Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms

Ken Hasselmann, Antoine Ligot, Julian Ruddick and Mauro Birattari ()
Additional contact information
Ken Hasselmann: IRIDIA, Université libre de Bruxelles
Antoine Ligot: IRIDIA, Université libre de Bruxelles
Julian Ruddick: IRIDIA, Université libre de Bruxelles
Mauro Birattari: IRIDIA, Université libre de Bruxelles

Nature Communications, 2021, vol. 12, issue 1, 1-11

Abstract: Abstract Neuro-evolution is an appealing approach to generating collective behaviors for robot swarms. In its typical application, known as off-line automatic design, the neural networks controlling the robots are optimized in simulation. It is understood that the so-called reality gap, the unavoidable differences between simulation and reality, typically causes neural network to be less effective on real robots than what is predicted by simulation. In this paper, we present an empirical study on the extent to which the reality gap impacts the most popular and advanced neuro-evolutionary methods for the off-line design of robot swarms. The results show that the neural networks produced by the methods under analysis performed well in simulation, but not in real-robot experiments. Further, the ranking that could be observed in simulation between the methods eventually disappeared. We find compelling evidence that real-robot experiments are needed to reliably assess the performance of neuro-evolutionary methods and that the robustness to the reality gap is the main issue to be addressed to advance the application of neuro-evolution to robot swarms.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-021-24642-3 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-24642-3

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-021-24642-3

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().