Skip to main navigation Skip to search Skip to main content

Unconventional Hexacopters via Evolution and Learning: Performance Gains and New Insights

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

This study investigates a system of hexacopter type drones with evolvable morphologies and learnable controllers. The combination of morphological evolution and reinforcement learning is shown to produce unconventional drones that significantly outperform the traditional hexacopter on several tasks that are more complex than previously considered in the literature. In addition, novel metrics are introduced and new analyses are conducted on the interaction between morphological evolution and learning, uncovering previously unidentified effects.

Original languageEnglish
Title of host publicationApplications of Evolutionary Computation
Subtitle of host publication29th European Conference, EvoApplications 2026, Held as Part of EvoStar 2026, Toulouse, France, April 8–10, 2026, Proceedings, Part I
EditorsPablo García-Sánchez, Josefa Díaz Álvarez, Aidan Murphy
PublisherSpringer Science and Business Media Deutschland GmbH
Pages69-84
Number of pages16
Volume1
ISBN (Electronic)9783032236043
ISBN (Print)9783032236036
DOIs
Publication statusPublished - 2026
Event29th European Conference on Applications of Evolutionary Computation, EvoApplications 2026, held as part of EvoStar 2026 - Toulouse, France
Duration: 8 Apr 202610 Apr 2026

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume16524 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameEvoApplications: International Conference on the Applications of Evolutionary Computation (Part of EvoStar)
PublisherSpringer
Volume2026

Conference

Conference29th European Conference on Applications of Evolutionary Computation, EvoApplications 2026, held as part of EvoStar 2026
Country/TerritoryFrance
CityToulouse
Period8/04/2610/04/26

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Keywords

  • aerial robotics
  • co-optimization
  • evolutionary robotics
  • lifetime learning
  • morphological evolution
  • reinforcement learning

Fingerprint

Dive into the research topics of 'Unconventional Hexacopters via Evolution and Learning: Performance Gains and New Insights'. Together they form a unique fingerprint.

Cite this