Learning to acquire whole-body humanoid CoM movements to achieve dynamic tasks

This paper presents a novel approach to acquire dynamic whole-body movements on humanoid robots focused on learning a control policy for the center of mass. A policy-gradient method is used to acquire a CoM movement as a control policy for achieving a desired dynamic task. A CoM-Jacobian-based redun...

Full description

Saved in:
Bibliographic Details
Main Authors: Matsubara, T., Morimoto, J., Nakanishi, J., Sang-Ho Hyon, Hale, J.G., Cheng, G.
Format: Conference Proceeding
Language:English
Subjects:
Angular velocity
Computational modeling
Equations
Humanoid robot
Humanoid robots
Humans
Learning
Legged locomotion
Orbital robotics
Policy-gradient method
Reinforcement learning
Robotics and automation
Weight control
Whole-body movement
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a novel approach to acquire dynamic whole-body movements on humanoid robots focused on learning a control policy for the center of mass. A policy-gradient method is used to acquire a CoM movement as a control policy for achieving a desired dynamic task. A CoM-Jacobian-based redundancy resolution is then used to compute angular velocities for all joints in order to achieve a whole-body movement consistent with the CoM movement acquired through learning. To demonstrate the effectiveness of our method, we apply it in simulation to the learning of a strong punching movement on the Fujitsu humanoid robot, Hoap-2.
ISSN:1050-4729
2577-087X
DOI:10.1109/ROBOT.2007.363871