Body Randomization Reduces the Sim-to-Real Gap for Compliant Quadruped Locomotion

Designing controllers for compliant, underactuated robots is challenging and usually requires a learning procedure. Learning robotic control in simulated environments can speed up the process whilst lowering risk of physical damage. Since perfect simulations are unfeasible, several techniques are us...

Descripción completa

Detalles Bibliográficos
Autores principales: Vandesompele, Alexander, Urbain, Gabriel, Mahmud, Hossain, wyffels, Francis, Dambre, Joni
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2019
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6448581/
https://www.ncbi.nlm.nih.gov/pubmed/30983987
http://dx.doi.org/10.3389/fnbot.2019.00009

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6448581/
https://www.ncbi.nlm.nih.gov/pubmed/30983987
http://dx.doi.org/10.3389/fnbot.2019.00009

Ejemplares similares