Abstract: Disclosed is technology for controlling deep reinforcement learning-based legged robot locomotion by inferring implicit terrain information. A legged robot control method may include inferring an action of a quadrupedal robot from proprioception through a deep reinforcement learning-legged robot model, and a locomotion policy that implicitly infers properties of terrains through which the quadrupedal robot moves may be learned in the legged robot model.
Type:
Grant
Filed:
March 20, 2024
Date of Patent:
September 1, 2026
Assignee:
UROBOTICS CORP.
Inventors:
Hyun Myung, I Made Aswin Nahrendra, Byeongho Yu