Learning Quadrupedal Locomotion with Impaired Joints Using Random Joint Masking
Mincheol Kim,Ukcheol Shin,Jung-Yup Kim,Mincheol Kim,Ukcheol Shin,Jung-Yup Kim
Quadrupedal robots have played a crucial role in various environments, from structured environments to complex harsh terrains, thanks to their agile locomotion ability. However, these robots can easily lose their locomotion functionality if damaged by external accidents or internal malfunctions. In this paper, we propose a novel deep reinforcement learning framework to enable a quadrupedal robot t...
