Onboard evolution of understandable swarm behaviors

Simon Jones, Alan F T Winfield, Sabine Hauert, Matthew Studley

Research output: Contribution to journalArticle (Academic Journal)

181 Downloads (Pure)

Abstract

Designing the individual robot rules that give rise to desired emergent swarm behaviors is difficult. The common method of running evolutionary algorithms off-line to automatically discover controllers in simulation suffers from two disadvantages; the generation of controllers is not situated in the swarm and so cannot be performed in the wild, and the evolved controllers are often opaque and hard to understand. A swarm of robots with considerable on-board processing power is used to move the evolutionary process into the swarm, providing a potential route to continuously generating swarm behaviors adapted to the environments and tasks at hand. By making the evolved controllers human-understandable using behavior trees, the controllers can be queried, explained, and even improved by a human user. A swarm system capable of evolving and executing fit controllers in less than 15 minutes entirely within the swarm is demonstrated. One of the evolved controllers is then analyzed to explain its functionality. With the insights gained, a significant performance improvement in the evolved controller is engineered.
Original languageEnglish
Article number1900031
Number of pages12
JournalAdvanced Intelligent Systems
Volume1
Issue number6
Early online date18 Jul 2019
DOIs
Publication statusPublished - Oct 2019

Keywords

  • evolutionary robotics
  • swarm robotics

Fingerprint Dive into the research topics of 'Onboard evolution of understandable swarm behaviors'. Together they form a unique fingerprint.

  • Cite this