The balance between initial training and lifelong adaptation in evolving robot controllers

Standard

The balance between initial training and lifelong adaptation in evolving robot controllers. / Walker, Joanne Heather; Garrett, Simon Martin; Wilson, Myra Scott.

In: IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), Vol. 36, No. 2, 01.04.2006, p. 423-432.

Research output: Contribution to journalArticlepeer-review

Harvard

Walker, JH, Garrett, SM & Wilson, MS 2006, 'The balance between initial training and lifelong adaptation in evolving robot controllers', IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 36, no. 2, pp. 423-432. https://doi.org/10.1109/TSMCB.2005.859082

APA

Walker, J. H., Garrett, S. M., & Wilson, M. S. (2006). The balance between initial training and lifelong adaptation in evolving robot controllers. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 36(2), 423-432. https://doi.org/10.1109/TSMCB.2005.859082

Vancouver

Walker JH, Garrett SM, Wilson MS. The balance between initial training and lifelong adaptation in evolving robot controllers. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics). 2006 Apr 1;36(2):423-432. https://doi.org/10.1109/TSMCB.2005.859082

Author

Walker, Joanne Heather ; Garrett, Simon Martin ; Wilson, Myra Scott. / The balance between initial training and lifelong adaptation in evolving robot controllers. In: IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics). 2006 ; Vol. 36, No. 2. pp. 423-432.

Bibtex - Download

@article{ca79c41aebaa4b18acdf55cf5cfb70a1,
title = "The balance between initial training and lifelong adaptation in evolving robot controllers",
abstract = "A central aim of robotics research is to design robots that can perform in the real world; a real world that is often highly changeable in nature. An important challenge for researchers is therefore to produce robots that can improve their performance when the environment is stable, and adapt when the environment changes. This paper reports on experiments which show how evolutionary methods can provide lifelong adaptation for robots, and how this evolutionary process was embodied on the robot itself. A unique combination of training and lifelong adaptation are used, and this paper highlights the importance of training to this approach.",
author = "Walker, {Joanne Heather} and Garrett, {Simon Martin} and Wilson, {Myra Scott}",
note = "Wilson, Myra, Walker, J., Garrett, S., (2006) 'The balance between initial training and lifelong adaptation in evolving robot controllers', IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 36(2) pp.423-432 RAE2008",
year = "2006",
month = apr,
day = "1",
doi = "10.1109/TSMCB.2005.859082",
language = "English",
volume = "36",
pages = "423--432",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)",
issn = "1083-4419",
publisher = "IEEE Press",
number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - The balance between initial training and lifelong adaptation in evolving robot controllers

AU - Walker, Joanne Heather

AU - Garrett, Simon Martin

AU - Wilson, Myra Scott

N1 - Wilson, Myra, Walker, J., Garrett, S., (2006) 'The balance between initial training and lifelong adaptation in evolving robot controllers', IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 36(2) pp.423-432 RAE2008

PY - 2006/4/1

Y1 - 2006/4/1

N2 - A central aim of robotics research is to design robots that can perform in the real world; a real world that is often highly changeable in nature. An important challenge for researchers is therefore to produce robots that can improve their performance when the environment is stable, and adapt when the environment changes. This paper reports on experiments which show how evolutionary methods can provide lifelong adaptation for robots, and how this evolutionary process was embodied on the robot itself. A unique combination of training and lifelong adaptation are used, and this paper highlights the importance of training to this approach.

AB - A central aim of robotics research is to design robots that can perform in the real world; a real world that is often highly changeable in nature. An important challenge for researchers is therefore to produce robots that can improve their performance when the environment is stable, and adapt when the environment changes. This paper reports on experiments which show how evolutionary methods can provide lifelong adaptation for robots, and how this evolutionary process was embodied on the robot itself. A unique combination of training and lifelong adaptation are used, and this paper highlights the importance of training to this approach.

U2 - 10.1109/TSMCB.2005.859082

DO - 10.1109/TSMCB.2005.859082

M3 - Article

VL - 36

SP - 423

EP - 432

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)

SN - 1083-4419

IS - 2

ER -

View graph of relations
Citation formats