Abstract
We investigate whether a swarm of robots can evolve controllers that cause aggregation into 'multi-cellular' robot organisms without a specific reward to do so. To this end, we create a world where aggregated robots receive more energy than individual ones and enable robots to evolve their controllers on-the-fly, during their lifetime. We perform experiments in six different implementations of the basic idea distinguished by the system of energy distribution and the level of advantage aggregated robots have over individual ones. The results show that 'multi-cellular' robot organisms emerge in all of these cases. © 2012 Springer-Verlag.
| Original language | English |
|---|---|
| Pages (from-to) | 124-134 |
| Journal | Lecture Notes in Computer Science |
| Volume | 7248 |
| DOIs | |
| Publication status | Published - 2012 |
| Event | EvoApplications - Duration: 11 Apr 2012 → 13 Apr 2012 |
Bibliographical note
Proceedings title: Applications of Evolutionary Computation: Proceedings of EvoApplications 2012Publisher: Springer
ISBN: 978-3-642-29178-4
Editors: C di Chio
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 7 Affordable and Clean Energy
Fingerprint
Dive into the research topics of 'The Emergence of Multi-Cellular Robot Organisms through On-line On-board Evolution'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver