ITU

Evolving Robot Controllers for Structured Environments Through Environment Decomposition

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Standard

Evolving Robot Controllers for Structured Environments Through Environment Decomposition. / Moreno, Rodrigo; Faiña, Andres; Støy, Kasper.

Applications of Evolutionary Computation: 18th European Conference, EvoApplications 2015, Copenhagen, Denmark, April 8-10, 2015, Proceedings. Vol. 9028 Springer International Publishing, Switzerland, 2015. p. 795-806 (Lecture Notes in Computer Science).

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Harvard

Moreno, R, Faiña, A & Støy, K 2015, Evolving Robot Controllers for Structured Environments Through Environment Decomposition. in Applications of Evolutionary Computation: 18th European Conference, EvoApplications 2015, Copenhagen, Denmark, April 8-10, 2015, Proceedings. vol. 9028, Springer International Publishing, Switzerland, Lecture Notes in Computer Science, pp. 795-806, Evolutionary Computation in Robotics, Copenhagen, Denmark, 08/04/2015. <http://link.springer.com/chapter/10.1007/978-3-319-16549-3_64>

APA

Moreno, R., Faiña, A., & Støy, K. (2015). Evolving Robot Controllers for Structured Environments Through Environment Decomposition. In Applications of Evolutionary Computation: 18th European Conference, EvoApplications 2015, Copenhagen, Denmark, April 8-10, 2015, Proceedings (Vol. 9028, pp. 795-806). Springer International Publishing, Switzerland. Lecture Notes in Computer Science http://link.springer.com/chapter/10.1007/978-3-319-16549-3_64

Vancouver

Moreno R, Faiña A, Støy K. Evolving Robot Controllers for Structured Environments Through Environment Decomposition. In Applications of Evolutionary Computation: 18th European Conference, EvoApplications 2015, Copenhagen, Denmark, April 8-10, 2015, Proceedings. Vol. 9028. Springer International Publishing, Switzerland. 2015. p. 795-806. (Lecture Notes in Computer Science).

Author

Moreno, Rodrigo ; Faiña, Andres ; Støy, Kasper. / Evolving Robot Controllers for Structured Environments Through Environment Decomposition. Applications of Evolutionary Computation: 18th European Conference, EvoApplications 2015, Copenhagen, Denmark, April 8-10, 2015, Proceedings. Vol. 9028 Springer International Publishing, Switzerland, 2015. pp. 795-806 (Lecture Notes in Computer Science).

Bibtex

@inproceedings{3ef876ab33f248319df736273ad39522,
title = "Evolving Robot Controllers for Structured Environments Through Environment Decomposition",
abstract = "In this paper we aim to develop a controller that allows a robot to traverse an structured environment. The approach we use is to decompose the environment into simple sub-environments that we use as basis for evolving the controller. Specifically, we decompose a narrow corridor environment into four different sub-environments and evolve controllers that generalize to traverse two larger environments composed of the sub-environments. We also study two strategies for presenting the sub-environments to the evolutionary algorithm: all sub-environments at the same time and in sequence. Results show that by using a sequence the evolutionary algorithm can find a controller that performs well in all sub-environments more consistently than when presenting all sub-environments together. We conclude that environment decomposition is an useful approach for evolving controllers for structured environments and that the order in which the decomposed sub-environments are presented in sequence impacts the performance of the evolutionary algorithm.",
keywords = "Evolutionary robotics, Environment decomposition, Sequential evolution",
author = "Rodrigo Moreno and Andres Fai{\~n}a and Kasper St{\o}y",
year = "2015",
language = "English",
isbn = "978-3-319-16548-6",
volume = "9028",
series = "Lecture Notes in Computer Science",
publisher = "Springer International Publishing, Switzerland",
pages = "795--806",
booktitle = "Applications of Evolutionary Computation",
note = "Evolutionary Computation in Robotics, EvoROBOT 2015 ; Conference date: 08-04-2015 Through 10-04-2015",
url = "http://www.evostar.org/2015/cfp_evorobot.php",

}

RIS

TY - GEN

T1 - Evolving Robot Controllers for Structured Environments Through Environment Decomposition

AU - Moreno, Rodrigo

AU - Faiña, Andres

AU - Støy, Kasper

PY - 2015

Y1 - 2015

N2 - In this paper we aim to develop a controller that allows a robot to traverse an structured environment. The approach we use is to decompose the environment into simple sub-environments that we use as basis for evolving the controller. Specifically, we decompose a narrow corridor environment into four different sub-environments and evolve controllers that generalize to traverse two larger environments composed of the sub-environments. We also study two strategies for presenting the sub-environments to the evolutionary algorithm: all sub-environments at the same time and in sequence. Results show that by using a sequence the evolutionary algorithm can find a controller that performs well in all sub-environments more consistently than when presenting all sub-environments together. We conclude that environment decomposition is an useful approach for evolving controllers for structured environments and that the order in which the decomposed sub-environments are presented in sequence impacts the performance of the evolutionary algorithm.

AB - In this paper we aim to develop a controller that allows a robot to traverse an structured environment. The approach we use is to decompose the environment into simple sub-environments that we use as basis for evolving the controller. Specifically, we decompose a narrow corridor environment into four different sub-environments and evolve controllers that generalize to traverse two larger environments composed of the sub-environments. We also study two strategies for presenting the sub-environments to the evolutionary algorithm: all sub-environments at the same time and in sequence. Results show that by using a sequence the evolutionary algorithm can find a controller that performs well in all sub-environments more consistently than when presenting all sub-environments together. We conclude that environment decomposition is an useful approach for evolving controllers for structured environments and that the order in which the decomposed sub-environments are presented in sequence impacts the performance of the evolutionary algorithm.

KW - Evolutionary robotics

KW - Environment decomposition

KW - Sequential evolution

M3 - Article in proceedings

SN - 978-3-319-16548-6

VL - 9028

T3 - Lecture Notes in Computer Science

SP - 795

EP - 806

BT - Applications of Evolutionary Computation

PB - Springer International Publishing, Switzerland

T2 - Evolutionary Computation in Robotics

Y2 - 8 April 2015 through 10 April 2015

ER -

ID: 80288902