F., & Alexander, B. J. (2013). Evolving decision-making functions in an autonomous robotic exploration strategy using grammatical evolution. In IEEE International Conference on Intelligent Robots and Systems (pp. 4340-4346). [6696979] https://doi.org/10.1109/IROS.2013.6696979

Evolving decision-making functions in an autonomous robotic exploration strategy using grammatical evolution. / Ibrahim, Mohd Faisal; Alexander, Bradley James.

IEEE International Conference on Intelligent Robots and Systems. 2013. p. 4340-4346 6696979.

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

Ibrahim, MF & Alexander, BJ 2013, Evolving decision-making functions in an autonomous robotic exploration strategy using grammatical evolution. in IEEE International Conference on Intelligent Robots and Systems., 6696979, pp. 4340-4346, 2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013, Tokyo, 3/11/13. https://doi.org/10.1109/IROS.2013.6696979
Ibrahim MF, Alexander BJ. Evolving decision-making functions in an autonomous robotic exploration strategy using grammatical evolution. In IEEE International Conference on Intelligent Robots and Systems. 2013. p. 4340-4346. 6696979 https://doi.org/10.1109/IROS.2013.6696979
Ibrahim, Mohd Faisal ; Alexander, Bradley James. / Evolving decision-making functions in an autonomous robotic exploration strategy using grammatical evolution. IEEE International Conference on Intelligent Robots and Systems. 2013. pp. 4340-4346
@inproceedings{5413f38c4cbe4efba645c331d5f264cd,
title = "Evolving decision-making functions in an autonomous robotic exploration strategy using grammatical evolution",
abstract = "Customising navigational control for autonomous robotic mapping platforms is still a challenging task. Control software must simultaneously maximise the area explored whilst maintaining safety and working within the constraints of the platform. Scoring functions to assess navigational options are typically written by hand and manually refined. As navigational tasks become more complex this manual approach is unlikely to yield the best results. In this paper we explore the automatic derivation of a scoring function for a ground based exploration platform. We show that it is possible to derive the entire structure of a scoring function and that allowing structure to evolve yields significant performance advantages over the evolution of embedded constants alone.",
author = "Ibrahim, {Mohd Faisal} and Alexander, {Bradley James}",
year = "2013",
doi = "10.1109/IROS.2013.6696979",
language = "English",
isbn = "9781467363587",
pages = "4340--4346",
booktitle = "IEEE International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - Evolving decision-making functions in an autonomous robotic exploration strategy using grammatical evolution

AU - Ibrahim, Mohd Faisal

AU - Alexander, Bradley James

PY - 2013

Y1 - 2013

N2 - Customising navigational control for autonomous robotic mapping platforms is still a challenging task. Control software must simultaneously maximise the area explored whilst maintaining safety and working within the constraints of the platform. Scoring functions to assess navigational options are typically written by hand and manually refined. As navigational tasks become more complex this manual approach is unlikely to yield the best results. In this paper we explore the automatic derivation of a scoring function for a ground based exploration platform. We show that it is possible to derive the entire structure of a scoring function and that allowing structure to evolve yields significant performance advantages over the evolution of embedded constants alone.

AB - Customising navigational control for autonomous robotic mapping platforms is still a challenging task. Control software must simultaneously maximise the area explored whilst maintaining safety and working within the constraints of the platform. Scoring functions to assess navigational options are typically written by hand and manually refined. As navigational tasks become more complex this manual approach is unlikely to yield the best results. In this paper we explore the automatic derivation of a scoring function for a ground based exploration platform. We show that it is possible to derive the entire structure of a scoring function and that allowing structure to evolve yields significant performance advantages over the evolution of embedded constants alone.

UR - http://www.scopus.com/inward/record.url?scp=84893722618&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893722618&partnerID=8YFLogxK

U2 - 10.1109/IROS.2013.6696979

DO - 10.1109/IROS.2013.6696979

M3 - Conference contribution

AN - SCOPUS:84893722618

SN - 9781467363587

SP - 4340

EP - 4346

BT - IEEE International Conference on Intelligent Robots and Systems

ER -