Evolving Robots on Easy Mode: Towards a Variable Complexity Controller for Quadrupeds

Tønnes F. Nygaard*, Charles P. Martin, Jim Torresen, Kyrre Glette

*Corresponding author for this work

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

6 Citations (Scopus)

Abstract

The complexity of a legged robot’s environment or task can inform how specialised its gait must be to ensure success. Evolving specialised robotic gaits demands many evaluations—acceptable for computer simulations, but not for physical robots. For some tasks, a more general gait, with lower optimization costs, could be satisfactory. In this paper, we introduce a new type of gait controller where complexity can be set by a single parameter, using a dynamic genotype-phenotype mapping. Low controller complexity leads to conservative gaits, while higher complexity allows more sophistication and high performance for demanding tasks, at the cost of optimization effort. We investigate the new controller on a virtual robot in simulations and do preliminary testing on a real-world robot. We show that having variable complexity allows us to adapt to different optimization budgets. With a high evaluation budget in simulation, a complex controller performs best. Moreover, real-world evolution with a limited evaluation budget indicates that a lower gait complexity is preferable for a relatively simple environment.

Original languageEnglish
Title of host publicationApplications of Evolutionary Computation
Subtitle of host publication22nd International Conference, EvoApplications 2019, Held as Part of EvoStar 2019, Leipzig, Germany, April 24–26, 2019, Proceedings
EditorsPaul Kaufmann, Pedro A. Castillo
Place of PublicationCham
PublisherSpringer
Pages616-632
Number of pages17
ISBN (Electronic)978-3-030-16692-2
ISBN (Print)978-3-030-16691-5
DOIs
Publication statusPublished - 2019
Externally publishedYes
Event22nd International Conference on Applications of Evolutionary Computation, EvoApplications 2019, held as Part of EvoStar 2019 - Leipzig, Germany
Duration: 24 Apr 201926 Apr 2019
http://www.evostar.org/2019/

Publication series

NameLecture Notes in Computer Science (LNCS)
PublisherSpringer
Volume11454
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference22nd International Conference on Applications of Evolutionary Computation, EvoApplications 2019, held as Part of EvoStar 2019
Abbreviated titleEvoApplications 2019
Country/TerritoryGermany
CityLeipzig
Period24/04/1926/04/19
Internet address

Fingerprint

Dive into the research topics of 'Evolving Robots on Easy Mode: Towards a Variable Complexity Controller for Quadrupeds'. Together they form a unique fingerprint.

Cite this