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.
LEARNING ROBUST LEGGED ROBOT LOCOMOTION WITH IMPLICIT TERRAIN IMAGINATION VIA DEEP REINFORCEMENT LEARNING
2025-01-16
Patent
Electronic Resource
English
European Patent Office | 2025
|RLOC: terrain-aware legged locomotion using reinforcement learning and optimal control
BASE | 2022
|A Bayesian regression approach to terrain mapping and an application to legged robot locomotion
British Library Online Contents | 2009
|