Cargando…
A parallel heterogeneous policy deep reinforcement learning algorithm for bipedal walking motion design
Considering the dynamics and non-linear characteristics of biped robots, gait optimization is an extremely challenging task. To tackle this issue, a parallel heterogeneous policy Deep Reinforcement Learning (DRL) algorithm for gait optimization is proposed. Firstly, the Deep Deterministic Policy Gra...
Autores principales: | Li, Chunguang, Li, Mengru, Tao, Chongben |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10442573/ https://www.ncbi.nlm.nih.gov/pubmed/37614967 http://dx.doi.org/10.3389/fnbot.2023.1205775 |
Ejemplares similares
-
Implementation of Deep Deterministic Policy Gradients for Controlling Dynamic Bipedal Walking
por: Liu, Chujun, et al.
Publicado: (2019) -
Gait Optimization Method for Humanoid Robots Based on Parallel Comprehensive Learning Particle Swarm Optimizer Algorithm
por: Tao, Chongben, et al.
Publicado: (2021) -
Modeling, simulation and optimization of bipedal walking
por: Mombaur, Katja, et al.
Publicado: (2013) -
Multimodal bipedal locomotion generation with passive dynamics via deep reinforcement learning
por: Koseki, Shunsuke, et al.
Publicado: (2023) -
Anticipatory Control of Momentum for Bipedal Walking on Uneven Terrain
por: Darici, Osman, et al.
Publicado: (2020)