Close menu

SURE

Sunderland Repository records the research produced by the University of Sunderland including practice-based research and theses.

Bootstrapping Artificial Evolution to Design Robots for Autonomous Fabrication

Buchanan, Edgar, Le Goff, Léni K., Li, Wei, Hart, Emma, Eiben, Agoston E., De Carlo, Matteo, Winfield, Alan F., Hale, Matthew F., Woolley, Robert, Angus, Mike, Timmis, Jon and Tyrrell, Andy M. (2020) Bootstrapping Artificial Evolution to Design Robots for Autonomous Fabrication. Robotics, 9 (4). e106. ISSN 2218-6581

Item Type: Article

Abstract

A long-term vision of evolutionary robotics is a technology enabling the evolution of entire autonomous robotic ecosystems that live and work for long periods in challenging and dynamic environments without the need for direct human oversight. Evolutionary robotics has been widely used due to its capability of creating unique robot designs in simulation. Recent work has shown that it is possible to autonomously construct evolved designs in the physical domain; however, this brings new challenges: the autonomous manufacture and assembly process introduces new constraints that are not apparent in simulation. To tackle this, we introduce a new method for producing a repertoire of diverse but manufacturable robots. This repertoire is used to seed an evolutionary loop that subsequently evolves robot designs and controllers capable of solving a maze-navigation task. We show that compared to random initialisation, seeding with a diverse and manufacturable population speeds up convergence and on some tasks, increases performance, while maintaining manufacturability.

[img]
Preview
PDF
robotics-09-00106.pdf - Published Version
Available under License Creative Commons Attribution.

Download (21MB) | Preview

More Information

Additional Information: ** From MDPI via Jisc Publications Router ** History: accepted 02-12-2020; pub-electronic 07-12-2020. ** Licence for this article: https://creativecommons.org/licenses/by/4.0/
Uncontrolled Keywords: evolutionary robotics, autonomous robot evolution, autonomous robot fabrication, robot manufacturability
Related URLs:
SWORD Depositor: Publication Router
Depositing User: Publication Router

Identifiers

Item ID: 12855
Identification Number: https://doi.org/10.3390/robotics9040106
ISSN: 2218-6581
URI: http://sure.sunderland.ac.uk/id/eprint/12855
Official URL: https://www.mdpi.com/2218-6581/9/4/106

Users with ORCIDS

ORCID for Edgar Buchanan: ORCID iD orcid.org/0000-0001-6587-8808
ORCID for Léni K. Le Goff: ORCID iD orcid.org/0000-0003-1749-9154
ORCID for Agoston E. Eiben: ORCID iD orcid.org/0000-0002-3106-4213
ORCID for Matteo De Carlo: ORCID iD orcid.org/0000-0002-6435-0873
ORCID for Alan F. Winfield: ORCID iD orcid.org/0000-0002-1476-3127
ORCID for Jon Timmis: ORCID iD orcid.org/0000-0003-1055-0471
ORCID for Andy M. Tyrrell: ORCID iD orcid.org/0000-0002-8533-2404

Catalogue record

Date Deposited: 14 Dec 2020 14:56
Last Modified: 14 Dec 2020 15:00

Contributors

Author: Edgar Buchanan ORCID iD
Author: Léni K. Le Goff ORCID iD
Author: Agoston E. Eiben ORCID iD
Author: Matteo De Carlo ORCID iD
Author: Alan F. Winfield ORCID iD
Author: Jon Timmis ORCID iD
Author: Andy M. Tyrrell ORCID iD
Author: Wei Li
Author: Emma Hart
Author: Matthew F. Hale
Author: Robert Woolley
Author: Mike Angus

University Divisions

Faculty of Technology > School of Computer Science

Actions (login required)

View Item (Repository Staff Only) View Item (Repository Staff Only)