Benefits of Lamarckian Evolution for Morphologically Evolving Robots

Milan Jelisavcic, Rafael Kiesel, Kyrre Glette, Evert Haasdijk, A.E. Eiben

Research output: Contribution to ConferencePosterOther research output

Abstract

Implementing lifetime learning by means of on-line evolution, we establish an indirect encoding scheme that combines Compositional Pattern Producing Networks (CPPNs) and Central Pattern Generators (CPGs) as a relevant learner and controller for open-loop gait controllers in modular robots which have evolving morphologies. Experimental validation on the morphologically evolved robots shows that a Lamarckian setup with CPPN-CPG provides substantial benefits compared to controllers learned from scratch.
Original languageEnglish
Number of pages2
DOIs
Publication statusAccepted/In press - Jul 2017
EventThe Genetic and Evolutionary Computation Conference - Germany, Berlin, Germany
Duration: 15 Jul 201719 Jul 2017
Conference number: 18
http://gecco-2017.sigevo.org/index.html/HomePage

Conference

ConferenceThe Genetic and Evolutionary Computation Conference
Abbreviated titleGECCO 2017
CountryGermany
CityBerlin
Period15/07/1719/07/17
Internet address

Fingerprint

Robots
Controllers
Modular robots

Keywords

  • Evolutionary robotics
  • On-line evolution
  • Indirect encoding
  • Lamarckian evolution
  • Gait learning

Cite this

Jelisavcic, M., Kiesel, R., Glette, K., Haasdijk, E., & Eiben, A. E. (Accepted/In press). Benefits of Lamarckian Evolution for Morphologically Evolving Robots. Poster session presented at The Genetic and Evolutionary Computation Conference, Berlin, Germany. https://doi.org/10.1145/3067695.3076046
Jelisavcic, Milan ; Kiesel, Rafael ; Glette, Kyrre ; Haasdijk, Evert ; Eiben, A.E. / Benefits of Lamarckian Evolution for Morphologically Evolving Robots. Poster session presented at The Genetic and Evolutionary Computation Conference, Berlin, Germany.2 p.
@conference{9ef2054a26de474a9eefd4903b808383,
title = "Benefits of Lamarckian Evolution for Morphologically Evolving Robots",
abstract = "Implementing lifetime learning by means of on-line evolution, we establish an indirect encoding scheme that combines Compositional Pattern Producing Networks (CPPNs) and Central Pattern Generators (CPGs) as a relevant learner and controller for open-loop gait controllers in modular robots which have evolving morphologies. Experimental validation on the morphologically evolved robots shows that a Lamarckian setup with CPPN-CPG provides substantial benefits compared to controllers learned from scratch.",
keywords = "Evolutionary robotics, On-line evolution, Indirect encoding, Lamarckian evolution, Gait learning",
author = "Milan Jelisavcic and Rafael Kiesel and Kyrre Glette and Evert Haasdijk and A.E. Eiben",
year = "2017",
month = "7",
doi = "10.1145/3067695.3076046",
language = "English",
note = "The Genetic and Evolutionary Computation Conference, GECCO 2017 ; Conference date: 15-07-2017 Through 19-07-2017",
url = "http://gecco-2017.sigevo.org/index.html/HomePage",

}

Jelisavcic, M, Kiesel, R, Glette, K, Haasdijk, E & Eiben, AE 2017, 'Benefits of Lamarckian Evolution for Morphologically Evolving Robots' The Genetic and Evolutionary Computation Conference, Berlin, Germany, 15/07/17 - 19/07/17, . https://doi.org/10.1145/3067695.3076046

Benefits of Lamarckian Evolution for Morphologically Evolving Robots. / Jelisavcic, Milan; Kiesel, Rafael; Glette, Kyrre; Haasdijk, Evert; Eiben, A.E.

2017. Poster session presented at The Genetic and Evolutionary Computation Conference, Berlin, Germany.

Research output: Contribution to ConferencePosterOther research output

TY - CONF

T1 - Benefits of Lamarckian Evolution for Morphologically Evolving Robots

AU - Jelisavcic, Milan

AU - Kiesel, Rafael

AU - Glette, Kyrre

AU - Haasdijk, Evert

AU - Eiben, A.E.

PY - 2017/7

Y1 - 2017/7

N2 - Implementing lifetime learning by means of on-line evolution, we establish an indirect encoding scheme that combines Compositional Pattern Producing Networks (CPPNs) and Central Pattern Generators (CPGs) as a relevant learner and controller for open-loop gait controllers in modular robots which have evolving morphologies. Experimental validation on the morphologically evolved robots shows that a Lamarckian setup with CPPN-CPG provides substantial benefits compared to controllers learned from scratch.

AB - Implementing lifetime learning by means of on-line evolution, we establish an indirect encoding scheme that combines Compositional Pattern Producing Networks (CPPNs) and Central Pattern Generators (CPGs) as a relevant learner and controller for open-loop gait controllers in modular robots which have evolving morphologies. Experimental validation on the morphologically evolved robots shows that a Lamarckian setup with CPPN-CPG provides substantial benefits compared to controllers learned from scratch.

KW - Evolutionary robotics

KW - On-line evolution

KW - Indirect encoding

KW - Lamarckian evolution

KW - Gait learning

U2 - 10.1145/3067695.3076046

DO - 10.1145/3067695.3076046

M3 - Poster

ER -

Jelisavcic M, Kiesel R, Glette K, Haasdijk E, Eiben AE. Benefits of Lamarckian Evolution for Morphologically Evolving Robots. 2017. Poster session presented at The Genetic and Evolutionary Computation Conference, Berlin, Germany. https://doi.org/10.1145/3067695.3076046