loading page

Learning fast and agile quadrupedal locomotion over complex terrain
  • +2
  • Xu Chang,
  • Zhitong Zhang,
  • Honglei An,
  • Hongxu Ma,
  • Qing Wei
Xu Chang
National University of Defense Technology College of Intelligence Science

Corresponding Author:[email protected]

Author Profile
Zhitong Zhang
National University of Defense Technology College of Intelligence Science
Author Profile
Honglei An
National University of Defense Technology College of Intelligence Science
Author Profile
Hongxu Ma
National University of Defense Technology College of Intelligence Science
Author Profile
Qing Wei
National University of Defense Technology College of Intelligence Science
Author Profile

Abstract

In this paper, we propose a robust controller that achieves natural and stably fast locomotion on a real blind quadruped robot. With only proprioceptive information, the quadruped robot can move at a maximum speed of 10 times its body length per second, and has the ability to pass through various complex terrains. The controller is trained in the simulation environment by model-free reinforcement learning and no specific human knowledge such as a foot trajectory generator are used in the training architecture. Our research finds that there is a problem of data symmetry loss during training, which leads to unbalanced performance of the learned controller on the left-right symmetric quadruped robot structure, and proposes a mirror-world neural network to solve the performance problem. The learned controller composed of the mirror-world network can make the robot achieve excellent anti-disturbance ability. The learned controller can coordinate the robot’s gait frequency and locomotion speed, and has good generalization ability to reach locomotion speed it has never learned and traverse terrains it has never seen before.