Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
Off-line neuro-evolution produces robot swarms whose good performance in simulation does not often transfer to the real word. With an extensive empirical study, Hasselmann et al. substantiate overfitting as the dominant cause.
Main Authors: | Ken Hasselmann, Antoine Ligot, Julian Ruddick, Mauro Birattari |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-07-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-021-24642-3 |
Similar Items
-
Automatic Off-Line Design of Robot Swarms: A Manifesto
by: Mauro Birattari, et al.
Published: (2019-07-01) -
Complexity Measures: Open Questions and Novel Opportunities in the Automatic Design and Analysis of Robot Swarms
by: Andrea Roli, et al.
Published: (2019-11-01) -
Automatic modular design of robot swarms using behavior trees as a control architecture
by: Antoine Ligot, et al.
Published: (2020-11-01) -
Concurrent design of control software and configuration of hardware for robot swarms under economic constraints
by: Muhammad Salman, et al.
Published: (2019-09-01) -
Modular automatic design of collective behaviors for robots endowed with local communication capabilities
by: Ken Hasselmann, et al.
Published: (2020-08-01)