Data-Driven Latent Space Representation for Robust Bipedal Locomotion Learning
Guillermo A. Castillo,Bowen Weng,Wei Zhang,Ayonga Hereid,Guillermo A. Castillo,Bowen Weng,Wei Zhang,Ayonga Hereid
This paper presents a novel framework for learning robust bipedal walking by combining a data-driven state representation with a Reinforcement Learning (RL) based locomotion policy. The framework utilizes an autoencoder to learn a low-dimensional latent space that captures the complex dynamics of bipedal locomotion from existing locomotion data. This reduced dimensional state representation is the...
