An Experiment in Morphological Development for Learning ANN Based Controllers

Martin Naya, Andres Faina, Richard Duro

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Abstract

Morphological development is part of the way any human or animal learns. The learning processes starts with the morphology at birth and progresses through changing morphologies until adulthood is reached. Biologically, this seems to facilitate learning and make it more robust. However, when this approach is transferred to robotic systems, the results found in the literature are inconsistent: morphological development does not provide a learning advantage in every case. In fact, it can lead to poorer results than when learning with a fixed morphology. In this paper we analyze some of the issues involved by means of a simple, but very informative experiment in quadruped walking. From the results obtained an initial series of insights on when and under what conditions to apply morphological development for learning are presented.
Original languageEnglish
Title of host publicationProceedings of 2020 International Joint Conference on Neural Networks (IJCNN)
Number of pages8
PublisherIEEE
Publication date2020
ISBN (Electronic)978-1-7281-6926-2
DOIs
Publication statusPublished - 2020
EventInternational Joint Conference on Neural Networks - , United Kingdom
Duration: 19 Jul 202024 Jul 2020

Conference

ConferenceInternational Joint Conference on Neural Networks
Country/TerritoryUnited Kingdom
Period19/07/202024/07/2020

Keywords

  • Morphological Development
  • Robotic Learning
  • Quadruped Walking Experiment
  • Biological Learning Processes
  • Adaptive Morphologies

Fingerprint

Dive into the research topics of 'An Experiment in Morphological Development for Learning ANN Based Controllers'. Together they form a unique fingerprint.

Cite this