Xu Chang

Xu Chang

Auto-generated profile, based on publicly available information

Xu Chang

National University of Defense Technology College of Intelligence Science

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 September 2021 in International Journal of Control, Automation, and Systems
Verified
Journal Article
Closed access
PDF file
XCXu Chang
Xu Chang
HMHongxu Ma
Hongxu Ma
HAHonglei An
Honglei An

18 October 2021 in Robotica
Verified
Journal Article
Closed access
PDF file
XCXu Chang
Xu Chang
HAHONGLEI AN
HONGLEI AN
HMHongxu Ma
Hongxu Ma
This paper first uses a decoupling modeling method to model legged robots. The method groups all the degrees of freedom according to the number of limbs, regarding each limb as a manipulator with serial structure, which greatly reduces the number of dynamic parameters that need to be identified simultaneously. On this basis, a step-by-step identification method from the end-effector link to the base link, referred to as “E-B” identification method, is proposed. Simulation verification is carried out on a quadruped robot with 16 degrees of freedom in Gazebo, and the validity of the method proposed is discussed.

18 October 2023
Verified
Preprint
Open access
PDF file
XCXu Chang
Xu Chang
ZZZhitong Zhang
Zhitong Zhang
HAHonglei An
Honglei An
HMHongxu Ma
Hongxu Ma
QWQing Wei
Qing Wei
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.