Growth-based morphological development: a natural approach to fitness landscape shaping

Martin Naya, Andres Faina, Richard Duro

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

In nature, the morphological changes that occur as cognitive development takes place in human beings and animals have been shown to facilitate learning. Taking inspiration from nature, morphological development aimed at improving learning has been applied in the literature to different robotics configurations and tasks with mixed results. In this paper, we consider a growth-based morphological development approach applied to a quadruped walking task, and, in addition to determining that it improves the learning characteristics, we show that morphological development is something other than just introducing noise as a fitness landscape smoothing technique. Finally, by means of a study of the evolution of the different fitness landscapes, we argue and discuss that learning using growth is equivalent to an incremental learning or fitness landscape shaping approach.
OriginalsprogEngelsk
TitelProceedings of the Genetic and Evolutionary Computation Conference Companion
ForlagAssociation for Computing Machinery
Publikationsdato2022
Sider140–143
ISBN (Elektronisk)9781450392686
DOI
StatusUdgivet - 2022
BegivenhedGECCO '22: Genetic and Evolutionary Computation Conference - Boston, USA
Varighed: 9 jul. 202213 jul. 2022

Konference

KonferenceGECCO '22: Genetic and Evolutionary Computation Conference
Land/OmrådeUSA
ByBoston
Periode09/07/202213/07/2022

Emneord

  • Morphological Development
  • Cognitive Development
  • Quadruped Robotics
  • Fitness Landscape
  • Incremental Learning

Fingeraftryk

Dyk ned i forskningsemnerne om 'Growth-based morphological development: a natural approach to fitness landscape shaping'. Sammen danner de et unikt fingeraftryk.

Citationsformater