Cargando…
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...
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: | |
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 |
Ejemplares similares
-
Combining Evolutionary and Adaptive Control Strategies for Quadruped Robotic Locomotion
por: Massi, Elisa, et al.
Publicado: (2019) -
Morphological Properties of Mass–Spring Networks for Optimal Locomotion Learning
por: Urbain, Gabriel, et al.
Publicado: (2017) -
A Simple Yet Effective Whole-Body Locomotion Framework for Quadruped Robots
por: Raiola, Gennaro, et al.
Publicado: (2020) -
The effect of tail stiffness on a sprawling quadruped locomotion
por: Buckley, Josh, et al.
Publicado: (2023) -
Leg Locomotion Adaption for Quadruped Robots with Ground Compliance Estimation
por: Zhang, Songyuan, et al.
Publicado: (2020)