Open AccessOnboard Evolution of Understandable Swarm Behaviors
Author(s) -
Jones Simon,
Winfield Alan F.,
Hauert Sabine,
Studley Matthew
Publication year - 2019
Publication title -
advanced intelligent systems
Language(s) - English
Resource type - Journals
ISSN - 2640-4567
DOI - 10.1002/aisy.201970062
Subject(s) - swarm robotics , swarm behaviour , ant robotics , robot , artificial intelligence , computer science , robotics , swarm intelligence , evolutionary robotics , mobile robot , machine learning , robot control , particle swarm optimization
Evolutionary Swarm Robotics : As described in article number 1900031 by Sabine Hauert, Matthew Studley, and co‐workers, the Xpuck Teraflop swarm, with considerable onboard processing power, evolves behavior trees directly onboard the individual robots to quickly and automatically discover useful swarm strategies which are understandable to humans. This could be the first step toward deploying robots in real‐world applications in a fully automatic and adaptable way.