An Approach to Representation Learning in Morphological Robot Evolution

Aart C. Stuurman; Anil Yaman; A. E. Eiben

doi:10.1109/SSCI52147.2023.10371837

An Approach to Representation Learning in Morphological Robot Evolution

Aart C. Stuurman
, Anil Yaman
, A. E. Eiben

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

67 Downloads (Pure)

Abstract

A key challenge for evolving complex physical ob-jects is to design a representation, that is, to devise suitable genotypes and a good mapping from genotypes to phenotypes (the objects to be evolved). This paper outlines a new approach to address this challenge for evolving robot morphologies and presents a proof-of-concept study to assess its feasibility. The key idea is to design genotype-phenotype mappings using variational autoencoders. This idea is implemented and tested for the evolution of modular robots for a locomotion task. The experiments show the practicability of this idea where the representation is not hand-designed, but algorithmically generated. This indicates a great future potential for the evolution of complex objects where there are no straightforward representations to use.

Original language	English
Title of host publication	2023 IEEE Symposium Series on Computational Intelligence (SSCI)
Subtitle of host publication	[Proceedings]
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1072-1077
Number of pages	6
ISBN (Electronic)	9781665430654
DOIs	https://doi.org/10.1109/SSCI52147.2023.10371837
Publication status	Published - 2024
Event	2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023 - Mexico City, Mexico Duration: 5 Dec 2023 → 8 Dec 2023

Conference

Conference	2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023
Country/Territory	Mexico
City	Mexico City
Period	5/12/23 → 8/12/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

evolutionary robotics
genotype-phenotype mapping
morphological evolution
representation

Access to Document

10.1109/SSCI52147.2023.10371837

An_Approach_to_Representation_Learning_in_Morphological_Robot_EvolutionFinal published version, 709 KBLicence: Article 25fa Dutch Copyright Act

Persistent URL (handle)

Persistent link

Cite this

@inproceedings{3b652048d33a40ddb46985bfca49e3d6,

title = "An Approach to Representation Learning in Morphological Robot Evolution",

abstract = "A key challenge for evolving complex physical ob-jects is to design a representation, that is, to devise suitable genotypes and a good mapping from genotypes to phenotypes (the objects to be evolved). This paper outlines a new approach to address this challenge for evolving robot morphologies and presents a proof-of-concept study to assess its feasibility. The key idea is to design genotype-phenotype mappings using variational autoencoders. This idea is implemented and tested for the evolution of modular robots for a locomotion task. The experiments show the practicability of this idea where the representation is not hand-designed, but algorithmically generated. This indicates a great future potential for the evolution of complex objects where there are no straightforward representations to use.",

keywords = "evolutionary robotics, genotype-phenotype mapping, morphological evolution, representation",

author = "Stuurman, \{Aart C.\} and Anil Yaman and Eiben, \{A. E.\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023 ; Conference date: 05-12-2023 Through 08-12-2023",

year = "2024",

doi = "10.1109/SSCI52147.2023.10371837",

language = "English",

pages = "1072--1077",

booktitle = "2023 IEEE Symposium Series on Computational Intelligence (SSCI)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Stuurman, AC, Yaman, A & Eiben, AE 2024, An Approach to Representation Learning in Morphological Robot Evolution. in 2023 IEEE Symposium Series on Computational Intelligence (SSCI): [Proceedings]. Institute of Electrical and Electronics Engineers Inc., pp. 1072-1077, 2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023, Mexico City, Mexico, 5/12/23. https://doi.org/10.1109/SSCI52147.2023.10371837

An Approach to Representation Learning in Morphological Robot Evolution. / Stuurman, Aart C.; Yaman, Anil ; Eiben, A. E.
2023 IEEE Symposium Series on Computational Intelligence (SSCI): [Proceedings]. Institute of Electrical and Electronics Engineers Inc., 2024. p. 1072-1077.

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - An Approach to Representation Learning in Morphological Robot Evolution

AU - Stuurman, Aart C.

AU - Yaman, Anil

AU - Eiben, A. E.

PY - 2024

Y1 - 2024

N2 - A key challenge for evolving complex physical ob-jects is to design a representation, that is, to devise suitable genotypes and a good mapping from genotypes to phenotypes (the objects to be evolved). This paper outlines a new approach to address this challenge for evolving robot morphologies and presents a proof-of-concept study to assess its feasibility. The key idea is to design genotype-phenotype mappings using variational autoencoders. This idea is implemented and tested for the evolution of modular robots for a locomotion task. The experiments show the practicability of this idea where the representation is not hand-designed, but algorithmically generated. This indicates a great future potential for the evolution of complex objects where there are no straightforward representations to use.

AB - A key challenge for evolving complex physical ob-jects is to design a representation, that is, to devise suitable genotypes and a good mapping from genotypes to phenotypes (the objects to be evolved). This paper outlines a new approach to address this challenge for evolving robot morphologies and presents a proof-of-concept study to assess its feasibility. The key idea is to design genotype-phenotype mappings using variational autoencoders. This idea is implemented and tested for the evolution of modular robots for a locomotion task. The experiments show the practicability of this idea where the representation is not hand-designed, but algorithmically generated. This indicates a great future potential for the evolution of complex objects where there are no straightforward representations to use.

KW - evolutionary robotics

KW - genotype-phenotype mapping

KW - morphological evolution

KW - representation

UR - https://www.scopus.com/pages/publications/85182942665

UR - https://www.scopus.com/pages/publications/85182942665#tab=citedBy

U2 - 10.1109/SSCI52147.2023.10371837

DO - 10.1109/SSCI52147.2023.10371837

M3 - Conference contribution

AN - SCOPUS:85182942665

SP - 1072

EP - 1077

BT - 2023 IEEE Symposium Series on Computational Intelligence (SSCI)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

Y2 - 5 December 2023 through 8 December 2023

ER -

An Approach to Representation Learning in Morphological Robot Evolution

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this