If it evolves it needs to learn

A. E. Eiben; Emma Hart

doi:10.1145/3377929.3398151

If it evolves it needs to learn

A. E. Eiben, Emma Hart

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

42 Downloads (Pure)

Abstract

We elaborate on (future) evolutionary robot systems where morphologies and controllers of real robots are evolved in the real-world. We argue that such systems must contain a learning component where a newborn robot refines its inherited controller to align with its body, which will inevitably be different from its parents.

Original language	English
Title of host publication	GECCO '20
Subtitle of host publication	Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion
Publisher	Association for Computing Machinery, Inc
Pages	1383-1384
Number of pages	2
ISBN (Electronic)	9781450371278
DOIs	https://doi.org/10.1145/3377929.3398151
Publication status	Published - Jul 2020
Event	2020 Genetic and Evolutionary Computation Conference, GECCO 2020 - Cancun, Mexico Duration: 8 Jul 2020 → 12 Jul 2020

Conference

Conference	2020 Genetic and Evolutionary Computation Conference, GECCO 2020
Country/Territory	Mexico
City	Cancun
Period	8/07/20 → 12/07/20

Keywords

Evolutionary robotics
Lamarckian evolution
Online learning

Access to Document

10.1145/3377929.3398151

If it evolves it needs to learnFinal published version, 530 KBLicence: Article 25fa Dutch Copyright Act

Handle.net

Persistent link

Cite this

@inproceedings{589e18c7c2134b8892b37c556c60ec86,

title = "If it evolves it needs to learn",

abstract = "We elaborate on (future) evolutionary robot systems where morphologies and controllers of real robots are evolved in the real-world. We argue that such systems must contain a learning component where a newborn robot refines its inherited controller to align with its body, which will inevitably be different from its parents.",

keywords = "Evolutionary robotics, Lamarckian evolution, Online learning",

author = "Eiben, {A. E.} and Emma Hart",

year = "2020",

month = jul,

doi = "10.1145/3377929.3398151",

language = "English",

pages = "1383--1384",

booktitle = "GECCO '20",

publisher = "Association for Computing Machinery, Inc",

note = "2020 Genetic and Evolutionary Computation Conference, GECCO 2020 ; Conference date: 08-07-2020 Through 12-07-2020",

}

TY - GEN

T1 - If it evolves it needs to learn

AU - Eiben, A. E.

AU - Hart, Emma

PY - 2020/7

Y1 - 2020/7

N2 - We elaborate on (future) evolutionary robot systems where morphologies and controllers of real robots are evolved in the real-world. We argue that such systems must contain a learning component where a newborn robot refines its inherited controller to align with its body, which will inevitably be different from its parents.

AB - We elaborate on (future) evolutionary robot systems where morphologies and controllers of real robots are evolved in the real-world. We argue that such systems must contain a learning component where a newborn robot refines its inherited controller to align with its body, which will inevitably be different from its parents.

KW - Evolutionary robotics

KW - Lamarckian evolution

KW - Online learning

UR - http://www.scopus.com/inward/record.url?scp=85089748964&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85089748964&partnerID=8YFLogxK

U2 - 10.1145/3377929.3398151

DO - 10.1145/3377929.3398151

M3 - Conference contribution

AN - SCOPUS:85089748964

SP - 1383

EP - 1384

BT - GECCO '20

PB - Association for Computing Machinery, Inc

T2 - 2020 Genetic and Evolutionary Computation Conference, GECCO 2020

Y2 - 8 July 2020 through 12 July 2020

ER -

If it evolves it needs to learn

Abstract

Conference

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this