An Experiment in Morphological Development for Learning ANN Based Controllers

Martin Naya, Andres Faina, Richard Duro

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer 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.
OriginalsprogEngelsk
TitelProceedings of 2020 International Joint Conference on Neural Networks (IJCNN)
Antal sider8
ForlagIEEE
Publikationsdato2020
ISBN (Elektronisk)978-1-7281-6926-2
DOI
StatusUdgivet - 2020
BegivenhedInternational Joint Conference on Neural Networks - , Storbritannien
Varighed: 19 jul. 202024 jul. 2020

Konference

KonferenceInternational Joint Conference on Neural Networks
Land/OmrådeStorbritannien
Periode19/07/202024/07/2020

Emneord

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

Fingeraftryk

Dyk ned i forskningsemnerne om 'An Experiment in Morphological Development for Learning ANN Based Controllers'. Sammen danner de et unikt fingeraftryk.

Citationsformater