Cargando…
Morphological Properties of Mass–Spring Networks for Optimal Locomotion Learning
Robots have proven very useful in automating industrial processes. Their rigid components and powerful actuators, however, render them unsafe or unfit to work in normal human environments such as schools or hospitals. Robots made of compliant, softer materials may offer a valid alternative. Yet, the...
Autores principales: | Urbain, Gabriel, Degrave, Jonas, Carette, Benonie, Dambre, Joni, Wyffels, Francis |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5366341/ https://www.ncbi.nlm.nih.gov/pubmed/28396634 http://dx.doi.org/10.3389/fnbot.2017.00016 |
Ejemplares similares
-
Body Randomization Reduces the Sim-to-Real Gap for Compliant Quadruped Locomotion
por: Vandesompele, Alexander, et al.
Publicado: (2019) -
A Differentiable Physics Engine for Deep Learning in Robotics
por: Degrave, Jonas, et al.
Publicado: (2019) -
Combining Evolutionary and Adaptive Control Strategies for Quadruped Robotic Locomotion
por: Massi, Elisa, et al.
Publicado: (2019) -
Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics
por: Burms, Jeroen, et al.
Publicado: (2015) -
Highly parallel simulation and optimization of photonic circuits in time and frequency domain based on the deep-learning framework PyTorch
por: Laporte, Floris, et al.
Publicado: (2019)