An Experiment in Morphological Development for Learning ANN Based Controllers
- Martin Naya,
- ,
- Richard Duro
- University of A Coruna,
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-reviewOpen access
Publication Information
Output type
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-reviewOriginal language
EnglishPublication milestones
- Published - 2020
Publication status
Published - 2020
Publisher
IEEE, United StatesISBN (Electronic)
978-1-7281-6926-2Publication IDs
- Scopus: 85093853504
Host publication title
Proceedings of 2020 International Joint Conference on Neural Networks (IJCNN)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.
Publication metrics
PlumX, opens in new tab
Captures
11
Citations
5
Access to documents
Submitted manuscript, 396.08 KB
Related Event
Title
International Joint Conference on Neural Networks
Event type
ConferenceDate
19/07/2020 - 24/07/2020Location
United Kingdom
