Cargando…
Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms
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 diffe...
Autores principales: | Hasselmann, Ken, Ligot, Antoine, Ruddick, Julian, Birattari, Mauro |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8285396/ https://www.ncbi.nlm.nih.gov/pubmed/34272382 http://dx.doi.org/10.1038/s41467-021-24642-3 |
Ejemplares similares
-
Automatic Off-Line Design of Robot Swarms: A Manifesto
por: Birattari, Mauro, et al.
Publicado: (2019) -
Complexity Measures: Open Questions and Novel Opportunities in the Automatic Design and Analysis of Robot Swarms
por: Roli, Andrea, et al.
Publicado: (2019) -
Automatic modular design of robot swarms using behavior trees as a control architecture
por: Ligot, Antoine, et al.
Publicado: (2020) -
On Using Simulation to Predict the Performance of Robot Swarms
por: Ligot, Antoine, et al.
Publicado: (2022) -
Concurrent design of control software and configuration of hardware for robot swarms under economic constraints
por: Salman, Muhammad, et al.
Publicado: (2019)