ITU

An Experiment in Morphological Development for Learning ANN Based Controllers

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

Standard

An Experiment in Morphological Development for Learning ANN Based Controllers. / Naya, Martin; Faina, Andres; Duro, Richard.

Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020.

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

Harvard

Naya, M, Faina, A & Duro, R 2020, An Experiment in Morphological Development for Learning ANN Based Controllers. in Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, International Joint Conference on Neural Networks, United Kingdom, 19/07/2020. https://doi.org/10.1109/IJCNN48605.2020.9206749

APA

Naya, M., Faina, A., & Duro, R. (2020). An Experiment in Morphological Development for Learning ANN Based Controllers. In Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN) IEEE. https://doi.org/10.1109/IJCNN48605.2020.9206749

Vancouver

Naya M, Faina A, Duro R. An Experiment in Morphological Development for Learning ANN Based Controllers. In Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN). IEEE. 2020 https://doi.org/10.1109/IJCNN48605.2020.9206749

Author

Naya, Martin ; Faina, Andres ; Duro, Richard. / An Experiment in Morphological Development for Learning ANN Based Controllers. Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020.

Bibtex

@inproceedings{15dd0b1171b445cc909da672ffcaf54f,
title = "An Experiment in Morphological Development for Learning ANN Based Controllers",
abstract = "Morphological development is part of the way any human or animal learns. The learning processes starts with the morphology at birth and progresses through changing morphologies until adulthood is reached. Biologically, this seems to facilitate learning and make it more robust. However, when this approach is transferred to robotic systems, the results found in the literature are inconsistent: morphological development does not provide a learning advantage in every case. In fact, it can lead to poorer results than when learning with a fixed morphology. In this paper we analyze some of the issues involved by means of a simple, but very informative experiment in quadruped walking. From the results obtained an initial series of insights on when and under what conditions to apply morphological development for learning are presented.",
author = "Martin Naya and Andres Faina and Richard Duro",
year = "2020",
doi = "10.1109/IJCNN48605.2020.9206749",
language = "English",
booktitle = "Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE",
address = "United States",
note = "International Joint Conference on Neural Networks, IJCNN ; Conference date: 19-07-2020 Through 24-07-2020",

}

RIS

TY - GEN

T1 - An Experiment in Morphological Development for Learning ANN Based Controllers

AU - Naya, Martin

AU - Faina, Andres

AU - Duro, Richard

PY - 2020

Y1 - 2020

N2 - Morphological development is part of the way any human or animal learns. The learning processes starts with the morphology at birth and progresses through changing morphologies until adulthood is reached. Biologically, this seems to facilitate learning and make it more robust. However, when this approach is transferred to robotic systems, the results found in the literature are inconsistent: morphological development does not provide a learning advantage in every case. In fact, it can lead to poorer results than when learning with a fixed morphology. In this paper we analyze some of the issues involved by means of a simple, but very informative experiment in quadruped walking. From the results obtained an initial series of insights on when and under what conditions to apply morphological development for learning are presented.

AB - Morphological development is part of the way any human or animal learns. The learning processes starts with the morphology at birth and progresses through changing morphologies until adulthood is reached. Biologically, this seems to facilitate learning and make it more robust. However, when this approach is transferred to robotic systems, the results found in the literature are inconsistent: morphological development does not provide a learning advantage in every case. In fact, it can lead to poorer results than when learning with a fixed morphology. In this paper we analyze some of the issues involved by means of a simple, but very informative experiment in quadruped walking. From the results obtained an initial series of insights on when and under what conditions to apply morphological development for learning are presented.

U2 - 10.1109/IJCNN48605.2020.9206749

DO - 10.1109/IJCNN48605.2020.9206749

M3 - Article in proceedings

BT - Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

T2 - International Joint Conference on Neural Networks

Y2 - 19 July 2020 through 24 July 2020

ER -

ID: 85233520