Evolving Behavioral Specialization in Robot Teams to Solve a Collective Construction Task

G. Nitschke; M.C. Schut; A.E. Eiben

doi:10.1016/j.swevo.2011.08.002

Evolving Behavioral Specialization in Robot Teams to Solve a Collective Construction Task

G. Nitschke, M.C. Schut, A.E. Eiben

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

This article comparatively tests three cooperative co-evolution methods for automated controller design in simulated robot teams. Collective Neuro-Evolution (CONE) co-evolves multiple robot controllers using emergent behavioral specialization in order to increase collective behavior task performance. CONE is comparatively evaluated with two related controller design methods in a collective construction task. The task requires robots to gather building blocks and assemble the blocks in specific sequences in order to build structures. Results indicate that for the team sizes tested, CONE yields a higher collective behavior task performance (comparative to related methods) as a consequence of its capability to evolve specialized behaviors. © 2011 Elsevier B.V. All rights reserved.

Original language	English
Pages (from-to)	25-38
Number of pages	14
Journal	Swarm and Evolutionary Computation
Volume	2
Issue number	1
Early online date	14 Sept 2011
DOIs	https://doi.org/10.1016/j.swevo.2011.08.002
Publication status	Published - 2012

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.swevo.2011.08.002

Persistent URL (handle)

Persistent link

Cite this

@article{f3d7556fc58d455096c0ac3cc8dc9c61,

title = "Evolving Behavioral Specialization in Robot Teams to Solve a Collective Construction Task",

abstract = "This article comparatively tests three cooperative co-evolution methods for automated controller design in simulated robot teams. Collective Neuro-Evolution (CONE) co-evolves multiple robot controllers using emergent behavioral specialization in order to increase collective behavior task performance. CONE is comparatively evaluated with two related controller design methods in a collective construction task. The task requires robots to gather building blocks and assemble the blocks in specific sequences in order to build structures. Results indicate that for the team sizes tested, CONE yields a higher collective behavior task performance (comparative to related methods) as a consequence of its capability to evolve specialized behaviors. {\textcopyright} 2011 Elsevier B.V. All rights reserved.",

author = "G. Nitschke and M.C. Schut and A.E. Eiben",

year = "2012",

doi = "10.1016/j.swevo.2011.08.002",

language = "English",

volume = "2",

pages = "25--38",

journal = "Swarm and Evolutionary Computation",

issn = "2210-6502",

publisher = "Elsevier BV",

number = "1",

}

TY - JOUR

T1 - Evolving Behavioral Specialization in Robot Teams to Solve a Collective Construction Task

AU - Nitschke, G.

AU - Schut, M.C.

AU - Eiben, A.E.

PY - 2012

Y1 - 2012

N2 - This article comparatively tests three cooperative co-evolution methods for automated controller design in simulated robot teams. Collective Neuro-Evolution (CONE) co-evolves multiple robot controllers using emergent behavioral specialization in order to increase collective behavior task performance. CONE is comparatively evaluated with two related controller design methods in a collective construction task. The task requires robots to gather building blocks and assemble the blocks in specific sequences in order to build structures. Results indicate that for the team sizes tested, CONE yields a higher collective behavior task performance (comparative to related methods) as a consequence of its capability to evolve specialized behaviors. © 2011 Elsevier B.V. All rights reserved.

AB - This article comparatively tests three cooperative co-evolution methods for automated controller design in simulated robot teams. Collective Neuro-Evolution (CONE) co-evolves multiple robot controllers using emergent behavioral specialization in order to increase collective behavior task performance. CONE is comparatively evaluated with two related controller design methods in a collective construction task. The task requires robots to gather building blocks and assemble the blocks in specific sequences in order to build structures. Results indicate that for the team sizes tested, CONE yields a higher collective behavior task performance (comparative to related methods) as a consequence of its capability to evolve specialized behaviors. © 2011 Elsevier B.V. All rights reserved.

U2 - 10.1016/j.swevo.2011.08.002

DO - 10.1016/j.swevo.2011.08.002

M3 - Article

SN - 2210-6502

VL - 2

SP - 25

EP - 38

JO - Swarm and Evolutionary Computation

JF - Swarm and Evolutionary Computation

IS - 1

ER -

Evolving Behavioral Specialization in Robot Teams to Solve a Collective Construction Task

Abstract

UN SDGs

Access to Document

Persistent URL (handle)

Fingerprint

Cite this