Comparing encodings for performance and phenotypic exploration in evolving modular robots

Frank Veenstra; Emma Hart; Edgar Buchanan; Wei Li; Matteo De Carlo; Agoston E. Eiben

doi:10.1145/3319619.3322054

Comparing encodings for performance and phenotypic exploration in evolving modular robots

Frank Veenstra, Emma Hart, Edgar Buchanan, Wei Li, Matteo De Carlo, Agoston E. Eiben

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

64 Downloads (Pure)

Abstract

To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings-a compositional pattern producing network (CPPN) and a Lindenmayer System (L-System). The evolutionary progression and final performance of the direct encoding and the L-System was significantly better than the CPPN. The generative encodings converge quicker than the direct encoding in terms of morphological and controller diversity.

Original language	English
Title of host publication	GECCO '19
Subtitle of host publication	Proceedings of the Genetic and Evolutionary Computation Conference Companion
Publisher	Association for Computing Machinery, Inc
Pages	127-128
Number of pages	2
ISBN (Electronic)	9781450367486
DOIs	https://doi.org/10.1145/3319619.3322054
Publication status	Published - Jul 2019
Event	2019 Genetic and Evolutionary Computation Conference, GECCO 2019 - Prague, Czech Republic Duration: 13 Jul 2019 → 17 Jul 2019

Conference

Conference	2019 Genetic and Evolutionary Computation Conference, GECCO 2019
Country/Territory	Czech Republic
City	Prague
Period	13/07/19 → 17/07/19

Funding

This project has received funding from "Autonomous Robot Evolution: Cradle To Grave", EPSRC reference: EP/R035733/1.

Funders	Funder number
Engineering and Physical Sciences Research Council	EP/R035733/1
Engineering and Physical Sciences Research Council

Keywords

Encodings
Evolutionary Robotics

Access to Document

10.1145/3319619.3322054

Comparing encodings for performance and phenotypic exploration in evolving modular robotsFinal published version, 636 KBLicence: Article 25fa Dutch Copyright Act

Persistent URL (handle)

Persistent link

Cite this

@inproceedings{ea259653bc8144a78100ee294ab9d04a,

title = "Comparing encodings for performance and phenotypic exploration in evolving modular robots",

abstract = "To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings-a compositional pattern producing network (CPPN) and a Lindenmayer System (L-System). The evolutionary progression and final performance of the direct encoding and the L-System was significantly better than the CPPN. The generative encodings converge quicker than the direct encoding in terms of morphological and controller diversity.",

keywords = "Encodings, Evolutionary Robotics",

author = "Frank Veenstra and Emma Hart and Edgar Buchanan and Wei Li and {De Carlo}, Matteo and Eiben, {Agoston E.}",

year = "2019",

month = jul,

doi = "10.1145/3319619.3322054",

language = "English",

pages = "127--128",

booktitle = "GECCO '19",

publisher = "Association for Computing Machinery, Inc",

note = "2019 Genetic and Evolutionary Computation Conference, GECCO 2019 ; Conference date: 13-07-2019 Through 17-07-2019",

}

Veenstra, F, Hart, E, Buchanan, E, Li, W, De Carlo, M & Eiben, AE 2019, Comparing encodings for performance and phenotypic exploration in evolving modular robots. in GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, pp. 127-128, 2019 Genetic and Evolutionary Computation Conference, GECCO 2019, Prague, Czech Republic, 13/07/19. https://doi.org/10.1145/3319619.3322054

Comparing encodings for performance and phenotypic exploration in evolving modular robots. / Veenstra, Frank; Hart, Emma; Buchanan, Edgar et al.
GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, 2019. p. 127-128.

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

TY - GEN

T1 - Comparing encodings for performance and phenotypic exploration in evolving modular robots

AU - Veenstra, Frank

AU - Hart, Emma

AU - Buchanan, Edgar

AU - Li, Wei

AU - De Carlo, Matteo

AU - Eiben, Agoston E.

PY - 2019/7

Y1 - 2019/7

N2 - To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings-a compositional pattern producing network (CPPN) and a Lindenmayer System (L-System). The evolutionary progression and final performance of the direct encoding and the L-System was significantly better than the CPPN. The generative encodings converge quicker than the direct encoding in terms of morphological and controller diversity.

AB - To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings-a compositional pattern producing network (CPPN) and a Lindenmayer System (L-System). The evolutionary progression and final performance of the direct encoding and the L-System was significantly better than the CPPN. The generative encodings converge quicker than the direct encoding in terms of morphological and controller diversity.

KW - Encodings

KW - Evolutionary Robotics

UR - http://www.scopus.com/inward/record.url?scp=85070649159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070649159&partnerID=8YFLogxK

U2 - 10.1145/3319619.3322054

DO - 10.1145/3319619.3322054

M3 - Conference contribution

SP - 127

EP - 128

BT - GECCO '19

PB - Association for Computing Machinery, Inc

T2 - 2019 Genetic and Evolutionary Computation Conference, GECCO 2019

Y2 - 13 July 2019 through 17 July 2019

ER -

Comparing encodings for performance and phenotypic exploration in evolving modular robots

Abstract

Conference

Funding

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this