Unconventional Hexacopters via Evolution and Learning

None, None; None, None; None, None; None, None; None, None

Unconventional Hexacopters via Evolution and Learning

Performance Gains and New Insights

Conference Paper (2026)

Author(s)

Jed R. Muff (Vrije Universiteit Amsterdam)

Keiichi Ito (Vrije Universiteit Amsterdam)

Elijah H.W. Ang (TU Delft - Aerospace Engineering)

Karine Miras (Vrije Universiteit Amsterdam)

A. E. Eiben (Vrije Universiteit Amsterdam)

Research Group

Control & Simulation

Reinforcement learning Co-optimization Aerial robotics Morphological evolution Evolutionary robotics Lifetime learning

DOI related publication

https://doi.org/10.1007/978-3-032-23604-3_5 Final published version

To reference this document use

https://resolver.tudelft.nl/uuid:6d78232c-cc8d-46d1-83ba-c5b8033b9437

More Info

expand_more

Publication Year

2026

Language

English

Research Group

Control & Simulation

Pages (from-to)

69-84

Publisher

Springer Nature

ISBN (print)

9783032236036

Event

29th European Conference on Applications of Evolutionary Computation, EvoApplications 2026, held as part of EvoStar 2026 (2026-04-08 - 2026-04-10), Toulouse, France

Page Views

8

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

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.

Files

978-3-032-23604-3_5.pdf

(pdf | 2.07 Mb)

– Personal use only – Dutch Copyright Act (Article 25fa)

File under embargo until 09-11-2026