Directed locomotion for modular robots with evolvable morphologies

Gongjin Lan, M. Jelisavcic, Diederik M. Roijers, Evert Haasdijk, Agoston Eiben

Onderzoeksoutput: Conference paper

13 Citaten (Scopus)

Samenvatting

Morphologically evolving robot systems need to include a learning period right after ‘birth’ to acquire a controller that fits the newly created body. In this paper, we investigate learning one skill in particular: walking in a given direction. To this end, we apply the HyperNEAT algorithm guided by a fitness function that balances the distance travelled in a direction and the deviation between the desired and the actually travelled directions. We validate this method on a variety of modular robots with different shapes and sizes and observe that the best controllers produce trajectories that accurately follow the correct direction and reach a considerable distance in the given test interval.

Originele taal-2English
TitelParallel Problem Solving from Nature – PPSN XV
UitgeverijSpringer
Pagina's476-487
ISBN van geprinte versie9783319992532, 9783319992525
DOI's
StatusPublished - 22 aug 2018
Evenement15th International Conference on Parallel Problem Solving from Nature - Coimbra, Portugal
Duur: 8 sep 201812 sep 2018
http://ppsn2018.dei.uc.pt/

Conference

Conference15th International Conference on Parallel Problem Solving from Nature
Verkorte titelPPSN
Land/RegioPortugal
StadCoimbra
Periode8/09/1812/09/18
Internet adres

Vingerafdruk

Duik in de onderzoeksthema's van 'Directed locomotion for modular robots with evolvable morphologies'. Samen vormen ze een unieke vingerafdruk.

Citeer dit