Robot Swarms Can Evolve to Self-Organize Their Tasks

Evolution isn't just for biological species; it's also something that can occur with robots. Researchers have found that Darwinian selection can be used to evolve robot controllers able to effectively self-organize their tasks.

The scientists evolved complex robot behaviors using artificial evolution and detailed robotics simulations. These findings, in particular, are important for "swarm robotics."

Swarm robotics aims to use teams of small robots to explore complex environments, such as on the moon or foreign planets. A large team of small robots can cover more group more quickly, and could also aid in search and rescue missions on Earth. However, designing controllers that allow the robots to effectively organize themselves isn't easy, which is why the researchers conducted this latest study.

The researchers created simulations to take a closer look at how robots could potentially evolve to work together. They found that, similar to biological organisms, the robots could specialize over time.

Just like social insects such as ants, bees or termites, teams of robots can display a self-organized division of labor in which the different robots automatically specialize into carrying out different subtasks in a group.

The findings are especially important for swarm robotics. As technology improves, it's important to know what direction to take in order to create the most effective team of robots for search and exploration tasks and other jobs that may require robot swarms.

The findings are published in the journal PLOS: Computational Biology.

Related Stories

Virtual Reality: How Technology is on the Brink of Taking Us to Virtual Worlds

NASA Robot 'Weaves' Rocket Parts for Future Mars Mission (VIDEO)

For more great science stories and general news, please visit our sister site, Headlines and Global News (HNGN).