Teams of self-organised robots could be efficient in exploring Mars

Artificial evolution key to self-organising robots

Artificial evolution mimicking principles of Darwinian natural selection could lead to the creation of self-organised robots.

In a simulation run by a team of researchers from the University of Leuven, the Free University of Brussels (both Belgium) and the Middle East Technical University, Turkey, teams of robots were able to get organised and divide tasks between themselves in the same way ants, bees and other social insects do.

In an article published in the journal PLOS Computational Biology, the research team led by Eliseo Ferrante from KU Leuven described how different robots  automatically specialised to carry out different subtasks in the group.

The researchers used a computational technique known as grammatical evolution to have the robotic teams organise themselves in a simulated hunt for food. 

“Remarkably, such a division of labour could be achieved even if the robots were not told beforehand how the global task of retrieving items back to their base could best be divided into smaller subtasks,” the researchers wrote in the article.

“This is the first time that a self-organized division of labour mechanism could be evolved de novo.”

The field of 'swarm robotics' aims to use teams of small robots to explore complex environments, such as the moon or foreign planets. However, designing controllers that allow the robots to effectively organise themselves has so far been complicated. The simulation of the Belgian-Turkish team achieved better results than was previously possible.


Recent articles

Info Message

Our sites use cookies to support some functionality, and to collect anonymous user data.

Learn more about IET cookies and how to control them