Terrain-Aware Risk-Assessment-Network-Aided Deep Reinforcement Learning for Quadrupedal Locomotion in Tough Terrain
Hongyin Zhang,Jilong Wang,Zhengqing Wu,Yinuo Wang,Donglin Wang,Hongyin Zhang,Jilong Wang,Zhengqing Wu,Yinuo Wang,Donglin Wang
When it comes to the control system of quadruped robots, deep reinforcement learning (DRL) is considered to be a promising solution. Despite years of development in this field, difficulties remain in guaranteeing the action stability of DRL-based quadruped robots’ locomotion, especially in tough terrain. In this paper, a terrain-aware teacher-student controller integrating a risk assessment networ...
